chapter 2 version 1 NRCS agg code
James Lin
8/6/2021
1 Set up
knitr::opts_chunk$set(
echo = T,
message = FALSE,
warning = FALSE
)1.1 1) Load packages
library(readxl)
library(dplyr)
library(tidyr)
library(ggplot2)
library(janitor)
library(grid)
library(ggthemes)
library(extrafont)
#font_import()
loadfonts(device = "win")
windowsFonts(Times = windowsFont("TT Times New Roman"))
library(lsmeans)
library(nlme)
library(car)
library(lme4)
library(multcomp)
library(lmerTest)
library(multcompView)
library(semPlot)
library(lavaan)
library(broom)
library(broom.mixed)
library(emmeans)1.2 2) Import data
#import data
soilhealth <- read_excel("3-29-21 part 8 nrcs soil health.xlsx")
#change column names
soilhealth <- soilhealth %>%
clean_names()
#str(soilhealth)
#View(soilhealth)
#convert variables to factors
soilhealth$nhorizon <- as.factor(soilhealth$nhorizon)
soilhealth$blk <- as.factor(soilhealth$blk)
soilhealth$horizon <- as.factor(soilhealth$horizon)
soilhealth$thorizon <- as.factor(soilhealth$thorizon)
soilhealth$rlanduse <- as.factor(soilhealth$rlanduse)
soilhealth$landuse <- as.factor(soilhealth$landuse)
soilhealth$prec <- as.factor(soilhealth$prec)
soilhealth$ag <- as.factor(soilhealth$ag)
soilhealth$tillage <- as.factor(soilhealth$tillage)
#convert variables to numeric
soilhealth$bdepth=as.numeric(soilhealth$bdepth)
soilhealth$precip <- as.numeric(soilhealth$precip)
soilhealth$t_np <- as.numeric(soilhealth$t_np)
soilhealth$to_cp <- as.numeric(soilhealth$to_cp)
soilhealth$ca <- as.numeric(soilhealth$ca)
soilhealth$cu <- as.numeric(soilhealth$cu)
soilhealth$mg <- as.numeric(soilhealth$mg)
soilhealth$mn <- as.numeric(soilhealth$mn)
soilhealth$na <- as.numeric(soilhealth$na)
soilhealth$p <- as.numeric(soilhealth$p)
soilhealth$p_h <- as.numeric(soilhealth$p_h)
soilhealth$k <- as.numeric(soilhealth$k)
soilhealth$zn <- as.numeric(soilhealth$zn)
soilhealth$fe <- as.numeric(soilhealth$fe)
#vartable(soilhealth)1.3 3) Data Wrangling
# removes ottawa
soilhealth1 <- soilhealth %>%
filter(location!="Ottawa")
soilhealth1$landuse<- factor(soilhealth1$landuse,
levels = c(1,2,3),
labels = c("AG", "EA", "NP"))
#str(soilhealth1)
soilhealth1 <- as.data.frame(soilhealth1)
# soilhealth2 <- soilhealth1
# soilhealth2 <- soilhealth2[c(1,5,9,29,33,37,57,61,65,85,89,93,109,113,117,137,141,145,165,169,173,189,193,197,213,217,221),]
# #soilhealth2
# keep nutrients
nut <- soilhealth1 %>%
dplyr::filter(location!="Ottawa") %>%
dplyr::select(location, treatment, bdepth, horizon, blk, replication, landuse, precip, clay, nh4, no3, t_np, to_cp, ca, cu, mg, mn, na, p, p_h, k, zn, fe, gwc) %>%
dplyr::mutate(cn=(to_cp/t_np), ca_g=(ca/1000))
#str(nut)
#summary(nut)
#vartable(nut)
# keeps aggregate data
agg <- soilhealth1 %>%
dplyr::select(location, treatment, bdepth, horizon, blk, replication, landuse, precip, x20wsa2000, x20wsa250, x20wsa53, x20wsa20, x20mwd, x5wsa2000, x5wsa250, x5wsa53, x5wsa20, x5mwd, nagg, bd, clay)
#str(agg)
#summary(agg)
#plot(agg)
#vartable(agg)
# Keep respiration data, enzymes, proteins
# normalize the enzyme distributions
#vartable(agg)
epr <- soilhealth1 %>%
dplyr::select(location, treatment, bdepth, horizon, blk, replication, landuse, precip, ac, glucosidase, glucosaminidase, acidphosphotase, alkphosphatase, arylsulfatase, phosphodiesterase, protein, respiration) %>%
dplyr::mutate(lnac=log(ac), lngluc=log(glucosidase), lnglucosam=log(glucosaminidase), lnacidp=log(acidphosphotase), lnalkp=log(alkphosphatase), lnary=log(arylsulfatase), lnpho=log(phosphodiesterase), lnprotein=log(protein), lngluc_glucosam= (lngluc/lnglucosam), lngluc_acidp= (lngluc/lnacidp), lngluc_alkp=(lngluc/lnalkp), lngluc_pho=(lngluc/lnpho), lngluc_ary=(lngluc/lnary))
#str(epr)
#vartable(epr)
ratios <- soilhealth1 %>%
dplyr::select(location, treatment, bdepth, horizon, blk, landuse, precip, replication, respiration, to_cg, t_nm, protein) %>%
dplyr::mutate(t_ng=(t_nm/1000), ptn=(protein/t_ng), rec=(respiration/to_cg))
#vartable(ratios)
#To deal with egative natural log values from enzymes, I added 1.1 to each variable.
epr2 <- soilhealth1 %>%
dplyr::select(location, treatment, bdepth, horizon, blk, landuse, precip, replication, ac, glucosidase, glucosaminidase, acidphosphotase, alkphosphatase, arylsulfatase, phosphodiesterase, protein, respiration) %>%
mutate(lnac=log(ac), lngluc=log(glucosidase*100), lnglucosam=log(glucosaminidase*100), lnacidp=log(acidphosphotase*100), lnalkp=log(alkphosphatase*100), lnary=log(arylsulfatase*100), lnpho=log(phosphodiesterase*100), lnprotein=log(protein), lngluc_glucosam= (lngluc/lnglucosam), lngluc_acidp= (lngluc/lnacidp), lngluc_alkp=(lngluc/lnalkp), lngluc_pho=(lngluc/lnpho), lngluc_ary=(lngluc/lnary))
#summary(epr1)1.4 4) Depth Wrangling
#remove IR from epr, epr2
epra <- epr %>%
filter(treatment!="IR")
epra2 <- epr2 %>%
filter(treatment!="IR")
#depth for biological
epra5 <- epra %>%
filter(bdepth==5)
epra10 <- epra %>%
filter(bdepth==10)
epra15 <- epra %>%
filter(bdepth==15)
#remove IR from nut
nutr <- nut %>%
filter(treatment!="IR")
#depth for chemical
nut5 <- nutr %>%
filter(bdepth==5)
nut10<- nutr %>%
filter(bdepth==10)
nut15<- nutr %>%
filter(bdepth==15)
#remove IR from agg
aggr <- agg %>%
filter(treatment!="IR")
#depth for phyisical
agg5 <- aggr %>%
filter(bdepth==5)
agg10 <- aggr %>%
filter(bdepth==10)
agg15 <- aggr %>%
filter(bdepth==15)
#depth for epr2 ratios
epra25 <- epra2 %>%
filter(bdepth==5)
epra210 <- epra2 %>%
filter(bdepth==10)
epra215 <- epra2 %>%
filter(bdepth==15)
#depth for ratios
ratio5 <- ratios %>%
filter(bdepth==5)
ratio10 <- ratios %>%
filter(bdepth==10)
ratio15 <- ratios %>%
filter(bdepth==15)1.5 5) Theme James
library(grid)
library(ggthemes)
#fcol <- c( "AG" = "black", "EA" = "grey40", "NP" = "grey90", "IR"="blue")
#kstate purple - 512888
fcol <- c( "AG" = "#FF3333", "EA" = "#FF9933", "NP" = "#512888", "IR"="#0033FF")
colsnp <- c( "AG" = "black", "EA" = "grey40", "NP" = "grey90")
pd <- position_dodge(0.1)
theme_James <- function(base_size=14, base_family="TT Times New Roman") {
(theme_foundation(base_size=base_size, base_family=base_family)+
theme_bw()+
theme(panel.background = element_rect(colour = NA),
plot.background = element_rect(colour = NA),
axis.title = element_text(color="black",size=rel(1.2)),
axis.text = element_text(color="black", size = 12),
legend.key = element_rect(colour = NA),
legend.spacing = unit(0, "cm"),
legend.text = element_text(size=12),
legend.title = element_blank(),
panel.grid = element_blank(),
plot.title = element_text(color="Black",size = rel(1.5),face = "bold",hjust = 0.5),
strip.text = element_text(color="Black",size = rel(1),face="bold")
))
}2 20 min Aggregate Graphs
2.1 0-5 cm 20 minutes
###20 mwd
agg5 <- aggr %>%
filter(bdepth==5)
agg10 <- aggr %>%
filter(bdepth==10)
agg15 <- aggr %>%
filter(bdepth==15)
x## [1] "0-5 cm"agg5$precip <- as.factor(agg5$precip)
x20mwd <- lmer(x20mwd ~ landuse*precip + (1|replication), data=agg5, na.action=na.omit)
anova(x20mwd, type=3)## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## landuse 10.6851 5.3426 2 27 46.2074 1.919e-09 ***
## precip 0.0037 0.0018 2 27 0.0160 0.9842
## landuse:precip 0.5627 0.1407 4 27 1.2166 0.3269
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1x20mwd_means_tp <- lsmeans(x20mwd, specs = "landuse", by = "precip")
#PWC
x20mwd_pwc_tp <- cld(x20mwd_means_tp, adjust = "none", Letters = letters, reversed = T)
#transforming it in a data frame to use on ggplot
x20mwd_pwc_tp <- as.data.frame(x20mwd_pwc_tp)
x20mwd_pwc_tp## landuse precip lsmean SE df lower.CL upper.CL .group
## 1 NP 472 1.6391185 0.1700156 27 1.29027523 1.9879618 a
## 2 EA 472 0.7012615 0.1700156 27 0.35241823 1.0501048 b
## 3 AG 472 0.6816877 0.1700156 27 0.33284448 1.0305310 b
## 4 NP 579 1.8859738 0.1700156 27 1.53713048 2.2348170 a
## 5 EA 579 0.7881320 0.1700156 27 0.43928873 1.1369753 b
## 6 AG 579 0.2889481 0.1700156 27 -0.05989515 0.6377914 c
## 7 NP 850 1.7101955 0.1700156 27 1.36135223 2.0590388 a
## 8 EA 850 0.9290419 0.1700156 27 0.58019863 1.2778852 b
## 9 AG 850 0.3925357 0.1700156 27 0.04369248 0.7413790 c#Determining the real SE
real_sex20mwd5cm <- agg5 %>%
dplyr::group_by(precip, landuse) %>%
dplyr::summarise(
n=n(),
mean=mean(x20mwd),
sd=sd(x20mwd)
) %>%
dplyr::mutate( se=sd/sqrt(n))
#add locations
df <- data.frame (location = c("Tribune", "Hays", "Manhattan"),
precip = c("472", "579", "850"))
df<- merge(df, real_sex20mwd5cm, by=c("precip"))
x20mwd5_pwc_tp_5v <- merge(x20mwd_pwc_tp, df, by=c("precip", "landuse"))
x20mwd5_pwc_tp_5v <- as.data.frame(x20mwd5_pwc_tp_5v)
x20mwd5_pwc_tp_5v## precip landuse lsmean SE df lower.CL upper.CL .group location
## 1 472 AG 0.6816877 0.1700156 27 0.33284448 1.0305310 b Tribune
## 2 472 EA 0.7012615 0.1700156 27 0.35241823 1.0501048 b Tribune
## 3 472 NP 1.6391185 0.1700156 27 1.29027523 1.9879618 a Tribune
## 4 579 AG 0.2889481 0.1700156 27 -0.05989515 0.6377914 c Hays
## 5 579 EA 0.7881320 0.1700156 27 0.43928873 1.1369753 b Hays
## 6 579 NP 1.8859738 0.1700156 27 1.53713048 2.2348170 a Hays
## 7 850 AG 0.3925357 0.1700156 27 0.04369248 0.7413790 c Manhattan
## 8 850 EA 0.9290419 0.1700156 27 0.58019863 1.2778852 b Manhattan
## 9 850 NP 1.7101955 0.1700156 27 1.36135223 2.0590388 a Manhattan
## n mean sd se
## 1 4 0.6816878 0.34067898 0.17033949
## 2 4 0.7012615 0.07939717 0.03969858
## 3 4 1.6391185 0.63652059 0.31826030
## 4 4 0.2889481 0.06823212 0.03411606
## 5 4 0.7881320 0.07579000 0.03789500
## 6 4 1.8859738 0.38793154 0.19396577
## 7 4 0.3925358 0.11290835 0.05645417
## 8 4 0.9290419 0.18911734 0.09455867
## 9 4 1.7101955 0.55105588 0.27552794x20mwd5_pwc_tp_5v$location_f =factor(x20mwd5_pwc_tp_5v$location, levels=c('Tribune', 'Hays', 'Manhattan'))
ggplot(data=x20mwd5_pwc_tp_5v, aes(x=landuse, y=lsmean, fill = landuse)) +
geom_bar(position=position_dodge(), stat="identity", colour = "black") +
geom_errorbar(aes(ymin=lsmean-se, ymax=lsmean+se),
width=.2, # Width of the error bars
position=position_dodge(.9)) +
scale_y_continuous(limits=c(0,3)) +
facet_wrap(facets=vars(location_f), strip.position="bottom") +
xlab("")+
facet_wrap(facets=vars(location_f), strip.position="bottom") +
scale_fill_manual(values = colsnp) +
ggtitle("20 Minute MWD 0-5 cm by Land use and Precipitation")+
theme_James() +
theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
panel.background = element_blank(), axis.line = element_line(colour = "black"),
panel.border = element_rect(colour = "black", fill=NA, size=0.5),
strip.background=element_rect(size=0.5, colour = "black"),
axis.text.x=element_blank(),
axis.ticks.x=element_blank(),
legend.position= c(0.1,0.85)) +
labs(y=" Mean Weight Diameter (mm)") +
geom_label(aes(label=trimws(.group), y = lsmean+.5),
label.padding = unit(.3,"lines"), show.legend=NA , label.size = NA, fill=NA, font="bold") +
guides(fill = guide_legend(override.aes = aes(label="")))
###8-2 mm
agg5 <- aggr %>%
filter(bdepth==5)
agg10 <- aggr %>%
filter(bdepth==10)
agg15 <- aggr %>%
filter(bdepth==15)
x## [1] "0-5 cm"agg5$precip <- as.factor(agg5$precip)
x20wsa2000 <- lmer(x20wsa2000 ~ treatment*precip + (1|replication), data=agg5, na.action=na.omit)
anova(x20wsa2000, type=3)## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## treatment 3614.3 1807.14 2 27 36.3110 2.216e-08 ***
## precip 17.6 8.80 2 27 0.1769 0.8388
## treatment:precip 210.9 52.71 4 27 1.0592 0.3957
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1x20wsa2000_means_tp <- lsmeans(x20wsa2000, specs = "treatment", by = "precip")
#PWC
x20wsa2000_pwc_tp <- cld(x20wsa2000_means_tp, adjust = "none", Letters = letters, reversed = T)
#transforming it in a data frame to use on ggplot
x20wsa2000_pwc_tp <- as.data.frame(x20wsa2000_pwc_tp)
#add locations
df <- data.frame (location = c("Tribune", "Hays", "Manhattan"),
precip = c("472", "579", "850"))
x20wsa2000p<- merge(df, x20wsa2000_pwc_tp, by=c("precip"))
x20wsa2000p$location_f =factor(x20wsa2000p$location, levels=c('Tribune', 'Hays', 'Manhattan'))
x20wsa2000p## precip location treatment lsmean SE df lower.CL upper.CL .group
## 1 472 Tribune NP 26.3313434 3.527336 27 19.093849 33.568838 a
## 2 472 Tribune EA 8.8448459 3.527336 27 1.607351 16.082341 b
## 3 472 Tribune AG 8.7304187 3.527336 27 1.492924 15.967914 b
## 4 579 Hays NP 30.8387700 3.527336 27 23.601275 38.076265 a
## 5 579 Hays EA 9.3305850 3.527336 27 2.093090 16.568080 b
## 6 579 Hays AG 0.9315208 3.527336 27 -6.305974 8.169016 b
## 7 850 Manhattan NP 25.3077401 3.527336 27 18.070245 32.545235 a
## 8 850 Manhattan EA 11.4886335 3.527336 27 4.251139 18.726128 b
## 9 850 Manhattan AG 1.9782694 3.527336 27 -5.259225 9.215764 b
## location_f
## 1 Tribune
## 2 Tribune
## 3 Tribune
## 4 Hays
## 5 Hays
## 6 Hays
## 7 Manhattan
## 8 Manhattan
## 9 Manhattan2.1.1 2-0.250 mm
agg5 <- aggr %>%
filter(bdepth==5)
agg10 <- aggr %>%
filter(bdepth==10)
agg15 <- aggr %>%
filter(bdepth==15)
x## [1] "0-5 cm"agg5$precip <- as.factor(agg5$precip)
x20wsa250 <- lmer(x20wsa250 ~ treatment*precip + (1|replication), data=agg5, na.action=na.omit)
anova(x20wsa250, type=3)## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## treatment 1511.80 755.90 2 20.3129 30.6394 7.358e-07 ***
## precip 330.72 165.36 2 8.5003 6.7026 0.01789 *
## treatment:precip 117.76 29.44 4 20.3129 1.1933 0.34379
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1x20wsa250_means_tp <- lsmeans(x20wsa250, specs = "treatment", by = "precip")
#PWC
x20wsa250_pwc_tp <- cld(x20wsa250_means_tp, adjust = "none", Letters = letters, reversed = T)
#transforming it in a data frame to use on ggplot
x20wsa250_pwc_tp <- as.data.frame(x20wsa250_pwc_tp)
#add locations
df <- data.frame (location = c("Tribune", "Hays", "Manhattan"),
precip = c("472", "579", "850"))
x20wsa250p<- merge(df, x20wsa250_pwc_tp, by=c("precip"))
x20wsa250p$location_f =factor(x20wsa250p$location, levels=c('Tribune', 'Hays', 'Manhattan'))
x20wsa250p## precip location treatment lsmean SE df lower.CL upper.CL
## 1 472 Tribune NP 25.60527 2.634026 25.7468 20.188356 31.02218
## 2 472 Tribune EA 16.27820 2.634026 25.7468 10.861289 21.69511
## 3 472 Tribune AG 14.44550 2.634026 25.7468 9.028589 19.86241
## 4 579 Hays NP 28.53917 2.634026 25.7468 23.122260 33.95608
## 5 579 Hays EA 22.02193 2.634026 25.7468 16.605020 27.43884
## 6 579 Hays AG 11.97343 2.634026 25.7468 6.556520 17.39034
## 7 850 Manhattan NP 37.24528 2.634026 25.7468 31.828368 42.66219
## 8 850 Manhattan EA 24.97329 2.634026 25.7468 19.556377 30.39020
## 9 850 Manhattan AG 17.62782 2.634026 25.7468 12.210914 23.04474
## .group location_f
## 1 a Tribune
## 2 b Tribune
## 3 b Tribune
## 4 a Hays
## 5 a Hays
## 6 b Hays
## 7 a Manhattan
## 8 b Manhattan
## 9 c Manhattan2.1.2 0.250-0.053 mm
agg5 <- aggr %>%
filter(bdepth==5)
agg10 <- aggr %>%
filter(bdepth==10)
agg15 <- aggr %>%
filter(bdepth==15)
x## [1] "0-5 cm"agg5$precip <- as.factor(agg5$precip)
x20wsa53 <- lmer(x20wsa53 ~ treatment*precip + (1|replication), data=agg5, na.action=na.omit)
anova(x20wsa53, type=3)## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## treatment 11892.9 5946.5 2 20.8198 136.2712 1.096e-12 ***
## precip 45.9 22.9 2 8.7658 0.5255 0.60879
## treatment:precip 631.3 157.8 4 20.8198 3.6170 0.02169 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1x20wsa53_means_tp <- lsmeans(x20wsa53, specs = "treatment", by = "precip")
x20wsa53_means_tp## precip = 472:
## treatment lsmean SE df lower.CL upper.CL
## AG 53.1 3.74 22.8 45.34 60.8
## EA 49.1 3.74 22.8 41.40 56.9
## NP 22.3 3.74 22.8 14.56 30.0
##
## precip = 579:
## treatment lsmean SE df lower.CL upper.CL
## AG 69.8 3.74 22.8 62.06 77.5
## EA 47.9 3.74 22.8 40.20 55.7
## NP 14.9 3.74 22.8 7.18 22.6
##
## precip = 850:
## treatment lsmean SE df lower.CL upper.CL
## AG 61.2 3.74 22.8 53.43 68.9
## EA 47.4 3.74 22.8 39.65 55.1
## NP 16.6 3.74 22.8 8.83 24.3
##
## Degrees-of-freedom method: kenward-roger
## Confidence level used: 0.95#PWC
x20wsa53_pwc_tp <- cld(x20wsa53_means_tp, adjust = "none", Letters = letters, reversed = T)
#transforming it in a data frame to use on ggplot
x20wsa53_pwc_tp <- as.data.frame(x20wsa53_pwc_tp)
#add locations
df <- data.frame (location = c("Tribune", "Hays", "Manhattan"),
precip = c("472", "579", "850"))
x20wsa53p<- merge(df, x20wsa53_pwc_tp, by=c("precip"))
x20wsa53p$location_f =factor(x20wsa53p$location, levels=c('Tribune', 'Hays', 'Manhattan'))
x20wsa53p## precip location treatment lsmean SE df lower.CL upper.CL
## 1 472 Tribune AG 53.07399 3.736594 22.78911 45.340296 60.80768
## 2 472 Tribune EA 49.13078 3.736594 22.78911 41.397089 56.86447
## 3 472 Tribune NP 22.29726 3.736594 22.78911 14.563572 30.03096
## 4 579 Hays AG 69.79728 3.736594 22.78911 62.063591 77.53098
## 5 579 Hays EA 47.93665 3.736594 22.78911 40.202952 55.67034
## 6 579 Hays NP 14.90930 3.736594 22.78911 7.175602 22.64299
## 7 850 Manhattan AG 61.16504 3.736594 22.78911 53.431345 68.89873
## 8 850 Manhattan EA 47.38140 3.736594 22.78911 39.647708 55.11509
## 9 850 Manhattan NP 16.56350 3.736594 22.78911 8.829805 24.29719
## .group location_f
## 1 a Tribune
## 2 a Tribune
## 3 b Tribune
## 4 a Hays
## 5 b Hays
## 6 c Hays
## 7 a Manhattan
## 8 b Manhattan
## 9 c Manhattan2.1.3 0.053-0.02 mm
agg5 <- aggr %>%
filter(bdepth==5)
agg10 <- aggr %>%
filter(bdepth==10)
agg15 <- aggr %>%
filter(bdepth==15)
x## [1] "0-5 cm"agg5$precip <- as.factor(agg5$precip)
x20wsa20 <- lmer(x20wsa20 ~ treatment*precip + (1|replication), data=agg5, na.action=na.omit)
anova(x20wsa20, type=3)## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## treatment 126.572 63.286 2 27 26.3225 4.548e-07 ***
## precip 14.220 7.110 2 27 2.9573 0.06897 .
## treatment:precip 2.103 0.526 4 27 0.2187 0.92567
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1x20wsa20_means_tp <- lsmeans(x20wsa20, specs = "treatment", by = "precip")
x20wsa20_means_tp## precip = 472:
## treatment lsmean SE df lower.CL upper.CL
## AG 6.16 0.775 27 4.567 7.75
## EA 3.99 0.775 27 2.399 5.58
## NP 1.95 0.775 27 0.359 3.54
##
## precip = 579:
## treatment lsmean SE df lower.CL upper.CL
## AG 5.28 0.775 27 3.692 6.87
## EA 3.38 0.775 27 1.784 4.97
## NP 1.05 0.775 27 -0.543 2.64
##
## precip = 850:
## treatment lsmean SE df lower.CL upper.CL
## AG 7.25 0.775 27 5.654 8.84
## EA 5.14 0.775 27 3.554 6.74
## NP 1.93 0.775 27 0.342 3.52
##
## Degrees-of-freedom method: kenward-roger
## Confidence level used: 0.95#PWC
x20wsa20_pwc_tp <- cld(x20wsa20_means_tp, adjust = "none", Letters = letters, reversed = T)
x20wsa20_pwc_tp## precip = 472:
## treatment lsmean SE df lower.CL upper.CL .group
## AG 6.16 0.775 27 4.567 7.75 a
## EA 3.99 0.775 27 2.399 5.58 ab
## NP 1.95 0.775 27 0.359 3.54 b
##
## precip = 579:
## treatment lsmean SE df lower.CL upper.CL .group
## AG 5.28 0.775 27 3.692 6.87 a
## EA 3.38 0.775 27 1.784 4.97 a
## NP 1.05 0.775 27 -0.543 2.64 b
##
## precip = 850:
## treatment lsmean SE df lower.CL upper.CL .group
## AG 7.25 0.775 27 5.654 8.84 a
## EA 5.14 0.775 27 3.554 6.74 a
## NP 1.93 0.775 27 0.342 3.52 b
##
## Degrees-of-freedom method: kenward-roger
## Confidence level used: 0.95
## significance level used: alpha = 0.05
## NOTE: Compact letter displays can be misleading
## because they show NON-findings rather than findings.
## Consider using 'pairs()', 'pwpp()', or 'pwpm()' instead.#transforming it in a data frame to use on ggplot
x20wsa20_pwc_tp <- as.data.frame(x20wsa20_pwc_tp)
x20wsa20_pwc_tp## treatment precip lsmean SE df lower.CL upper.CL .group
## 3 AG 472 6.1575 0.7752837 27 4.5667492 7.748251 a
## 2 EA 472 3.9900 0.7752837 27 2.3992492 5.580751 ab
## 1 NP 472 1.9500 0.7752837 27 0.3592492 3.540751 b
## 6 AG 579 5.2825 0.7752837 27 3.6917492 6.873251 a
## 5 EA 579 3.3750 0.7752837 27 1.7842492 4.965751 a
## 4 NP 579 1.0475 0.7752837 27 -0.5432508 2.638251 b
## 9 AG 850 7.2450 0.7752837 27 5.6542492 8.835751 a
## 8 EA 850 5.1450 0.7752837 27 3.5542492 6.735751 a
## 7 NP 850 1.9325 0.7752837 27 0.3417492 3.523251 b#add locations
df <- data.frame (location = c("Tribune", "Hays", "Manhattan"),
precip = c("472", "579", "850"))
x20wsa20p<- merge(df, x20wsa20_pwc_tp, by=c("precip"))
x20wsa20p$location_f =factor(x20wsa20p$location, levels=c('Tribune', 'Hays', 'Manhattan'))
x20wsa20p## precip location treatment lsmean SE df lower.CL upper.CL .group
## 1 472 Tribune AG 6.1575 0.7752837 27 4.5667492 7.748251 a
## 2 472 Tribune EA 3.9900 0.7752837 27 2.3992492 5.580751 ab
## 3 472 Tribune NP 1.9500 0.7752837 27 0.3592492 3.540751 b
## 4 579 Hays AG 5.2825 0.7752837 27 3.6917492 6.873251 a
## 5 579 Hays EA 3.3750 0.7752837 27 1.7842492 4.965751 a
## 6 579 Hays NP 1.0475 0.7752837 27 -0.5432508 2.638251 b
## 7 850 Manhattan AG 7.2450 0.7752837 27 5.6542492 8.835751 a
## 8 850 Manhattan EA 5.1450 0.7752837 27 3.5542492 6.735751 a
## 9 850 Manhattan NP 1.9325 0.7752837 27 0.3417492 3.523251 b
## location_f
## 1 Tribune
## 2 Tribune
## 3 Tribune
## 4 Hays
## 5 Hays
## 6 Hays
## 7 Manhattan
## 8 Manhattan
## 9 Manhattan2.2 5-10 cm 20 minutes
###8-2 mm
agg5 <- aggr %>%
filter(bdepth==5)
agg10 <- aggr %>%
filter(bdepth==10)
agg15 <- aggr %>%
filter(bdepth==15)
x## [1] "0-5 cm"agg10$precip <- as.factor(agg10$precip)
x20wsa200010 <- lmer(x20wsa2000 ~ treatment*precip + (1|replication), data=agg10, na.action=na.omit)
anova(x20wsa200010, type=3)## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## treatment 2616.00 1308.00 2 27 75.5924 8.643e-12 ***
## precip 12.68 6.34 2 27 0.3665 0.696579
## treatment:precip 311.07 77.77 4 27 4.4944 0.006514 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1x20wsa200010_means_tp <- lsmeans(x20wsa200010, specs = "treatment", by = "precip")
#PWC
x20wsa200010_pwc_tp <- cld(x20wsa200010_means_tp, adjust = "none", Letters = letters, reversed = T)
#transforming it in a data frame to use on ggplot
x20wsa200010_pwc_tp <- as.data.frame(x20wsa200010_pwc_tp)
#add locations
df <- data.frame (location = c("Tribune", "Hays", "Manhattan"),
precip = c("472", "579", "850"))
x20wsa200010p<- merge(df, x20wsa200010_pwc_tp, by=c("precip"))
x20wsa200010p$location_f =factor(x20wsa200010p$location, levels=c('Tribune', 'Hays', 'Manhattan'))
x20wsa200010p## precip location treatment lsmean SE df lower.CL upper.CL .group
## 1 472 Tribune NP 19.874634 2.079862 27 15.60710952 24.142159 a
## 2 472 Tribune AG 7.158672 2.079862 27 2.89114749 11.426197 b
## 3 472 Tribune EA 2.303734 2.079862 27 -1.96379035 6.571259 b
## 4 579 Hays NP 27.933098 2.079862 27 23.66557284 32.200622 a
## 5 579 Hays EA 4.312530 2.079862 27 0.04500509 8.580054 b
## 6 579 Hays AG 1.369402 2.079862 27 -2.89812306 5.636926 b
## 7 850 Manhattan NP 19.539639 2.079862 27 15.27211447 23.807164 a
## 8 850 Manhattan EA 8.197339 2.079862 27 3.92981461 12.464864 b
## 9 850 Manhattan AG 3.003322 2.079862 27 -1.26420295 7.270846 b
## location_f
## 1 Tribune
## 2 Tribune
## 3 Tribune
## 4 Hays
## 5 Hays
## 6 Hays
## 7 Manhattan
## 8 Manhattan
## 9 Manhattan2.2.1 2-0.250 mm
agg5 <- aggr %>%
filter(bdepth==5)
agg10 <- aggr %>%
filter(bdepth==10)
agg15 <- aggr %>%
filter(bdepth==15)
x## [1] "0-5 cm"agg10$precip <- as.factor(agg10$precip)
x20wsa25010 <- lmer(x20wsa250 ~ treatment*precip + (1|replication), data=agg10, na.action=na.omit)
anova(x20wsa25010, type=3)## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## treatment 547.76 273.88 2 24.547 3.0591 0.06513 .
## precip 319.85 159.93 2 22.179 1.7863 0.19085
## treatment:precip 1341.29 335.32 4 23.861 3.7454 0.01673 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1x20wsa25010_means_tp <- lsmeans(x20wsa25010, specs = "treatment", by = "precip")
#PWC
x20wsa25010_pwc_tp <- cld(x20wsa25010_means_tp, adjust = "none", Letters = letters, reversed = T)
#transforming it in a data frame to use on ggplot
x20wsa25010_pwc_tp <- as.data.frame(x20wsa25010_pwc_tp)
#add locations
df <- data.frame (location = c("Tribune", "Hays", "Manhattan"),
precip = c("472", "579", "850"))
x20wsa25010p<- merge(df, x20wsa25010_pwc_tp, by=c("precip"))
x20wsa25010p$location_f =factor(x20wsa25010p$location, levels=c('Tribune', 'Hays', 'Manhattan'))
x20wsa25010p## precip location treatment lsmean SE df lower.CL upper.CL
## 1 472 Tribune NP 33.76226 4.905017 26.37839 23.686887 43.83763
## 2 472 Tribune AG 31.38025 4.905017 26.37839 21.304875 41.45562
## 3 472 Tribune EA 15.88541 4.905017 26.37839 5.810033 25.96078
## 4 579 Hays EA 29.76832 4.905017 26.37839 19.692944 39.84369
## 5 579 Hays NP 22.88141 4.905017 26.37839 12.806039 32.95679
## 6 579 Hays AG 12.44605 4.905017 26.37839 2.370679 22.52143
## 7 850 Manhattan NP 35.21192 4.905017 26.37839 25.136550 45.28730
## 8 850 Manhattan EA 31.98805 4.905017 26.37839 21.912672 42.06342
## 9 850 Manhattan AG 19.00936 4.905017 26.37839 8.933983 29.08473
## .group location_f
## 1 a Tribune
## 2 a Tribune
## 3 b Tribune
## 4 a Hays
## 5 ab Hays
## 6 b Hays
## 7 a Manhattan
## 8 ab Manhattan
## 9 b Manhattan2.2.2 0.250-0.053 mm
agg5 <- aggr %>%
filter(bdepth==5)
agg10 <- aggr %>%
filter(bdepth==10)
agg15 <- aggr %>%
filter(bdepth==15)
x## [1] "0-5 cm"agg10$precip <- as.factor(agg10$precip)
x20wsa5310 <- lmer(x20wsa53 ~ treatment*precip + (1|replication), data=agg10, na.action=na.omit)
anova(x20wsa5310, type=3)## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## treatment 5648.5 2824.26 2 24.246 39.1889 2.533e-08 ***
## precip 75.7 37.83 2 16.940 0.5250 0.600891
## treatment:precip 1338.3 334.58 4 22.291 4.6426 0.007072 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1x20wsa5310_means_tp <- lsmeans(x20wsa5310, specs = "treatment", by = "precip")
x20wsa5310_means_tp## precip = 472:
## treatment lsmean SE df lower.CL upper.CL
## AG 40.3 4.91 21 30.1 50.5
## EA 60.5 4.91 21 50.3 70.7
## NP 24.3 4.91 21 14.1 34.5
##
## precip = 579:
## treatment lsmean SE df lower.CL upper.CL
## AG 61.0 4.91 21 50.8 71.2
## EA 47.5 4.91 21 37.3 57.7
## NP 28.4 4.91 21 18.2 38.6
##
## precip = 850:
## treatment lsmean SE df lower.CL upper.CL
## AG 60.5 4.91 21 50.3 70.7
## EA 45.0 4.91 21 34.8 55.2
## NP 23.6 4.91 21 13.4 33.8
##
## Degrees-of-freedom method: kenward-roger
## Confidence level used: 0.95#PWC
x20wsa5310_pwc_tp <- cld(x20wsa5310_means_tp, adjust = "none", Letters = letters, reversed = T)
#transforming it in a data frame to use on ggplot
x20wsa5310_pwc_tp <- as.data.frame(x20wsa5310_pwc_tp)
#add locations
df <- data.frame (location = c("Tribune", "Hays", "Manhattan"),
precip = c("472", "579", "850"))
x20wsa5310p<- merge(df, x20wsa5310_pwc_tp, by=c("precip"))
x20wsa5310p$location_f =factor(x20wsa5310p$location, levels=c('Tribune', 'Hays', 'Manhattan'))
x20wsa5310p## precip location treatment lsmean SE df lower.CL upper.CL
## 1 472 Tribune EA 60.53863 4.905302 20.96793 50.33654 70.74071
## 2 472 Tribune AG 40.25275 4.905302 20.96793 30.05067 50.45484
## 3 472 Tribune NP 24.33689 4.905302 20.96793 14.13481 34.53898
## 4 579 Hays AG 61.04155 4.905302 20.96793 50.83947 71.24364
## 5 579 Hays EA 47.54742 4.905302 20.96793 37.34533 57.74950
## 6 579 Hays NP 28.36159 4.905302 20.96793 18.15950 38.56367
## 7 850 Manhattan AG 60.48042 4.905302 20.96793 50.27834 70.68251
## 8 850 Manhattan EA 45.04338 4.905302 20.96793 34.84130 55.24547
## 9 850 Manhattan NP 23.59988 4.905302 20.96793 13.39779 33.80196
## .group location_f
## 1 a Tribune
## 2 b Tribune
## 3 c Tribune
## 4 a Hays
## 5 b Hays
## 6 c Hays
## 7 a Manhattan
## 8 b Manhattan
## 9 c Manhattan2.2.3 0.053-0.02 mm
agg5 <- aggr %>%
filter(bdepth==5)
agg10 <- aggr %>%
filter(bdepth==10)
agg15 <- aggr %>%
filter(bdepth==15)
x## [1] "0-5 cm"agg10$precip <- as.factor(agg10$precip)
x20wsa2010 <- lmer(x20wsa20 ~ treatment*precip + (1|replication), data=agg10, na.action=na.omit)
anova(x20wsa2010, type=3)## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## treatment 79.773 39.886 2 27 22.0949 2.069e-06 ***
## precip 4.560 2.280 2 27 1.2630 0.2989752
## treatment:precip 55.436 13.859 4 27 7.6771 0.0002882 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1x20wsa2010_means_tp <- lsmeans(x20wsa2010, specs = "treatment", by = "precip")
x20wsa2010_means_tp## precip = 472:
## treatment lsmean SE df lower.CL upper.CL
## AG 4.11 0.672 27 2.729 5.49
## EA 5.41 0.672 27 4.032 6.79
## NP 2.18 0.672 27 0.804 3.56
##
## precip = 579:
## treatment lsmean SE df lower.CL upper.CL
## AG 8.78 0.672 27 7.399 10.16
## EA 3.78 0.672 27 2.399 5.16
## NP 1.76 0.672 27 0.379 3.14
##
## precip = 850:
## treatment lsmean SE df lower.CL upper.CL
## AG 4.81 0.672 27 3.434 6.19
## EA 5.05 0.672 27 3.669 6.43
## NP 3.04 0.672 27 1.662 4.42
##
## Degrees-of-freedom method: kenward-roger
## Confidence level used: 0.95#PWC
x20wsa2010_pwc_tp <- cld(x20wsa2010_means_tp, adjust = "none", Letters = letters, reversed = T)
x20wsa2010_pwc_tp## precip = 472:
## treatment lsmean SE df lower.CL upper.CL .group
## EA 5.41 0.672 27 4.032 6.79 a
## AG 4.11 0.672 27 2.729 5.49 ab
## NP 2.18 0.672 27 0.804 3.56 b
##
## precip = 579:
## treatment lsmean SE df lower.CL upper.CL .group
## AG 8.78 0.672 27 7.399 10.16 a
## EA 3.78 0.672 27 2.399 5.16 b
## NP 1.76 0.672 27 0.379 3.14 c
##
## precip = 850:
## treatment lsmean SE df lower.CL upper.CL .group
## EA 5.05 0.672 27 3.669 6.43 a
## AG 4.81 0.672 27 3.434 6.19 ab
## NP 3.04 0.672 27 1.662 4.42 b
##
## Degrees-of-freedom method: kenward-roger
## Confidence level used: 0.95
## significance level used: alpha = 0.05
## NOTE: Compact letter displays can be misleading
## because they show NON-findings rather than findings.
## Consider using 'pairs()', 'pwpp()', or 'pwpm()' instead.#transforming it in a data frame to use on ggplot
x20wsa2010_pwc_tp <- as.data.frame(x20wsa2010_pwc_tp)
x20wsa2010_pwc_tp## treatment precip lsmean SE df lower.CL upper.CL .group
## 3 EA 472 5.4100 0.671795 27 4.0315905 6.78841 a
## 1 AG 472 4.1075 0.671795 27 2.7290905 5.48591 ab
## 2 NP 472 2.1825 0.671795 27 0.8040905 3.56091 b
## 6 AG 579 8.7775 0.671795 27 7.3990905 10.15591 a
## 5 EA 579 3.7775 0.671795 27 2.3990905 5.15591 b
## 4 NP 579 1.7575 0.671795 27 0.3790905 3.13591 c
## 9 EA 850 5.0475 0.671795 27 3.6690905 6.42591 a
## 7 AG 850 4.8125 0.671795 27 3.4340905 6.19091 ab
## 8 NP 850 3.0400 0.671795 27 1.6615905 4.41841 b#add locations
df <- data.frame (location = c("Tribune", "Hays", "Manhattan"),
precip = c("472", "579", "850"))
x20wsa2010p<- merge(df, x20wsa2010_pwc_tp, by=c("precip"))
x20wsa2010p$location_f =factor(x20wsa2010p$location, levels=c('Tribune', 'Hays', 'Manhattan'))
x20wsa2010p## precip location treatment lsmean SE df lower.CL upper.CL .group
## 1 472 Tribune EA 5.4100 0.671795 27 4.0315905 6.78841 a
## 2 472 Tribune AG 4.1075 0.671795 27 2.7290905 5.48591 ab
## 3 472 Tribune NP 2.1825 0.671795 27 0.8040905 3.56091 b
## 4 579 Hays AG 8.7775 0.671795 27 7.3990905 10.15591 a
## 5 579 Hays EA 3.7775 0.671795 27 2.3990905 5.15591 b
## 6 579 Hays NP 1.7575 0.671795 27 0.3790905 3.13591 c
## 7 850 Manhattan EA 5.0475 0.671795 27 3.6690905 6.42591 a
## 8 850 Manhattan AG 4.8125 0.671795 27 3.4340905 6.19091 ab
## 9 850 Manhattan NP 3.0400 0.671795 27 1.6615905 4.41841 b
## location_f
## 1 Tribune
## 2 Tribune
## 3 Tribune
## 4 Hays
## 5 Hays
## 6 Hays
## 7 Manhattan
## 8 Manhattan
## 9 Manhattan2.3 10-15 cm 20 minutes
###8-2 mm
agg5 <- aggr %>%
filter(bdepth==5)
agg10 <- aggr %>%
filter(bdepth==10)
agg15 <- aggr %>%
filter(bdepth==15)
x## [1] "0-5 cm"agg15$precip <- as.factor(agg15$precip)
x20wsa200015 <- lmer(x20wsa2000 ~ treatment*precip + (1|replication), data=agg15, na.action=na.omit)
anova(x20wsa200015, type=3)## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## treatment 3708.8 1854.41 2 27 128.1703 1.649e-14 ***
## precip 46.3 23.17 2 27 1.6012 0.2202
## treatment:precip 41.8 10.45 4 27 0.7222 0.5844
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1x20wsa200015_means_tp <- lsmeans(x20wsa200015, specs = "treatment", by = "precip")
#PWC
x20wsa200015_pwc_tp <- cld(x20wsa200015_means_tp, adjust = "none", Letters = letters, reversed = T)
#transforming it in a data frame to use on ggplot
x20wsa200015_pwc_tp <- as.data.frame(x20wsa200015_pwc_tp)
#add locations
df <- data.frame (location = c("Tribune", "Hays", "Manhattan"),
precip = c("472", "579", "850"))
x20wsa200015p<- merge(df, x20wsa200015_pwc_tp, by=c("precip"))
x20wsa200015p$location_f =factor(x20wsa200015p$location, levels=c('Tribune', 'Hays', 'Manhattan'))
x20wsa200015p## precip location treatment lsmean SE df lower.CL upper.CL .group
## 1 472 Tribune NP 26.297002 1.901863 27 22.3947003 30.199303 a
## 2 472 Tribune AG 7.344079 1.901863 27 3.4417780 11.246381 b
## 3 472 Tribune EA 3.058975 1.901863 27 -0.8433266 6.961276 b
## 4 579 Hays NP 23.871558 1.901863 27 19.9692562 27.773859 a
## 5 579 Hays EA 2.561610 1.901863 27 -1.3406916 6.463911 b
## 6 579 Hays AG 1.931631 1.901863 27 -1.9706708 5.833932 b
## 7 850 Manhattan NP 25.368150 1.901863 27 21.4658488 29.270451 a
## 8 850 Manhattan EA 4.378598 1.901863 27 0.4762962 8.280899 b
## 9 850 Manhattan AG 2.653159 1.901863 27 -1.2491423 6.555460 b
## location_f
## 1 Tribune
## 2 Tribune
## 3 Tribune
## 4 Hays
## 5 Hays
## 6 Hays
## 7 Manhattan
## 8 Manhattan
## 9 Manhattan2.3.1 2-0.250 mm
agg5 <- aggr %>%
filter(bdepth==5)
agg10 <- aggr %>%
filter(bdepth==10)
agg15 <- aggr %>%
filter(bdepth==15)
x## [1] "0-5 cm"agg15$precip <- as.factor(agg15$precip)
x20wsa25015 <- lmer(x20wsa250 ~ treatment*precip + (1|replication), data=agg15, na.action=na.omit)
anova(x20wsa25015, type=3)## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## treatment 832.09 416.05 2 22.322 4.4308 0.02396 *
## precip 253.13 126.56 2 11.356 1.3479 0.29837
## treatment:precip 396.69 99.17 4 22.322 1.0562 0.40112
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1x20wsa25015_means_tp <- lsmeans(x20wsa25015, specs = "treatment", by = "precip")
#PWC
x20wsa25015_pwc_tp <- cld(x20wsa25015_means_tp, adjust = "none", Letters = letters, reversed = T)
#transforming it in a data frame to use on ggplot
x20wsa25015_pwc_tp <- as.data.frame(x20wsa25015_pwc_tp)
#add locations
df <- data.frame (location = c("Tribune", "Hays", "Manhattan"),
precip = c("472", "579", "850"))
x20wsa25015p<- merge(df, x20wsa25015_pwc_tp, by=c("precip"))
x20wsa25015p$location_f =factor(x20wsa25015p$location, levels=c('Tribune', 'Hays', 'Manhattan'))
x20wsa25015p## precip location treatment lsmean SE df lower.CL upper.CL
## 1 472 Tribune NP 31.52114 5.299915 24.42448 20.592709 42.44958
## 2 472 Tribune AG 27.33366 5.299915 24.42448 16.405226 38.26210
## 3 472 Tribune EA 15.88228 5.299915 24.42448 4.953841 26.81071
## 4 579 Hays AG 32.94085 5.299915 24.42448 22.012414 43.86929
## 5 579 Hays NP 23.26334 5.299915 24.42448 12.334906 34.19178
## 6 579 Hays EA 18.86667 5.299915 24.42448 7.938236 29.79511
## 7 850 Manhattan NP 37.56309 5.299915 24.42448 26.634649 48.49152
## 8 850 Manhattan AG 29.49422 5.299915 24.42448 18.565782 40.42265
## 9 850 Manhattan EA 25.79500 5.299915 24.42448 14.866564 36.72344
## .group location_f
## 1 a Tribune
## 2 ab Tribune
## 3 b Tribune
## 4 a Hays
## 5 a Hays
## 6 a Hays
## 7 a Manhattan
## 8 a Manhattan
## 9 a Manhattan2.3.2 0.250-0.053 mm
agg5 <- aggr %>%
filter(bdepth==5)
agg10 <- aggr %>%
filter(bdepth==10)
agg15 <- aggr %>%
filter(bdepth==15)
x## [1] "0-5 cm"agg15$precip <- as.factor(agg15$precip)
x20wsa5315 <- lmer(x20wsa53 ~ treatment*precip + (1|replication), data=agg15, na.action=na.omit)
anova(x20wsa5315, type=3)## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## treatment 5954.3 2977.14 2 22.126 25.8975 1.601e-06 ***
## precip 236.0 117.98 2 11.493 1.0263 0.3890
## treatment:precip 588.3 147.08 4 22.126 1.2794 0.3081
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1x20wsa5315_means_tp <- lsmeans(x20wsa5315, specs = "treatment", by = "precip")
x20wsa5315_means_tp## precip = 472:
## treatment lsmean SE df lower.CL upper.CL
## AG 43.9 5.59 26.4 32.38 55.3
## EA 51.1 5.59 26.4 39.65 62.6
## NP 20.9 5.59 26.4 9.40 32.3
##
## precip = 579:
## treatment lsmean SE df lower.CL upper.CL
## AG 44.0 5.59 26.4 32.56 55.5
## EA 60.0 5.59 26.4 48.51 71.5
## NP 32.7 5.59 26.4 21.21 44.2
##
## precip = 850:
## treatment lsmean SE df lower.CL upper.CL
## AG 54.0 5.59 26.4 42.57 65.5
## EA 52.4 5.59 26.4 40.89 63.8
## NP 19.5 5.59 26.4 7.98 30.9
##
## Degrees-of-freedom method: kenward-roger
## Confidence level used: 0.95#PWC
x20wsa5315_pwc_tp <- cld(x20wsa5315_means_tp, adjust = "none", Letters = letters, reversed = T)
#transforming it in a data frame to use on ggplot
x20wsa5315_pwc_tp <- as.data.frame(x20wsa5315_pwc_tp)
#add locations
df <- data.frame (location = c("Tribune", "Hays", "Manhattan"),
precip = c("472", "579", "850"))
x20wsa5315p<- merge(df, x20wsa5315_pwc_tp, by=c("precip"))
x20wsa5315p$location_f =factor(x20wsa5315p$location, levels=c('Tribune', 'Hays', 'Manhattan'))
x20wsa5315p## precip location treatment lsmean SE df lower.CL upper.CL
## 1 472 Tribune EA 51.12957 5.586198 26.3469 39.654327 62.60481
## 2 472 Tribune AG 43.85542 5.586198 26.3469 32.380181 55.33066
## 3 472 Tribune NP 20.87374 5.586198 26.3469 9.398503 32.34898
## 4 579 Hays EA 59.98533 5.586198 26.3469 48.510085 71.46056
## 5 579 Hays AG 44.03529 5.586198 26.3469 32.560046 55.51053
## 6 579 Hays NP 32.68928 5.586198 26.3469 21.214043 44.16452
## 7 850 Manhattan AG 54.04183 5.586198 26.3469 42.566587 65.51707
## 8 850 Manhattan EA 52.36527 5.586198 26.3469 40.890028 63.84051
## 9 850 Manhattan NP 19.45423 5.586198 26.3469 7.978991 30.92947
## .group location_f
## 1 a Tribune
## 2 a Tribune
## 3 b Tribune
## 4 a Hays
## 5 b Hays
## 6 b Hays
## 7 a Manhattan
## 8 a Manhattan
## 9 b Manhattan2.3.3 0.053-0.02 mm
agg5 <- aggr %>%
filter(bdepth==5)
agg10 <- aggr %>%
filter(bdepth==10)
agg15 <- aggr %>%
filter(bdepth==15)
x## [1] "0-5 cm"agg15$precip <- as.factor(agg15$precip)
x20wsa2015 <- lmer(x20wsa20 ~ treatment*precip + (1|replication), data=agg15, na.action=na.omit)
anova(x20wsa2015, type=3)## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## treatment 157.687 78.844 2 18.9916 21.2369 1.434e-05 ***
## precip 9.154 4.577 2 6.5278 1.2328 0.35141
## treatment:precip 50.755 12.689 4 18.9916 3.4178 0.02888 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1x20wsa2015_means_tp <- lsmeans(x20wsa2015, specs = "treatment", by = "precip")
x20wsa2015_means_tp## precip = 472:
## treatment lsmean SE df lower.CL upper.CL
## AG 4.41 1.09 22.6 2.146 6.68
## EA 8.42 1.09 22.6 6.156 10.69
## NP 1.61 1.09 22.6 -0.651 3.88
##
## precip = 579:
## treatment lsmean SE df lower.CL upper.CL
## AG 7.83 1.09 22.6 5.561 10.09
## EA 5.56 1.09 22.6 3.296 7.83
## NP 2.44 1.09 22.6 0.174 4.71
##
## precip = 850:
## treatment lsmean SE df lower.CL upper.CL
## AG 3.47 1.09 22.6 1.204 5.74
## EA 6.94 1.09 22.6 4.674 9.21
## NP 1.73 1.09 22.6 -0.534 4.00
##
## Degrees-of-freedom method: kenward-roger
## Confidence level used: 0.95#PWC
x20wsa2015_pwc_tp <- cld(x20wsa2015_means_tp, adjust = "none", Letters = letters, reversed = T)
x20wsa2015_pwc_tp## precip = 472:
## treatment lsmean SE df lower.CL upper.CL .group
## EA 8.42 1.09 22.6 6.156 10.69 a
## AG 4.41 1.09 22.6 2.146 6.68 b
## NP 1.61 1.09 22.6 -0.651 3.88 b
##
## precip = 579:
## treatment lsmean SE df lower.CL upper.CL .group
## AG 7.83 1.09 22.6 5.561 10.09 a
## EA 5.56 1.09 22.6 3.296 7.83 a
## NP 2.44 1.09 22.6 0.174 4.71 b
##
## precip = 850:
## treatment lsmean SE df lower.CL upper.CL .group
## EA 6.94 1.09 22.6 4.674 9.21 a
## AG 3.47 1.09 22.6 1.204 5.74 b
## NP 1.73 1.09 22.6 -0.534 4.00 b
##
## Degrees-of-freedom method: kenward-roger
## Confidence level used: 0.95
## significance level used: alpha = 0.05
## NOTE: Compact letter displays can be misleading
## because they show NON-findings rather than findings.
## Consider using 'pairs()', 'pwpp()', or 'pwpm()' instead.#transforming it in a data frame to use on ggplot
x20wsa2015_pwc_tp <- as.data.frame(x20wsa2015_pwc_tp)
x20wsa2015_pwc_tp## treatment precip lsmean SE df lower.CL upper.CL .group
## 3 EA 472 8.4225 1.094354 22.58634 6.1563605 10.688639 a
## 1 AG 472 4.4125 1.094354 22.58634 2.1463605 6.678639 b
## 2 NP 472 1.6150 1.094354 22.58634 -0.6511395 3.881139 b
## 6 AG 579 7.8275 1.094354 22.58634 5.5613605 10.093639 a
## 5 EA 579 5.5625 1.094354 22.58634 3.2963605 7.828639 a
## 4 NP 579 2.4400 1.094354 22.58634 0.1738605 4.706139 b
## 9 EA 850 6.9400 1.094354 22.58634 4.6738605 9.206139 a
## 7 AG 850 3.4700 1.094354 22.58634 1.2038605 5.736139 b
## 8 NP 850 1.7325 1.094354 22.58634 -0.5336395 3.998639 b#add locations
df <- data.frame (location = c("Tribune", "Hays", "Manhattan"),
precip = c("472", "579", "850"))
x20wsa2015p<- merge(df, x20wsa2015_pwc_tp, by=c("precip"))
x20wsa2015p$location_f =factor(x20wsa2015p$location, levels=c('Tribune', 'Hays', 'Manhattan'))
x20wsa2015p## precip location treatment lsmean SE df lower.CL upper.CL
## 1 472 Tribune EA 8.4225 1.094354 22.58634 6.1563605 10.688639
## 2 472 Tribune AG 4.4125 1.094354 22.58634 2.1463605 6.678639
## 3 472 Tribune NP 1.6150 1.094354 22.58634 -0.6511395 3.881139
## 4 579 Hays AG 7.8275 1.094354 22.58634 5.5613605 10.093639
## 5 579 Hays EA 5.5625 1.094354 22.58634 3.2963605 7.828639
## 6 579 Hays NP 2.4400 1.094354 22.58634 0.1738605 4.706139
## 7 850 Manhattan EA 6.9400 1.094354 22.58634 4.6738605 9.206139
## 8 850 Manhattan AG 3.4700 1.094354 22.58634 1.2038605 5.736139
## 9 850 Manhattan NP 1.7325 1.094354 22.58634 -0.5336395 3.998639
## .group location_f
## 1 a Tribune
## 2 b Tribune
## 3 b Tribune
## 4 a Hays
## 5 a Hays
## 6 b Hays
## 7 a Manhattan
## 8 b Manhattan
## 9 b Manhattan3 5 min Aggregate Graphs
3.1 0-5 cm 5 minutes
agg5 <- aggr %>%
filter(bdepth==5)
agg10 <- aggr %>%
filter(bdepth==10)
agg15 <- aggr %>%
filter(bdepth==15)
x## [1] "0-5 cm"agg5$precip <- as.factor(agg5$precip)
x5mwd <- lmer(x5mwd ~ landuse*precip + (1|replication), data=agg5, na.action=na.omit)
anova(x5mwd, type=3)## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## landuse 9.0889 4.5444 2 20.7855 147.735 5.163e-13 ***
## precip 1.9281 0.9641 2 8.4263 31.341 0.0001252 ***
## landuse:precip 3.5555 0.8889 4 20.7855 28.896 3.171e-08 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1x5mwd_means_tp <- lsmeans(x5mwd, specs = "landuse", by = "precip")
#PWC
x5mwd_pwc_tp <- cld(x5mwd_means_tp, adjust = "none", Letters = letters, reversed = T)
#transforming it in a data frame to use on ggplot
x5mwd_pwc_tp <- as.data.frame(x5mwd_pwc_tp)
x5mwd_pwc_tp## landuse precip lsmean SE df lower.CL upper.CL .group
## 1 EA 472 0.8730867 0.1153711 16.22468 0.6287858 1.1173875 a
## 3 NP 472 0.7705144 0.1153711 16.22468 0.5262135 1.0148152 a
## 2 AG 472 0.4969844 0.1153711 16.22468 0.2526835 0.7412853 b
## 4 NP 579 2.5919444 0.1153711 16.22468 2.3476436 2.8362453 a
## 5 EA 579 1.6406292 0.1153711 16.22468 1.3963283 1.8849301 b
## 6 AG 579 0.4614811 0.1153711 16.22468 0.2171802 0.7057820 c
## 7 NP 850 1.7832866 0.1153711 16.22468 1.5389857 2.0275875 a
## 8 EA 850 1.1125858 0.1153711 16.22468 0.8682849 1.3568867 b
## 9 AG 850 0.5132084 0.1153711 16.22468 0.2689075 0.7575093 c#Determining the real SE
real_sex5mwd5cm <- agg5 %>%
dplyr::group_by(precip, landuse) %>%
dplyr::summarise(
n=n(),
mean=mean(x5mwd),
sd=sd(x5mwd)
) %>%
dplyr::mutate( se=sd/sqrt(n))
#add locations
df <- data.frame (location = c("Tribune", "Hays", "Manhattan"),
precip = c("472", "579", "850"))
df<- merge(df, real_sex5mwd5cm, by=c("precip"))
x5mwd5_pwc_tp_5v <- merge(x5mwd_pwc_tp, df, by=c("precip", "landuse"))
x5mwd5_pwc_tp_5v <- as.data.frame(x5mwd5_pwc_tp_5v)
x5mwd5_pwc_tp_5v## precip landuse lsmean SE df lower.CL upper.CL .group
## 1 472 AG 0.4969844 0.1153711 16.22468 0.2526835 0.7412853 b
## 2 472 EA 0.8730867 0.1153711 16.22468 0.6287858 1.1173875 a
## 3 472 NP 0.7705144 0.1153711 16.22468 0.5262135 1.0148152 a
## 4 579 AG 0.4614811 0.1153711 16.22468 0.2171802 0.7057820 c
## 5 579 EA 1.6406292 0.1153711 16.22468 1.3963283 1.8849301 b
## 6 579 NP 2.5919444 0.1153711 16.22468 2.3476436 2.8362453 a
## 7 850 AG 0.5132084 0.1153711 16.22468 0.2689075 0.7575093 c
## 8 850 EA 1.1125858 0.1153711 16.22468 0.8682849 1.3568867 b
## 9 850 NP 1.7832866 0.1153711 16.22468 1.5389857 2.0275875 a
## location n mean sd se
## 1 Tribune 4 0.4969844 0.20872366 0.10436183
## 2 Tribune 4 0.8730867 0.34450024 0.17225012
## 3 Tribune 4 0.7705144 0.09091499 0.04545750
## 4 Hays 4 0.4614811 0.11490948 0.05745474
## 5 Hays 4 1.6406292 0.14262624 0.07131312
## 6 Hays 4 2.5919444 0.32999554 0.16499777
## 7 Manhattan 4 0.5132084 0.07644064 0.03822032
## 8 Manhattan 4 1.1125858 0.08289555 0.04144778
## 9 Manhattan 4 1.7832866 0.37560090 0.18780045x5mwd5_pwc_tp_5v$location_f =factor(x5mwd5_pwc_tp_5v$location, levels=c('Tribune', 'Hays', 'Manhattan'))
ggplot(data=x5mwd5_pwc_tp_5v, aes(x=landuse, y=lsmean, fill = landuse)) +
geom_bar(position=position_dodge(), stat="identity", colour = "black") +
geom_errorbar(aes(ymin=lsmean-se, ymax=lsmean+se),
width=.2, # Width of the error bars
position=position_dodge(.9)) +
scale_y_continuous(limits=c(0,3.5)) +
facet_wrap(facets=vars(location_f), strip.position="bottom") +
xlab("")+
facet_wrap(facets=vars(location_f), strip.position="bottom") +
scale_fill_manual(values = colsnp) +
ggtitle("5 Minute MWD 0-5 cm by Land use and Precipitation")+
theme_James() +
theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
panel.background = element_blank(), axis.line = element_line(colour = "black"),
panel.border = element_rect(colour = "black", fill=NA, size=0.5),
strip.background=element_rect(size=0.5, colour = "black"),
axis.text.x=element_blank(),
axis.ticks.x=element_blank(),
legend.position= c(0.1,0.85)) +
labs(y=" Mean Weight Diameter (mm)") +
geom_label(aes(label=trimws(.group), y = lsmean+.5),
label.padding = unit(.3,"lines"), show.legend=NA , label.size = NA, fill=NA, font="bold") +
guides(fill = guide_legend(override.aes = aes(label="")))
###8-2 mm
agg5 <- aggr %>%
filter(bdepth==5)
agg10 <- aggr %>%
filter(bdepth==10)
agg15 <- aggr %>%
filter(bdepth==15)
x## [1] "0-5 cm"agg5$precip <- as.factor(agg5$precip)
x5wsa2000 <- lmer(x5wsa2000 ~ treatment*precip + (1|replication), data=agg5, na.action=na.omit)
anova(x5wsa2000, type=3)## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## treatment 3046.25 1523.13 2 21.1098 98.376 1.998e-11 ***
## precip 939.68 469.84 2 9.1148 30.346 9.344e-05 ***
## treatment:precip 1637.29 409.32 4 21.1098 26.438 5.896e-08 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1x5wsa2000_means_tp <- lsmeans(x5wsa2000, specs = "treatment", by = "precip")
#PWC
x5wsa2000_pwc_tp <- cld(x5wsa2000_means_tp, adjust = "none", Letters = letters, reversed = T)
#transforming it in a data frame to use on ggplot
x5wsa2000_pwc_tp <- as.data.frame(x5wsa2000_pwc_tp)
#add locations
df <- data.frame (location = c("Tribune", "Hays", "Manhattan"),
precip = c("472", "579", "850"))
x5wsa2000p<- merge(df, x5wsa2000_pwc_tp, by=c("precip"))
x5wsa2000p$location_f =factor(x5wsa2000p$location, levels=c('Tribune', 'Hays', 'Manhattan'))
x5wsa2000p## precip location treatment lsmean SE df lower.CL upper.CL
## 1 472 Tribune EA 10.186894 2.267247 21.87134 5.483308 14.890481
## 2 472 Tribune NP 8.822787 2.267247 21.87134 4.119200 13.526373
## 3 472 Tribune AG 6.619284 2.267247 21.87134 1.915697 11.322870
## 4 579 Hays NP 44.065476 2.267247 21.87134 39.361889 48.769062
## 5 579 Hays EA 25.901540 2.267247 21.87134 21.197953 30.605126
## 6 579 Hays AG 1.563937 2.267247 21.87134 -3.139650 6.267523
## 7 850 Manhattan NP 25.434619 2.267247 21.87134 20.731032 30.138205
## 8 850 Manhattan EA 14.241278 2.267247 21.87134 9.537691 18.944864
## 9 850 Manhattan AG 2.857780 2.267247 21.87134 -1.845807 7.561367
## .group location_f
## 1 a Tribune
## 2 a Tribune
## 3 a Tribune
## 4 a Hays
## 5 b Hays
## 6 c Hays
## 7 a Manhattan
## 8 b Manhattan
## 9 c Manhattan3.1.1 2-0.250 mm
agg5 <- aggr %>%
filter(bdepth==5)
agg10 <- aggr %>%
filter(bdepth==10)
agg15 <- aggr %>%
filter(bdepth==15)
x## [1] "0-5 cm"agg5$precip <- as.factor(agg5$precip)
x5wsa250 <- lmer(x5wsa250 ~ treatment*precip + (1|replication), data=agg5, na.action=na.omit)
anova(x5wsa250, type=3)## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## treatment 977.51 488.76 2 21.239 8.4360 0.002012 **
## precip 780.26 390.13 2 10.129 6.7337 0.013802 *
## treatment:precip 571.64 142.91 4 21.239 2.4666 0.075969 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1x5wsa250_means_tp <- lsmeans(x5wsa250, specs = "treatment", by = "precip")
#PWC
x5wsa250_pwc_tp <- cld(x5wsa250_means_tp, adjust = "none", Letters = letters, reversed = T)
#transforming it in a data frame to use on ggplot
x5wsa250_pwc_tp <- as.data.frame(x5wsa250_pwc_tp)
#add locations
df <- data.frame (location = c("Tribune", "Hays", "Manhattan"),
precip = c("472", "579", "850"))
x5wsa250p<- merge(df, x5wsa250_pwc_tp, by=c("precip"))
x5wsa250p$location_f =factor(x5wsa250p$location, levels=c('Tribune', 'Hays', 'Manhattan'))
x5wsa250p## precip location treatment lsmean SE df lower.CL upper.CL
## 1 472 Tribune EA 29.018520 3.940058 26.52673 20.927435 37.10960
## 2 472 Tribune NP 27.005202 3.940058 26.52673 18.914117 35.09629
## 3 472 Tribune AG 9.931781 3.940058 26.52673 1.840697 18.02287
## 4 579 Hays NP 32.570016 3.940058 26.52673 24.478931 40.66110
## 5 579 Hays AG 27.649027 3.940058 26.52673 19.557942 35.74011
## 6 579 Hays EA 26.595305 3.940058 26.52673 18.504220 34.68639
## 7 850 Manhattan NP 44.262281 3.940058 26.52673 36.171196 52.35337
## 8 850 Manhattan EA 31.323713 3.940058 26.52673 23.232629 39.41480
## 9 850 Manhattan AG 28.049438 3.940058 26.52673 19.958353 36.14052
## .group location_f
## 1 a Tribune
## 2 a Tribune
## 3 b Tribune
## 4 a Hays
## 5 a Hays
## 6 a Hays
## 7 a Manhattan
## 8 b Manhattan
## 9 b Manhattan3.1.2 0.250-0.053 mm
agg5 <- aggr %>%
filter(bdepth==5)
agg10 <- aggr %>%
filter(bdepth==10)
agg15 <- aggr %>%
filter(bdepth==15)
x## [1] "0-5 cm"agg5$precip <- as.factor(agg5$precip)
x5wsa53 <- lmer(x5wsa53 ~ treatment*precip + (1|replication), data=agg5, na.action=na.omit)
anova(x5wsa53, type=3)## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## treatment 6024.4 3012.22 2 21.639 41.5735 3.872e-08 ***
## precip 112.7 56.36 2 11.231 0.7779 0.4826
## treatment:precip 356.3 89.08 4 21.639 1.2294 0.3276
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1x5wsa53_means_tp <- lsmeans(x5wsa53, specs = "treatment", by = "precip")
x5wsa53_means_tp## precip = 472:
## treatment lsmean SE df lower.CL upper.CL
## AG 51.3 4.31 26.9 42.44 60.1
## EA 35.1 4.31 26.9 26.28 44.0
## NP 23.4 4.31 26.9 14.57 32.3
##
## precip = 579:
## treatment lsmean SE df lower.CL upper.CL
## AG 46.2 4.31 26.9 37.38 55.1
## EA 39.8 4.31 26.9 30.98 48.7
## NP 18.9 4.31 26.9 10.08 27.8
##
## precip = 850:
## treatment lsmean SE df lower.CL upper.CL
## AG 52.8 4.31 26.9 43.94 61.6
## EA 30.9 4.31 26.9 22.02 39.7
## NP 13.0 4.31 26.9 4.11 21.8
##
## Degrees-of-freedom method: kenward-roger
## Confidence level used: 0.95#PWC
x5wsa53_pwc_tp <- cld(x5wsa53_means_tp, adjust = "none", Letters = letters, reversed = T)
#transforming it in a data frame to use on ggplot
x5wsa53_pwc_tp <- as.data.frame(x5wsa53_pwc_tp)
#add locations
df <- data.frame (location = c("Tribune", "Hays", "Manhattan"),
precip = c("472", "579", "850"))
x5wsa53p<- merge(df, x5wsa53_pwc_tp, by=c("precip"))
x5wsa53p$location_f =factor(x5wsa53p$location, levels=c('Tribune', 'Hays', 'Manhattan'))
x5wsa53p## precip location treatment lsmean SE df lower.CL upper.CL
## 1 472 Tribune AG 51.28463 4.308961 26.93583 42.442385 60.12687
## 2 472 Tribune EA 35.12016 4.308961 26.93583 26.277920 43.96241
## 3 472 Tribune NP 23.41428 4.308961 26.93583 14.572037 32.25652
## 4 579 Hays AG 46.22015 4.308961 26.93583 37.377911 55.06240
## 5 579 Hays EA 39.81846 4.308961 26.93583 30.976213 48.66070
## 6 579 Hays NP 18.92336 4.308961 26.93583 10.081112 27.76560
## 7 850 Manhattan AG 52.78271 4.308961 26.93583 43.940465 61.62495
## 8 850 Manhattan EA 30.85960 4.308961 26.93583 22.017359 39.70184
## 9 850 Manhattan NP 12.95212 4.308961 26.93583 4.109876 21.79436
## .group location_f
## 1 a Tribune
## 2 b Tribune
## 3 b Tribune
## 4 a Hays
## 5 a Hays
## 6 b Hays
## 7 a Manhattan
## 8 b Manhattan
## 9 c Manhattan3.1.3 0.053-0.02 mm
agg5 <- aggr %>%
filter(bdepth==5)
agg10 <- aggr %>%
filter(bdepth==10)
agg15 <- aggr %>%
filter(bdepth==15)
x## [1] "0-5 cm"agg5$precip <- as.factor(agg5$precip)
x5wsa20 <- lmer(x5wsa20 ~ treatment*precip + (1|replication), data=agg5, na.action=na.omit)
anova(x5wsa20, type=3)## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## treatment 81.43 40.715 2 27 1.7331 0.195822
## precip 341.14 170.569 2 27 7.2607 0.002997 **
## treatment:precip 195.51 48.876 4 27 2.0805 0.111180
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1x5wsa20_means_tp <- lsmeans(x5wsa20, specs = "treatment", by = "precip")
x5wsa20_means_tp## precip = 472:
## treatment lsmean SE df lower.CL upper.CL
## AG 6.82 2.42 27 1.85001 11.79
## EA 4.96 2.42 27 -0.00749 9.94
## NP 5.25 2.42 27 0.28251 10.23
##
## precip = 579:
## treatment lsmean SE df lower.CL upper.CL
## AG 6.05 2.42 27 1.08001 11.02
## EA 16.82 2.42 27 11.84501 21.79
## NP 8.62 2.42 27 3.64501 13.59
##
## precip = 850:
## treatment lsmean SE df lower.CL upper.CL
## AG 3.98 2.42 27 -0.99249 8.95
## EA 3.77 2.42 27 -1.19749 8.75
## NP 1.43 2.42 27 -3.53853 6.41
##
## Degrees-of-freedom method: kenward-roger
## Confidence level used: 0.95#PWC
x5wsa20_pwc_tp <- cld(x5wsa20_means_tp, adjust = "none", Letters = letters, reversed = T)
x5wsa20_pwc_tp## precip = 472:
## treatment lsmean SE df lower.CL upper.CL .group
## AG 6.82 2.42 27 1.85001 11.79 a
## NP 5.25 2.42 27 0.28251 10.23 a
## EA 4.96 2.42 27 -0.00749 9.94 a
##
## precip = 579:
## treatment lsmean SE df lower.CL upper.CL .group
## EA 16.82 2.42 27 11.84501 21.79 a
## NP 8.62 2.42 27 3.64501 13.59 b
## AG 6.05 2.42 27 1.08001 11.02 b
##
## precip = 850:
## treatment lsmean SE df lower.CL upper.CL .group
## AG 3.98 2.42 27 -0.99249 8.95 a
## EA 3.77 2.42 27 -1.19749 8.75 a
## NP 1.43 2.42 27 -3.53853 6.41 a
##
## Degrees-of-freedom method: kenward-roger
## Confidence level used: 0.95
## significance level used: alpha = 0.05
## NOTE: Compact letter displays can be misleading
## because they show NON-findings rather than findings.
## Consider using 'pairs()', 'pwpp()', or 'pwpm()' instead.#transforming it in a data frame to use on ggplot
x5wsa20_pwc_tp <- as.data.frame(x5wsa20_pwc_tp)
x5wsa20_pwc_tp## treatment precip lsmean SE df lower.CL upper.CL .group
## 2 AG 472 6.822500 2.423439 27 1.850013269 11.794987 a
## 3 NP 472 5.255000 2.423439 27 0.282513269 10.227487 a
## 1 EA 472 4.965000 2.423439 27 -0.007486731 9.937487 a
## 4 EA 579 16.817500 2.423439 27 11.845013269 21.789987 a
## 6 NP 579 8.617500 2.423439 27 3.645013269 13.589987 b
## 5 AG 579 6.052500 2.423439 27 1.080013269 11.024987 b
## 9 AG 850 3.980000 2.423439 27 -0.992486731 8.952487 a
## 8 EA 850 3.775000 2.423439 27 -1.197486731 8.747487 a
## 7 NP 850 1.433954 2.423439 27 -3.538532696 6.406441 a#add locations
df <- data.frame (location = c("Tribune", "Hays", "Manhattan"),
precip = c("472", "579", "850"))
x5wsa20p<- merge(df, x5wsa20_pwc_tp, by=c("precip"))
x5wsa20p$location_f =factor(x5wsa20p$location, levels=c('Tribune', 'Hays', 'Manhattan'))
x5wsa20p## precip location treatment lsmean SE df lower.CL upper.CL
## 1 472 Tribune AG 6.822500 2.423439 27 1.850013269 11.794987
## 2 472 Tribune NP 5.255000 2.423439 27 0.282513269 10.227487
## 3 472 Tribune EA 4.965000 2.423439 27 -0.007486731 9.937487
## 4 579 Hays EA 16.817500 2.423439 27 11.845013269 21.789987
## 5 579 Hays NP 8.617500 2.423439 27 3.645013269 13.589987
## 6 579 Hays AG 6.052500 2.423439 27 1.080013269 11.024987
## 7 850 Manhattan AG 3.980000 2.423439 27 -0.992486731 8.952487
## 8 850 Manhattan EA 3.775000 2.423439 27 -1.197486731 8.747487
## 9 850 Manhattan NP 1.433954 2.423439 27 -3.538532696 6.406441
## .group location_f
## 1 a Tribune
## 2 a Tribune
## 3 a Tribune
## 4 a Hays
## 5 b Hays
## 6 b Hays
## 7 a Manhattan
## 8 a Manhattan
## 9 a Manhattan3.2 5-10 cm 5 minutes
###8-2 mm
agg5 <- aggr %>%
filter(bdepth==5)
agg10 <- aggr %>%
filter(bdepth==10)
agg15 <- aggr %>%
filter(bdepth==15)
x## [1] "0-5 cm"agg10$precip <- as.factor(agg10$precip)
x5wsa200010 <- lmer(x5wsa2000 ~ treatment*precip + (1|replication), data=agg10, na.action=na.omit)
anova(x5wsa200010, type=3)## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## treatment 3242.9 1621.44 2 24.816 70.616 5.717e-11 ***
## precip 1202.5 601.27 2 22.710 26.186 1.268e-06 ***
## treatment:precip 2277.5 569.37 4 24.206 24.797 2.946e-08 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1x5wsa200010_means_tp <- lsmeans(x5wsa200010, specs = "treatment", by = "precip")
#PWC
x5wsa200010_pwc_tp <- cld(x5wsa200010_means_tp, adjust = "none", Letters = letters, reversed = T)
#transforming it in a data frame to use on ggplot
x5wsa200010_pwc_tp <- as.data.frame(x5wsa200010_pwc_tp)
#add locations
df <- data.frame (location = c("Tribune", "Hays", "Manhattan"),
precip = c("472", "579", "850"))
x5wsa200010p<- merge(df, x5wsa200010_pwc_tp, by=c("precip"))
x5wsa200010p$location_f =factor(x5wsa200010p$location, levels=c('Tribune', 'Hays', 'Manhattan'))
x5wsa200010p## precip location treatment lsmean SE df lower.CL upper.CL
## 1 472 Tribune NP 7.784108 2.481473 26.41131 2.687230 12.880986
## 2 472 Tribune AG 7.358129 2.481473 26.41131 2.261251 12.455007
## 3 472 Tribune EA 3.989024 2.481473 26.41131 -1.107854 9.085902
## 4 579 Hays NP 47.950775 2.481473 26.41131 42.853897 53.047653
## 5 579 Hays EA 10.999532 2.481473 26.41131 5.902654 16.096410
## 6 579 Hays AG 3.551578 2.481473 26.41131 -1.545301 8.648456
## 7 850 Manhattan NP 27.719093 2.481473 26.41131 22.622215 32.815972
## 8 850 Manhattan EA 18.601440 2.481473 26.41131 13.504562 23.698318
## 9 850 Manhattan AG 4.704605 2.481473 26.41131 -0.392273 9.801483
## .group location_f
## 1 a Tribune
## 2 a Tribune
## 3 a Tribune
## 4 a Hays
## 5 b Hays
## 6 c Hays
## 7 a Manhattan
## 8 b Manhattan
## 9 c Manhattan3.2.1 2-0.250 mm
agg5 <- aggr %>%
filter(bdepth==5)
agg10 <- aggr %>%
filter(bdepth==10)
agg15 <- aggr %>%
filter(bdepth==15)
x## [1] "0-5 cm"agg10$precip <- as.factor(agg10$precip)
x5wsa25010 <- lmer(x5wsa250 ~ treatment*precip + (1|replication), data=agg10, na.action=na.omit)
anova(x5wsa25010, type=3)## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## treatment 1308.4 654.22 2 24.405 8.6610 0.0014374 **
## precip 1914.2 957.07 2 23.351 12.6703 0.0001878 ***
## treatment:precip 1037.2 259.31 4 23.956 3.4329 0.0235728 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1x5wsa25010_means_tp <- lsmeans(x5wsa25010, specs = "treatment", by = "precip")
#PWC
x5wsa25010_pwc_tp <- cld(x5wsa25010_means_tp, adjust = "none", Letters = letters, reversed = T)
#transforming it in a data frame to use on ggplot
x5wsa25010_pwc_tp <- as.data.frame(x5wsa25010_pwc_tp)
#add locations
df <- data.frame (location = c("Tribune", "Hays", "Manhattan"),
precip = c("472", "579", "850"))
x5wsa25010p<- merge(df, x5wsa25010_pwc_tp, by=c("precip"))
x5wsa25010p$location_f =factor(x5wsa25010p$location, levels=c('Tribune', 'Hays', 'Manhattan'))
x5wsa25010p## precip location treatment lsmean SE df lower.CL upper.CL
## 1 472 Tribune NP 36.00030 4.391035 26.94418 26.989762 45.01083
## 2 472 Tribune EA 17.12701 4.391035 26.94418 8.116474 26.13754
## 3 472 Tribune AG 15.92634 4.391035 26.94418 6.915812 24.93688
## 4 579 Hays EA 38.08866 4.391035 26.94418 29.078132 47.09920
## 5 579 Hays NP 37.44081 4.391035 26.94418 28.430276 46.45134
## 6 579 Hays AG 16.11014 4.391035 26.94418 7.099607 25.12067
## 7 850 Manhattan NP 44.20709 4.391035 26.94418 35.196554 53.21762
## 8 850 Manhattan AG 41.27775 4.391035 26.94418 32.267214 50.28828
## 9 850 Manhattan EA 37.56607 4.391035 26.94418 28.555534 46.57660
## .group location_f
## 1 a Tribune
## 2 b Tribune
## 3 b Tribune
## 4 a Hays
## 5 a Hays
## 6 b Hays
## 7 a Manhattan
## 8 a Manhattan
## 9 a Manhattan3.2.2 0.250-0.053 mm
agg5 <- aggr %>%
filter(bdepth==5)
agg10 <- aggr %>%
filter(bdepth==10)
agg15 <- aggr %>%
filter(bdepth==15)
x## [1] "0-5 cm"agg10$precip <- as.factor(agg10$precip)
x5wsa5310 <- lmer(x5wsa53 ~ treatment*precip + (1|replication), data=agg10, na.action=na.omit)
anova(x5wsa5310, type=3)## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## treatment 4653.5 2326.74 2 24.510 27.3284 5.751e-07 ***
## precip 2560.8 1280.39 2 23.660 15.0387 6.102e-05 ***
## treatment:precip 770.2 192.55 4 24.108 2.2616 0.09212 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1x5wsa5310_means_tp <- lsmeans(x5wsa5310, specs = "treatment", by = "precip")
x5wsa5310_means_tp## precip = 472:
## treatment lsmean SE df lower.CL upper.CL
## AG 48.8 4.65 27 39.26 58.3
## EA 56.3 4.65 27 46.73 65.8
## NP 28.5 4.65 27 19.01 38.1
##
## precip = 579:
## treatment lsmean SE df lower.CL upper.CL
## AG 53.8 4.65 27 44.31 63.4
## EA 52.7 4.65 27 43.21 62.3
## NP 26.0 4.65 27 16.47 35.5
##
## precip = 850:
## treatment lsmean SE df lower.CL upper.CL
## AG 42.5 4.65 27 33.01 52.1
## EA 23.9 4.65 27 14.34 33.4
## NP 12.8 4.65 27 3.29 22.4
##
## Degrees-of-freedom method: kenward-roger
## Confidence level used: 0.95#PWC
x5wsa5310_pwc_tp <- cld(x5wsa5310_means_tp, adjust = "none", Letters = letters, reversed = T)
#transforming it in a data frame to use on ggplot
x5wsa5310_pwc_tp <- as.data.frame(x5wsa5310_pwc_tp)
#add locations
df <- data.frame (location = c("Tribune", "Hays", "Manhattan"),
precip = c("472", "579", "850"))
x5wsa5310p<- merge(df, x5wsa5310_pwc_tp, by=c("precip"))
x5wsa5310p$location_f =factor(x5wsa5310p$location, levels=c('Tribune', 'Hays', 'Manhattan'))
x5wsa5310p## precip location treatment lsmean SE df lower.CL upper.CL
## 1 472 Tribune EA 56.26802 4.646506 26.97369 46.733745 65.80230
## 2 472 Tribune AG 48.79037 4.646506 26.97369 39.256094 58.32465
## 3 472 Tribune NP 28.54305 4.646506 26.97369 19.008772 38.07733
## 4 579 Hays AG 53.84427 4.646506 26.97369 44.309997 63.37855
## 5 579 Hays EA 52.73937 4.646506 26.97369 43.205095 62.27365
## 6 579 Hays NP 26.00424 4.646506 26.97369 16.469966 35.53852
## 7 850 Manhattan AG 42.54411 4.646506 26.97369 33.009834 52.07839
## 8 850 Manhattan EA 23.87843 4.646506 26.97369 14.344149 33.41270
## 9 850 Manhattan NP 12.82837 4.646506 26.97369 3.294094 22.36265
## .group location_f
## 1 a Tribune
## 2 a Tribune
## 3 b Tribune
## 4 a Hays
## 5 a Hays
## 6 b Hays
## 7 a Manhattan
## 8 b Manhattan
## 9 b Manhattan3.2.3 0.053-0.02 mm
agg5 <- aggr %>%
filter(bdepth==5)
agg10 <- aggr %>%
filter(bdepth==10)
agg15 <- aggr %>%
filter(bdepth==15)
x## [1] "0-5 cm"agg10$precip <- as.factor(agg10$precip)
x5wsa2010 <- lmer(x5wsa20 ~ treatment*precip + (1|replication), data=agg10, na.action=na.omit)
anova(x20wsa2010, type=3)## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## treatment 79.773 39.886 2 27 22.0949 2.069e-06 ***
## precip 4.560 2.280 2 27 1.2630 0.2989752
## treatment:precip 55.436 13.859 4 27 7.6771 0.0002882 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1x5wsa2010_means_tp <- lsmeans(x5wsa2010, specs = "treatment", by = "precip")
#PWC
x5wsa2010_pwc_tp <- cld(x5wsa2010_means_tp, adjust = "none", Letters = letters, reversed = T)
#transforming it in a data frame to use on ggplot
x5wsa2010_pwc_tp <- as.data.frame(x5wsa2010_pwc_tp)
#add locations
df <- data.frame (location = c("Tribune", "Hays", "Manhattan"),
precip = c("472", "579", "850"))
x5wsa2010p<- merge(df, x5wsa2010_pwc_tp, by=c("precip"))
x5wsa2010p$location_f =factor(x5wsa2010p$location, levels=c('Tribune', 'Hays', 'Manhattan'))
x5wsa2010p## precip location treatment lsmean SE df lower.CL upper.CL .group
## 1 472 Tribune AG 7.5800 0.9417107 27 5.6477693 9.512231 a
## 2 472 Tribune EA 6.5025 0.9417107 27 4.5702693 8.434731 a
## 3 472 Tribune NP 4.8950 0.9417107 27 2.9627693 6.827231 a
## 4 579 Hays EA 11.5525 0.9417107 27 9.6202693 13.484731 a
## 5 579 Hays NP 9.0175 0.9417107 27 7.0852693 10.949731 a
## 6 579 Hays AG 5.6325 0.9417107 27 3.7002693 7.564731 b
## 7 850 Manhattan EA 4.2475 0.9417107 27 2.3152693 6.179731 a
## 8 850 Manhattan AG 2.2525 0.9417107 27 0.3202693 4.184731 a
## 9 850 Manhattan NP 1.7150 0.9417107 27 -0.2172307 3.647231 a
## location_f
## 1 Tribune
## 2 Tribune
## 3 Tribune
## 4 Hays
## 5 Hays
## 6 Hays
## 7 Manhattan
## 8 Manhattan
## 9 Manhattan3.3 10-15 cm 5 minutes
###8-2 mm
agg5 <- aggr %>%
filter(bdepth==5)
agg10 <- aggr %>%
filter(bdepth==10)
agg15 <- aggr %>%
filter(bdepth==15)
x## [1] "0-5 cm"agg15$precip <- as.factor(agg15$precip)
x5wsa200015 <- lmer(x5wsa2000 ~ treatment*precip + (1|replication), data=agg15, na.action=na.omit)
anova(x5wsa200015, type=3)## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## treatment 2795.75 1397.88 2 27 21.7816 2.331e-06 ***
## precip 690.88 345.44 2 27 5.3826 0.01078 *
## treatment:precip 934.65 233.66 4 27 3.6409 0.01694 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1x5wsa200015_means_tp <- lsmeans(x5wsa200015, specs = "treatment", by = "precip")
#PWC
x5wsa200015_pwc_tp <- cld(x5wsa200015_means_tp, adjust = "none", Letters = letters, reversed = T)
#transforming it in a data frame to use on ggplot
x5wsa200015_pwc_tp <- as.data.frame(x5wsa200015_pwc_tp)
#add locations
df <- data.frame (location = c("Tribune", "Hays", "Manhattan"),
precip = c("472", "579", "850"))
x5wsa200015p<- merge(df, x5wsa200015_pwc_tp, by=c("precip"))
x5wsa200015p$location_f =factor(x5wsa200015p$location, levels=c('Tribune', 'Hays', 'Manhattan'))
x5wsa200015p## precip location treatment lsmean SE df lower.CL upper.CL .group
## 1 472 Tribune NP 14.583834 4.005528 27 6.3651697 22.80250 a
## 2 472 Tribune AG 6.606750 4.005528 27 -1.6119142 14.82541 a
## 3 472 Tribune EA 6.572290 4.005528 27 -1.6463741 14.79095 a
## 4 579 Hays NP 40.495560 4.005528 27 32.2768962 48.71422 a
## 5 579 Hays AG 11.637256 4.005528 27 3.4185919 19.85592 b
## 6 579 Hays EA 7.687615 4.005528 27 -0.5310489 15.90628 b
## 7 850 Manhattan NP 26.750084 4.005528 27 18.5314199 34.96875 a
## 8 850 Manhattan EA 15.118422 4.005528 27 6.8997576 23.33709 ab
## 9 850 Manhattan AG 4.467970 4.005528 27 -3.7506942 12.68663 b
## location_f
## 1 Tribune
## 2 Tribune
## 3 Tribune
## 4 Hays
## 5 Hays
## 6 Hays
## 7 Manhattan
## 8 Manhattan
## 9 Manhattan3.3.1 2-0.250 mm
agg5 <- aggr %>%
filter(bdepth==5)
agg10 <- aggr %>%
filter(bdepth==10)
agg15 <- aggr %>%
filter(bdepth==15)
x## [1] "0-5 cm"agg15$precip <- as.factor(agg15$precip)
x5wsa25015 <- lmer(x5wsa250 ~ treatment*precip + (1|replication), data=agg15, na.action=na.omit)
anova(x5wsa25015, type=3)## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## treatment 473.48 236.74 2 27 1.7764 0.188457
## precip 2205.73 1102.87 2 27 8.2756 0.001574 **
## treatment:precip 1200.40 300.10 4 27 2.2519 0.089805 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1x5wsa25015_means_tp <- lsmeans(x5wsa25015, specs = "treatment", by = "precip")
#PWC
x5wsa25015_pwc_tp <- cld(x5wsa25015_means_tp, adjust = "none", Letters = letters, reversed = T)
#transforming it in a data frame to use on ggplot
x5wsa25015_pwc_tp <- as.data.frame(x5wsa25015_pwc_tp)
#add locations
df <- data.frame (location = c("Tribune", "Hays", "Manhattan"),
precip = c("472", "579", "850"))
x5wsa25015p<- merge(df, x5wsa25015_pwc_tp, by=c("precip"))
x5wsa25015p$location_f =factor(x5wsa25015p$location, levels=c('Tribune', 'Hays', 'Manhattan'))
x5wsa25015p## precip location treatment lsmean SE df lower.CL upper.CL .group
## 1 472 Tribune EA 32.71524 5.772062 27 20.871950 44.55854 a
## 2 472 Tribune AG 19.59991 5.772062 27 7.756621 31.44321 a
## 3 472 Tribune NP 18.03246 5.772062 27 6.189164 29.87575 a
## 4 579 Hays EA 45.46467 5.772062 27 33.621372 57.30796 a
## 5 579 Hays NP 32.09403 5.772062 27 20.250733 43.93732 a
## 6 579 Hays AG 32.00845 5.772062 27 20.165157 43.85174 a
## 7 850 Manhattan AG 52.68674 5.772062 27 40.843442 64.53003 a
## 8 850 Manhattan NP 37.69254 5.772062 27 25.849249 49.53584 a
## 9 850 Manhattan EA 36.01735 5.772062 27 24.174053 47.86064 a
## location_f
## 1 Tribune
## 2 Tribune
## 3 Tribune
## 4 Hays
## 5 Hays
## 6 Hays
## 7 Manhattan
## 8 Manhattan
## 9 Manhattan3.3.2 0.250-0.053 mm
agg5 <- aggr %>%
filter(bdepth==5)
agg10 <- aggr %>%
filter(bdepth==10)
agg15 <- aggr %>%
filter(bdepth==15)
x## [1] "0-5 cm"agg15$precip <- as.factor(agg15$precip)
x5wsa5315 <- lmer(x5wsa53 ~ treatment*precip + (1|replication), data=agg15, na.action=na.omit)
anova(x5wsa5315, type=3)## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## treatment 1446.44 723.22 2 27 5.3919 0.01071 *
## precip 1385.82 692.91 2 27 5.1660 0.01260 *
## treatment:precip 980.67 245.17 4 27 1.8278 0.15257
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1x5wsa5315_means_tp <- lsmeans(x5wsa5315, specs = "treatment", by = "precip")
x5wsa5315_means_tp## precip = 472:
## treatment lsmean SE df lower.CL upper.CL
## AG 54.1 5.79 27 42.18 65.9
## EA 41.1 5.79 27 29.22 53.0
## NP 33.0 5.79 27 21.13 44.9
##
## precip = 579:
## treatment lsmean SE df lower.CL upper.CL
## AG 32.3 5.79 27 20.39 44.1
## EA 49.6 5.79 27 37.72 61.5
## NP 26.4 5.79 27 14.54 38.3
##
## precip = 850:
## treatment lsmean SE df lower.CL upper.CL
## AG 33.1 5.79 27 21.21 45.0
## EA 29.5 5.79 27 17.66 41.4
## NP 20.1 5.79 27 8.18 31.9
##
## Degrees-of-freedom method: kenward-roger
## Confidence level used: 0.95#PWC
x5wsa5315_pwc_tp <- cld(x5wsa5315_means_tp, adjust = "none", Letters = letters, reversed = T)
#transforming it in a data frame to use on ggplot
x5wsa5315_pwc_tp <- as.data.frame(x5wsa5315_pwc_tp)
#add locations
df <- data.frame (location = c("Tribune", "Hays", "Manhattan"),
precip = c("472", "579", "850"))
x5wsa5315p<- merge(df, x5wsa5315_pwc_tp, by=c("precip"))
x5wsa5315p$location_f =factor(x5wsa5315p$location, levels=c('Tribune', 'Hays', 'Manhattan'))
x5wsa5315p## precip location treatment lsmean SE df lower.CL upper.CL .group
## 1 472 Tribune AG 54.06194 5.790714 27 42.180374 65.94350 a
## 2 472 Tribune EA 41.10064 5.790714 27 29.219080 52.98221 ab
## 3 472 Tribune NP 33.01473 5.790714 27 21.133171 44.89630 b
## 4 579 Hays EA 49.59674 5.790714 27 37.715174 61.47830 a
## 5 579 Hays AG 32.26746 5.790714 27 20.385893 44.14902 b
## 6 579 Hays NP 26.41757 5.790714 27 14.536007 38.29913 b
## 7 850 Manhattan AG 33.09569 5.790714 27 21.214123 44.97725 a
## 8 850 Manhattan EA 29.54047 5.790714 27 17.658910 41.42204 a
## 9 850 Manhattan NP 20.06624 5.790714 27 8.184675 31.94780 a
## location_f
## 1 Tribune
## 2 Tribune
## 3 Tribune
## 4 Hays
## 5 Hays
## 6 Hays
## 7 Manhattan
## 8 Manhattan
## 9 Manhattan3.3.3 0.053-0.02 mm
agg5 <- aggr %>%
filter(bdepth==5)
agg10 <- aggr %>%
filter(bdepth==10)
agg15 <- aggr %>%
filter(bdepth==15)
x## [1] "0-5 cm"agg15$precip <- as.factor(agg15$precip)
x5wsa2015 <- lmer(x5wsa20 ~ treatment*precip + (1|replication), data=agg15, na.action=na.omit)
anova(x5wsa2015, type=3)## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## treatment 30.440 15.220 2 27 8.3832 0.001472 **
## precip 192.516 96.258 2 27 53.0197 4.464e-10 ***
## treatment:precip 37.331 9.333 4 27 5.1406 0.003275 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1x5wsa2015_means_tp <- lsmeans(x5wsa2015, specs = "treatment", by = "precip")
x5wsa2015_means_tp## precip = 472:
## treatment lsmean SE df lower.CL upper.CL
## AG 5.56 0.674 27 4.1752 6.94
## EA 5.67 0.674 27 4.2927 7.06
## NP 5.08 0.674 27 3.7027 6.47
##
## precip = 579:
## treatment lsmean SE df lower.CL upper.CL
## AG 5.85 0.674 27 4.4702 7.23
## EA 10.87 0.674 27 9.4877 12.25
## NP 8.93 0.674 27 7.5452 10.31
##
## precip = 850:
## treatment lsmean SE df lower.CL upper.CL
## AG 3.07 0.674 27 1.6902 4.45
## EA 4.20 0.674 27 2.8202 5.58
## NP 1.41 0.674 27 0.0277 2.79
##
## Degrees-of-freedom method: kenward-roger
## Confidence level used: 0.95#PWC
x5wsa2015_pwc_tp <- cld(x5wsa2015_means_tp, adjust = "none", Letters = letters, reversed = T)
x5wsa2015_pwc_tp## precip = 472:
## treatment lsmean SE df lower.CL upper.CL .group
## EA 5.67 0.674 27 4.2927 7.06 a
## AG 5.56 0.674 27 4.1752 6.94 a
## NP 5.08 0.674 27 3.7027 6.47 a
##
## precip = 579:
## treatment lsmean SE df lower.CL upper.CL .group
## EA 10.87 0.674 27 9.4877 12.25 a
## NP 8.93 0.674 27 7.5452 10.31 a
## AG 5.85 0.674 27 4.4702 7.23 b
##
## precip = 850:
## treatment lsmean SE df lower.CL upper.CL .group
## EA 4.20 0.674 27 2.8202 5.58 a
## AG 3.07 0.674 27 1.6902 4.45 ab
## NP 1.41 0.674 27 0.0277 2.79 b
##
## Degrees-of-freedom method: kenward-roger
## Confidence level used: 0.95
## significance level used: alpha = 0.05
## NOTE: Compact letter displays can be misleading
## because they show NON-findings rather than findings.
## Consider using 'pairs()', 'pwpp()', or 'pwpm()' instead.#transforming it in a data frame to use on ggplot
x5wsa2015_pwc_tp <- as.data.frame(x5wsa2015_pwc_tp)
x5wsa2015_pwc_tp## treatment precip lsmean SE df lower.CL upper.CL .group
## 3 EA 472 5.6750 0.6737057 27 4.29267004 7.05733 a
## 1 AG 472 5.5575 0.6737057 27 4.17517004 6.93983 a
## 2 NP 472 5.0850 0.6737057 27 3.70267004 6.46733 a
## 4 EA 579 10.8700 0.6737057 27 9.48767004 12.25233 a
## 6 NP 579 8.9275 0.6737057 27 7.54517004 10.30983 a
## 5 AG 579 5.8525 0.6737057 27 4.47017004 7.23483 b
## 9 EA 850 4.2025 0.6737057 27 2.82017004 5.58483 a
## 7 AG 850 3.0725 0.6737057 27 1.69017004 4.45483 ab
## 8 NP 850 1.4100 0.6737057 27 0.02767004 2.79233 b#add locations
df <- data.frame (location = c("Tribune", "Hays", "Manhattan"),
precip = c("472", "579", "850"))
x5wsa2015p<- merge(df, x5wsa2015_pwc_tp, by=c("precip"))
x5wsa2015p$location_f =factor(x5wsa2015p$location, levels=c('Tribune', 'Hays', 'Manhattan'))
x5wsa2015p## precip location treatment lsmean SE df lower.CL upper.CL .group
## 1 472 Tribune EA 5.6750 0.6737057 27 4.29267004 7.05733 a
## 2 472 Tribune AG 5.5575 0.6737057 27 4.17517004 6.93983 a
## 3 472 Tribune NP 5.0850 0.6737057 27 3.70267004 6.46733 a
## 4 579 Hays EA 10.8700 0.6737057 27 9.48767004 12.25233 a
## 5 579 Hays NP 8.9275 0.6737057 27 7.54517004 10.30983 a
## 6 579 Hays AG 5.8525 0.6737057 27 4.47017004 7.23483 b
## 7 850 Manhattan EA 4.2025 0.6737057 27 2.82017004 5.58483 a
## 8 850 Manhattan AG 3.0725 0.6737057 27 1.69017004 4.45483 ab
## 9 850 Manhattan NP 1.4100 0.6737057 27 0.02767004 2.79233 b
## location_f
## 1 Tribune
## 2 Tribune
## 3 Tribune
## 4 Hays
## 5 Hays
## 6 Hays
## 7 Manhattan
## 8 Manhattan
## 9 Manhattan4 NRCS Aggregate Graphs
4.1 0-5 cm NRCS minutes
agg5 <- aggr %>%
filter(bdepth==5)
agg10 <- aggr %>%
filter(bdepth==10)
agg15 <- aggr %>%
filter(bdepth==15)
x## [1] "0-5 cm"agg5$precip <- as.factor(agg5$precip)
nagg <- lmer(nagg ~ treatment*precip + (1|replication), data=agg5, na.action=na.omit)
anova(nagg, type=3)## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## treatment 24694.3 12347.2 2 20.3873 291.6684 1.001e-15 ***
## precip 565.5 282.8 2 9.6661 6.6798 0.0150706 *
## treatment:precip 1324.0 331.0 4 20.3728 7.8188 0.0005496 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1nagg_means_tp <- lsmeans(nagg, specs = "treatment", by = "precip")
#PWC
nagg_pwc_tp <- cld(nagg_means_tp, adjust = "none", Letters = letters, reversed = T)
#transforming it in a data frame to use on ggplot
nagg_pwc_tp <- as.data.frame(nagg_pwc_tp)
#add locations
df <- data.frame (location = c("Tribune", "Hays", "Manhattan"),
precip = c("472", "579", "850"))
naggp<- merge(df, nagg_pwc_tp, by=c("precip"))
naggp$location_f =factor(naggp$location, levels=c('Tribune', 'Hays', 'Manhattan'))
naggp## precip location treatment lsmean SE df lower.CL upper.CL
## 1 472 Tribune NP 63.965361 3.395653 25.35995 56.976913 70.953809
## 2 472 Tribune EA 18.059249 3.395653 25.35995 11.070801 25.047697
## 3 472 Tribune AG 8.551010 3.395653 25.35995 1.562563 15.539458
## 4 579 Hays NP 79.341536 3.395653 25.35995 72.353089 86.329984
## 5 579 Hays EA 33.661765 3.395653 25.35995 26.673317 40.650213
## 6 579 Hays AG 8.396014 3.395653 25.35995 1.407567 15.384462
## 7 850 Manhattan NP 71.105925 3.395653 25.35995 64.117478 78.094373
## 8 850 Manhattan EA 45.922074 3.395653 25.35995 38.933627 52.910522
## 9 850 Manhattan AG 1.474729 3.972346 25.86318 -6.692648 9.642106
## .group location_f
## 1 a Tribune
## 2 b Tribune
## 3 b Tribune
## 4 a Hays
## 5 b Hays
## 6 c Hays
## 7 a Manhattan
## 8 b Manhattan
## 9 c Manhattan4.2 5-10 cm NRCS minutes
agg5 <- aggr %>%
filter(bdepth==5)
agg10 <- aggr %>%
filter(bdepth==10)
agg15 <- aggr %>%
filter(bdepth==15)
x## [1] "0-5 cm"agg10$precip <- as.factor(agg10$precip)
nagg10 <- lmer(nagg ~ treatment*precip + (1|replication), data=agg10, na.action=na.omit)
anova(nagg10, type=3)## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## treatment 16061.5 8030.7 2 26 235.869 < 2.2e-16 ***
## precip 1910.3 955.1 2 26 28.053 3.219e-07 ***
## treatment:precip 2078.9 519.7 4 26 15.264 1.521e-06 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1nagg10_means_tp <- lsmeans(nagg10, specs = "treatment", by = "precip")
#PWC
nagg10_pwc_tp <- cld(nagg10_means_tp, adjust = "none", Letters = letters, reversed = T)
#transforming it in a data frame to use on ggplot
nagg10_pwc_tp <- as.data.frame(nagg10_pwc_tp)
#add locations
df <- data.frame (location = c("Tribune", "Hays", "Manhattan"),
precip = c("472", "579", "850"))
nagg10p<- merge(df, nagg10_pwc_tp, by=c("precip"))
nagg10p$location_f =factor(nagg10p$location, levels=c('Tribune', 'Hays', 'Manhattan'))
nagg10p## precip location treatment lsmean SE df lower.CL upper.CL .group
## 1 472 Tribune NP 35.748582 2.917510 26 29.7515545 41.745610 a
## 2 472 Tribune AG 5.721995 2.917510 26 -0.2750325 11.719023 b
## 3 472 Tribune EA 3.686833 2.917510 26 -2.3101946 9.683861 b
## 4 579 Hays NP 67.060386 2.917510 26 61.0633580 73.057413 a
## 5 579 Hays EA 7.599869 2.917510 26 1.6028410 13.596896 b
## 6 579 Hays AG 6.400527 2.917510 26 0.4034990 12.397554 b
## 7 850 Manhattan NP 61.784932 2.917510 26 55.7879043 67.781959 a
## 8 850 Manhattan EA 32.138297 2.917510 26 26.1412695 38.135325 b
## 9 850 Manhattan AG 4.820744 3.452044 26 -2.2750349 11.916522 c
## location_f
## 1 Tribune
## 2 Tribune
## 3 Tribune
## 4 Hays
## 5 Hays
## 6 Hays
## 7 Manhattan
## 8 Manhattan
## 9 Manhattan4.3 10-15 cm NRCS minutes
agg5 <- aggr %>%
filter(bdepth==5)
agg10 <- aggr %>%
filter(bdepth==10)
agg15 <- aggr %>%
filter(bdepth==15)
x## [1] "0-5 cm"agg15$precip <- as.factor(agg15$precip)
nagg15 <- lmer(nagg ~ treatment*precip + (1|replication), data=agg15, na.action=na.omit)
anova(nagg15, type=3)## Type III Analysis of Variance Table with Satterthwaite's method
## Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
## treatment 7948.8 3974.4 2 21.897 70.2258 2.98e-10 ***
## precip 2336.6 1168.3 2 11.762 20.6433 0.0001421 ***
## treatment:precip 1452.6 363.1 4 21.897 6.4167 0.0014156 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1nagg15_means_tp <- lsmeans(nagg15, specs = "treatment", by = "precip")
#PWC
nagg15_pwc_tp <- cld(nagg15_means_tp, adjust = "none", Letters = letters, reversed = T)
#transforming it in a data frame to use on ggplot
nagg15_pwc_tp <- as.data.frame(nagg15_pwc_tp)
#add locations
df <- data.frame (location = c("Tribune", "Hays", "Manhattan"),
precip = c("472", "579", "850"))
nagg15p<- merge(df, nagg15_pwc_tp, by=c("precip"))
nagg15p$location_f =factor(nagg15p$location, levels=c('Tribune', 'Hays', 'Manhattan'))
nagg15p## precip location treatment lsmean SE df lower.CL upper.CL
## 1 472 Tribune NP 19.990638 3.794838 26.96694 12.2038258 27.77745
## 2 472 Tribune EA 4.310915 3.794838 26.96694 -3.4758968 12.09773
## 3 472 Tribune AG 4.156583 3.794838 26.96694 -3.6302288 11.94339
## 4 579 Hays NP 51.534489 3.794838 26.96694 43.7476771 59.32130
## 5 579 Hays AG 17.442633 3.794838 26.96694 9.6558211 25.22944
## 6 579 Hays EA 7.009381 3.794838 26.96694 -0.7774306 14.79619
## 7 850 Manhattan NP 54.878590 3.794838 26.96694 47.0917776 62.66540
## 8 850 Manhattan EA 20.871680 3.794838 26.96694 13.0848680 28.65849
## 9 850 Manhattan AG 9.891704 3.794838 26.96694 2.1048916 17.67852
## .group location_f
## 1 a Tribune
## 2 b Tribune
## 3 b Tribune
## 4 a Hays
## 5 b Hays
## 6 b Hays
## 7 a Manhattan
## 8 b Manhattan
## 9 b Manhattan5 Dataframes
x20wsa2000p## precip location treatment lsmean SE df lower.CL upper.CL .group
## 1 472 Tribune NP 26.3313434 3.527336 27 19.093849 33.568838 a
## 2 472 Tribune EA 8.8448459 3.527336 27 1.607351 16.082341 b
## 3 472 Tribune AG 8.7304187 3.527336 27 1.492924 15.967914 b
## 4 579 Hays NP 30.8387700 3.527336 27 23.601275 38.076265 a
## 5 579 Hays EA 9.3305850 3.527336 27 2.093090 16.568080 b
## 6 579 Hays AG 0.9315208 3.527336 27 -6.305974 8.169016 b
## 7 850 Manhattan NP 25.3077401 3.527336 27 18.070245 32.545235 a
## 8 850 Manhattan EA 11.4886335 3.527336 27 4.251139 18.726128 b
## 9 850 Manhattan AG 1.9782694 3.527336 27 -5.259225 9.215764 b
## location_f
## 1 Tribune
## 2 Tribune
## 3 Tribune
## 4 Hays
## 5 Hays
## 6 Hays
## 7 Manhattan
## 8 Manhattan
## 9 Manhattanx20wsa250p## precip location treatment lsmean SE df lower.CL upper.CL
## 1 472 Tribune NP 25.60527 2.634026 25.7468 20.188356 31.02218
## 2 472 Tribune EA 16.27820 2.634026 25.7468 10.861289 21.69511
## 3 472 Tribune AG 14.44550 2.634026 25.7468 9.028589 19.86241
## 4 579 Hays NP 28.53917 2.634026 25.7468 23.122260 33.95608
## 5 579 Hays EA 22.02193 2.634026 25.7468 16.605020 27.43884
## 6 579 Hays AG 11.97343 2.634026 25.7468 6.556520 17.39034
## 7 850 Manhattan NP 37.24528 2.634026 25.7468 31.828368 42.66219
## 8 850 Manhattan EA 24.97329 2.634026 25.7468 19.556377 30.39020
## 9 850 Manhattan AG 17.62782 2.634026 25.7468 12.210914 23.04474
## .group location_f
## 1 a Tribune
## 2 b Tribune
## 3 b Tribune
## 4 a Hays
## 5 a Hays
## 6 b Hays
## 7 a Manhattan
## 8 b Manhattan
## 9 c Manhattanx20wsa53p## precip location treatment lsmean SE df lower.CL upper.CL
## 1 472 Tribune AG 53.07399 3.736594 22.78911 45.340296 60.80768
## 2 472 Tribune EA 49.13078 3.736594 22.78911 41.397089 56.86447
## 3 472 Tribune NP 22.29726 3.736594 22.78911 14.563572 30.03096
## 4 579 Hays AG 69.79728 3.736594 22.78911 62.063591 77.53098
## 5 579 Hays EA 47.93665 3.736594 22.78911 40.202952 55.67034
## 6 579 Hays NP 14.90930 3.736594 22.78911 7.175602 22.64299
## 7 850 Manhattan AG 61.16504 3.736594 22.78911 53.431345 68.89873
## 8 850 Manhattan EA 47.38140 3.736594 22.78911 39.647708 55.11509
## 9 850 Manhattan NP 16.56350 3.736594 22.78911 8.829805 24.29719
## .group location_f
## 1 a Tribune
## 2 a Tribune
## 3 b Tribune
## 4 a Hays
## 5 b Hays
## 6 c Hays
## 7 a Manhattan
## 8 b Manhattan
## 9 c Manhattanx20wsa20p## precip location treatment lsmean SE df lower.CL upper.CL .group
## 1 472 Tribune AG 6.1575 0.7752837 27 4.5667492 7.748251 a
## 2 472 Tribune EA 3.9900 0.7752837 27 2.3992492 5.580751 ab
## 3 472 Tribune NP 1.9500 0.7752837 27 0.3592492 3.540751 b
## 4 579 Hays AG 5.2825 0.7752837 27 3.6917492 6.873251 a
## 5 579 Hays EA 3.3750 0.7752837 27 1.7842492 4.965751 a
## 6 579 Hays NP 1.0475 0.7752837 27 -0.5432508 2.638251 b
## 7 850 Manhattan AG 7.2450 0.7752837 27 5.6542492 8.835751 a
## 8 850 Manhattan EA 5.1450 0.7752837 27 3.5542492 6.735751 a
## 9 850 Manhattan NP 1.9325 0.7752837 27 0.3417492 3.523251 b
## location_f
## 1 Tribune
## 2 Tribune
## 3 Tribune
## 4 Hays
## 5 Hays
## 6 Hays
## 7 Manhattan
## 8 Manhattan
## 9 Manhattanx20wsa200010p## precip location treatment lsmean SE df lower.CL upper.CL .group
## 1 472 Tribune NP 19.874634 2.079862 27 15.60710952 24.142159 a
## 2 472 Tribune AG 7.158672 2.079862 27 2.89114749 11.426197 b
## 3 472 Tribune EA 2.303734 2.079862 27 -1.96379035 6.571259 b
## 4 579 Hays NP 27.933098 2.079862 27 23.66557284 32.200622 a
## 5 579 Hays EA 4.312530 2.079862 27 0.04500509 8.580054 b
## 6 579 Hays AG 1.369402 2.079862 27 -2.89812306 5.636926 b
## 7 850 Manhattan NP 19.539639 2.079862 27 15.27211447 23.807164 a
## 8 850 Manhattan EA 8.197339 2.079862 27 3.92981461 12.464864 b
## 9 850 Manhattan AG 3.003322 2.079862 27 -1.26420295 7.270846 b
## location_f
## 1 Tribune
## 2 Tribune
## 3 Tribune
## 4 Hays
## 5 Hays
## 6 Hays
## 7 Manhattan
## 8 Manhattan
## 9 Manhattanx20wsa25010p## precip location treatment lsmean SE df lower.CL upper.CL
## 1 472 Tribune NP 33.76226 4.905017 26.37839 23.686887 43.83763
## 2 472 Tribune AG 31.38025 4.905017 26.37839 21.304875 41.45562
## 3 472 Tribune EA 15.88541 4.905017 26.37839 5.810033 25.96078
## 4 579 Hays EA 29.76832 4.905017 26.37839 19.692944 39.84369
## 5 579 Hays NP 22.88141 4.905017 26.37839 12.806039 32.95679
## 6 579 Hays AG 12.44605 4.905017 26.37839 2.370679 22.52143
## 7 850 Manhattan NP 35.21192 4.905017 26.37839 25.136550 45.28730
## 8 850 Manhattan EA 31.98805 4.905017 26.37839 21.912672 42.06342
## 9 850 Manhattan AG 19.00936 4.905017 26.37839 8.933983 29.08473
## .group location_f
## 1 a Tribune
## 2 a Tribune
## 3 b Tribune
## 4 a Hays
## 5 ab Hays
## 6 b Hays
## 7 a Manhattan
## 8 ab Manhattan
## 9 b Manhattanx20wsa5310p## precip location treatment lsmean SE df lower.CL upper.CL
## 1 472 Tribune EA 60.53863 4.905302 20.96793 50.33654 70.74071
## 2 472 Tribune AG 40.25275 4.905302 20.96793 30.05067 50.45484
## 3 472 Tribune NP 24.33689 4.905302 20.96793 14.13481 34.53898
## 4 579 Hays AG 61.04155 4.905302 20.96793 50.83947 71.24364
## 5 579 Hays EA 47.54742 4.905302 20.96793 37.34533 57.74950
## 6 579 Hays NP 28.36159 4.905302 20.96793 18.15950 38.56367
## 7 850 Manhattan AG 60.48042 4.905302 20.96793 50.27834 70.68251
## 8 850 Manhattan EA 45.04338 4.905302 20.96793 34.84130 55.24547
## 9 850 Manhattan NP 23.59988 4.905302 20.96793 13.39779 33.80196
## .group location_f
## 1 a Tribune
## 2 b Tribune
## 3 c Tribune
## 4 a Hays
## 5 b Hays
## 6 c Hays
## 7 a Manhattan
## 8 b Manhattan
## 9 c Manhattanx20wsa2010p## precip location treatment lsmean SE df lower.CL upper.CL .group
## 1 472 Tribune EA 5.4100 0.671795 27 4.0315905 6.78841 a
## 2 472 Tribune AG 4.1075 0.671795 27 2.7290905 5.48591 ab
## 3 472 Tribune NP 2.1825 0.671795 27 0.8040905 3.56091 b
## 4 579 Hays AG 8.7775 0.671795 27 7.3990905 10.15591 a
## 5 579 Hays EA 3.7775 0.671795 27 2.3990905 5.15591 b
## 6 579 Hays NP 1.7575 0.671795 27 0.3790905 3.13591 c
## 7 850 Manhattan EA 5.0475 0.671795 27 3.6690905 6.42591 a
## 8 850 Manhattan AG 4.8125 0.671795 27 3.4340905 6.19091 ab
## 9 850 Manhattan NP 3.0400 0.671795 27 1.6615905 4.41841 b
## location_f
## 1 Tribune
## 2 Tribune
## 3 Tribune
## 4 Hays
## 5 Hays
## 6 Hays
## 7 Manhattan
## 8 Manhattan
## 9 Manhattanx20wsa200015p## precip location treatment lsmean SE df lower.CL upper.CL .group
## 1 472 Tribune NP 26.297002 1.901863 27 22.3947003 30.199303 a
## 2 472 Tribune AG 7.344079 1.901863 27 3.4417780 11.246381 b
## 3 472 Tribune EA 3.058975 1.901863 27 -0.8433266 6.961276 b
## 4 579 Hays NP 23.871558 1.901863 27 19.9692562 27.773859 a
## 5 579 Hays EA 2.561610 1.901863 27 -1.3406916 6.463911 b
## 6 579 Hays AG 1.931631 1.901863 27 -1.9706708 5.833932 b
## 7 850 Manhattan NP 25.368150 1.901863 27 21.4658488 29.270451 a
## 8 850 Manhattan EA 4.378598 1.901863 27 0.4762962 8.280899 b
## 9 850 Manhattan AG 2.653159 1.901863 27 -1.2491423 6.555460 b
## location_f
## 1 Tribune
## 2 Tribune
## 3 Tribune
## 4 Hays
## 5 Hays
## 6 Hays
## 7 Manhattan
## 8 Manhattan
## 9 Manhattanx20wsa25015p## precip location treatment lsmean SE df lower.CL upper.CL
## 1 472 Tribune NP 31.52114 5.299915 24.42448 20.592709 42.44958
## 2 472 Tribune AG 27.33366 5.299915 24.42448 16.405226 38.26210
## 3 472 Tribune EA 15.88228 5.299915 24.42448 4.953841 26.81071
## 4 579 Hays AG 32.94085 5.299915 24.42448 22.012414 43.86929
## 5 579 Hays NP 23.26334 5.299915 24.42448 12.334906 34.19178
## 6 579 Hays EA 18.86667 5.299915 24.42448 7.938236 29.79511
## 7 850 Manhattan NP 37.56309 5.299915 24.42448 26.634649 48.49152
## 8 850 Manhattan AG 29.49422 5.299915 24.42448 18.565782 40.42265
## 9 850 Manhattan EA 25.79500 5.299915 24.42448 14.866564 36.72344
## .group location_f
## 1 a Tribune
## 2 ab Tribune
## 3 b Tribune
## 4 a Hays
## 5 a Hays
## 6 a Hays
## 7 a Manhattan
## 8 a Manhattan
## 9 a Manhattanx20wsa5315p## precip location treatment lsmean SE df lower.CL upper.CL
## 1 472 Tribune EA 51.12957 5.586198 26.3469 39.654327 62.60481
## 2 472 Tribune AG 43.85542 5.586198 26.3469 32.380181 55.33066
## 3 472 Tribune NP 20.87374 5.586198 26.3469 9.398503 32.34898
## 4 579 Hays EA 59.98533 5.586198 26.3469 48.510085 71.46056
## 5 579 Hays AG 44.03529 5.586198 26.3469 32.560046 55.51053
## 6 579 Hays NP 32.68928 5.586198 26.3469 21.214043 44.16452
## 7 850 Manhattan AG 54.04183 5.586198 26.3469 42.566587 65.51707
## 8 850 Manhattan EA 52.36527 5.586198 26.3469 40.890028 63.84051
## 9 850 Manhattan NP 19.45423 5.586198 26.3469 7.978991 30.92947
## .group location_f
## 1 a Tribune
## 2 a Tribune
## 3 b Tribune
## 4 a Hays
## 5 b Hays
## 6 b Hays
## 7 a Manhattan
## 8 a Manhattan
## 9 b Manhattanx20wsa2015p## precip location treatment lsmean SE df lower.CL upper.CL
## 1 472 Tribune EA 8.4225 1.094354 22.58634 6.1563605 10.688639
## 2 472 Tribune AG 4.4125 1.094354 22.58634 2.1463605 6.678639
## 3 472 Tribune NP 1.6150 1.094354 22.58634 -0.6511395 3.881139
## 4 579 Hays AG 7.8275 1.094354 22.58634 5.5613605 10.093639
## 5 579 Hays EA 5.5625 1.094354 22.58634 3.2963605 7.828639
## 6 579 Hays NP 2.4400 1.094354 22.58634 0.1738605 4.706139
## 7 850 Manhattan EA 6.9400 1.094354 22.58634 4.6738605 9.206139
## 8 850 Manhattan AG 3.4700 1.094354 22.58634 1.2038605 5.736139
## 9 850 Manhattan NP 1.7325 1.094354 22.58634 -0.5336395 3.998639
## .group location_f
## 1 a Tribune
## 2 b Tribune
## 3 b Tribune
## 4 a Hays
## 5 a Hays
## 6 b Hays
## 7 a Manhattan
## 8 b Manhattan
## 9 b Manhattanx5wsa2000p## precip location treatment lsmean SE df lower.CL upper.CL
## 1 472 Tribune EA 10.186894 2.267247 21.87134 5.483308 14.890481
## 2 472 Tribune NP 8.822787 2.267247 21.87134 4.119200 13.526373
## 3 472 Tribune AG 6.619284 2.267247 21.87134 1.915697 11.322870
## 4 579 Hays NP 44.065476 2.267247 21.87134 39.361889 48.769062
## 5 579 Hays EA 25.901540 2.267247 21.87134 21.197953 30.605126
## 6 579 Hays AG 1.563937 2.267247 21.87134 -3.139650 6.267523
## 7 850 Manhattan NP 25.434619 2.267247 21.87134 20.731032 30.138205
## 8 850 Manhattan EA 14.241278 2.267247 21.87134 9.537691 18.944864
## 9 850 Manhattan AG 2.857780 2.267247 21.87134 -1.845807 7.561367
## .group location_f
## 1 a Tribune
## 2 a Tribune
## 3 a Tribune
## 4 a Hays
## 5 b Hays
## 6 c Hays
## 7 a Manhattan
## 8 b Manhattan
## 9 c Manhattanx5wsa250p## precip location treatment lsmean SE df lower.CL upper.CL
## 1 472 Tribune EA 29.018520 3.940058 26.52673 20.927435 37.10960
## 2 472 Tribune NP 27.005202 3.940058 26.52673 18.914117 35.09629
## 3 472 Tribune AG 9.931781 3.940058 26.52673 1.840697 18.02287
## 4 579 Hays NP 32.570016 3.940058 26.52673 24.478931 40.66110
## 5 579 Hays AG 27.649027 3.940058 26.52673 19.557942 35.74011
## 6 579 Hays EA 26.595305 3.940058 26.52673 18.504220 34.68639
## 7 850 Manhattan NP 44.262281 3.940058 26.52673 36.171196 52.35337
## 8 850 Manhattan EA 31.323713 3.940058 26.52673 23.232629 39.41480
## 9 850 Manhattan AG 28.049438 3.940058 26.52673 19.958353 36.14052
## .group location_f
## 1 a Tribune
## 2 a Tribune
## 3 b Tribune
## 4 a Hays
## 5 a Hays
## 6 a Hays
## 7 a Manhattan
## 8 b Manhattan
## 9 b Manhattanx5wsa53p## precip location treatment lsmean SE df lower.CL upper.CL
## 1 472 Tribune AG 51.28463 4.308961 26.93583 42.442385 60.12687
## 2 472 Tribune EA 35.12016 4.308961 26.93583 26.277920 43.96241
## 3 472 Tribune NP 23.41428 4.308961 26.93583 14.572037 32.25652
## 4 579 Hays AG 46.22015 4.308961 26.93583 37.377911 55.06240
## 5 579 Hays EA 39.81846 4.308961 26.93583 30.976213 48.66070
## 6 579 Hays NP 18.92336 4.308961 26.93583 10.081112 27.76560
## 7 850 Manhattan AG 52.78271 4.308961 26.93583 43.940465 61.62495
## 8 850 Manhattan EA 30.85960 4.308961 26.93583 22.017359 39.70184
## 9 850 Manhattan NP 12.95212 4.308961 26.93583 4.109876 21.79436
## .group location_f
## 1 a Tribune
## 2 b Tribune
## 3 b Tribune
## 4 a Hays
## 5 a Hays
## 6 b Hays
## 7 a Manhattan
## 8 b Manhattan
## 9 c Manhattanx5wsa20p## precip location treatment lsmean SE df lower.CL upper.CL
## 1 472 Tribune AG 6.822500 2.423439 27 1.850013269 11.794987
## 2 472 Tribune NP 5.255000 2.423439 27 0.282513269 10.227487
## 3 472 Tribune EA 4.965000 2.423439 27 -0.007486731 9.937487
## 4 579 Hays EA 16.817500 2.423439 27 11.845013269 21.789987
## 5 579 Hays NP 8.617500 2.423439 27 3.645013269 13.589987
## 6 579 Hays AG 6.052500 2.423439 27 1.080013269 11.024987
## 7 850 Manhattan AG 3.980000 2.423439 27 -0.992486731 8.952487
## 8 850 Manhattan EA 3.775000 2.423439 27 -1.197486731 8.747487
## 9 850 Manhattan NP 1.433954 2.423439 27 -3.538532696 6.406441
## .group location_f
## 1 a Tribune
## 2 a Tribune
## 3 a Tribune
## 4 a Hays
## 5 b Hays
## 6 b Hays
## 7 a Manhattan
## 8 a Manhattan
## 9 a Manhattanx5wsa200010p## precip location treatment lsmean SE df lower.CL upper.CL
## 1 472 Tribune NP 7.784108 2.481473 26.41131 2.687230 12.880986
## 2 472 Tribune AG 7.358129 2.481473 26.41131 2.261251 12.455007
## 3 472 Tribune EA 3.989024 2.481473 26.41131 -1.107854 9.085902
## 4 579 Hays NP 47.950775 2.481473 26.41131 42.853897 53.047653
## 5 579 Hays EA 10.999532 2.481473 26.41131 5.902654 16.096410
## 6 579 Hays AG 3.551578 2.481473 26.41131 -1.545301 8.648456
## 7 850 Manhattan NP 27.719093 2.481473 26.41131 22.622215 32.815972
## 8 850 Manhattan EA 18.601440 2.481473 26.41131 13.504562 23.698318
## 9 850 Manhattan AG 4.704605 2.481473 26.41131 -0.392273 9.801483
## .group location_f
## 1 a Tribune
## 2 a Tribune
## 3 a Tribune
## 4 a Hays
## 5 b Hays
## 6 c Hays
## 7 a Manhattan
## 8 b Manhattan
## 9 c Manhattanx5wsa25010p## precip location treatment lsmean SE df lower.CL upper.CL
## 1 472 Tribune NP 36.00030 4.391035 26.94418 26.989762 45.01083
## 2 472 Tribune EA 17.12701 4.391035 26.94418 8.116474 26.13754
## 3 472 Tribune AG 15.92634 4.391035 26.94418 6.915812 24.93688
## 4 579 Hays EA 38.08866 4.391035 26.94418 29.078132 47.09920
## 5 579 Hays NP 37.44081 4.391035 26.94418 28.430276 46.45134
## 6 579 Hays AG 16.11014 4.391035 26.94418 7.099607 25.12067
## 7 850 Manhattan NP 44.20709 4.391035 26.94418 35.196554 53.21762
## 8 850 Manhattan AG 41.27775 4.391035 26.94418 32.267214 50.28828
## 9 850 Manhattan EA 37.56607 4.391035 26.94418 28.555534 46.57660
## .group location_f
## 1 a Tribune
## 2 b Tribune
## 3 b Tribune
## 4 a Hays
## 5 a Hays
## 6 b Hays
## 7 a Manhattan
## 8 a Manhattan
## 9 a Manhattanx5wsa5310p## precip location treatment lsmean SE df lower.CL upper.CL
## 1 472 Tribune EA 56.26802 4.646506 26.97369 46.733745 65.80230
## 2 472 Tribune AG 48.79037 4.646506 26.97369 39.256094 58.32465
## 3 472 Tribune NP 28.54305 4.646506 26.97369 19.008772 38.07733
## 4 579 Hays AG 53.84427 4.646506 26.97369 44.309997 63.37855
## 5 579 Hays EA 52.73937 4.646506 26.97369 43.205095 62.27365
## 6 579 Hays NP 26.00424 4.646506 26.97369 16.469966 35.53852
## 7 850 Manhattan AG 42.54411 4.646506 26.97369 33.009834 52.07839
## 8 850 Manhattan EA 23.87843 4.646506 26.97369 14.344149 33.41270
## 9 850 Manhattan NP 12.82837 4.646506 26.97369 3.294094 22.36265
## .group location_f
## 1 a Tribune
## 2 a Tribune
## 3 b Tribune
## 4 a Hays
## 5 a Hays
## 6 b Hays
## 7 a Manhattan
## 8 b Manhattan
## 9 b Manhattanx5wsa2010p## precip location treatment lsmean SE df lower.CL upper.CL .group
## 1 472 Tribune AG 7.5800 0.9417107 27 5.6477693 9.512231 a
## 2 472 Tribune EA 6.5025 0.9417107 27 4.5702693 8.434731 a
## 3 472 Tribune NP 4.8950 0.9417107 27 2.9627693 6.827231 a
## 4 579 Hays EA 11.5525 0.9417107 27 9.6202693 13.484731 a
## 5 579 Hays NP 9.0175 0.9417107 27 7.0852693 10.949731 a
## 6 579 Hays AG 5.6325 0.9417107 27 3.7002693 7.564731 b
## 7 850 Manhattan EA 4.2475 0.9417107 27 2.3152693 6.179731 a
## 8 850 Manhattan AG 2.2525 0.9417107 27 0.3202693 4.184731 a
## 9 850 Manhattan NP 1.7150 0.9417107 27 -0.2172307 3.647231 a
## location_f
## 1 Tribune
## 2 Tribune
## 3 Tribune
## 4 Hays
## 5 Hays
## 6 Hays
## 7 Manhattan
## 8 Manhattan
## 9 Manhattanx5wsa200015p## precip location treatment lsmean SE df lower.CL upper.CL .group
## 1 472 Tribune NP 14.583834 4.005528 27 6.3651697 22.80250 a
## 2 472 Tribune AG 6.606750 4.005528 27 -1.6119142 14.82541 a
## 3 472 Tribune EA 6.572290 4.005528 27 -1.6463741 14.79095 a
## 4 579 Hays NP 40.495560 4.005528 27 32.2768962 48.71422 a
## 5 579 Hays AG 11.637256 4.005528 27 3.4185919 19.85592 b
## 6 579 Hays EA 7.687615 4.005528 27 -0.5310489 15.90628 b
## 7 850 Manhattan NP 26.750084 4.005528 27 18.5314199 34.96875 a
## 8 850 Manhattan EA 15.118422 4.005528 27 6.8997576 23.33709 ab
## 9 850 Manhattan AG 4.467970 4.005528 27 -3.7506942 12.68663 b
## location_f
## 1 Tribune
## 2 Tribune
## 3 Tribune
## 4 Hays
## 5 Hays
## 6 Hays
## 7 Manhattan
## 8 Manhattan
## 9 Manhattanx5wsa25015p## precip location treatment lsmean SE df lower.CL upper.CL .group
## 1 472 Tribune EA 32.71524 5.772062 27 20.871950 44.55854 a
## 2 472 Tribune AG 19.59991 5.772062 27 7.756621 31.44321 a
## 3 472 Tribune NP 18.03246 5.772062 27 6.189164 29.87575 a
## 4 579 Hays EA 45.46467 5.772062 27 33.621372 57.30796 a
## 5 579 Hays NP 32.09403 5.772062 27 20.250733 43.93732 a
## 6 579 Hays AG 32.00845 5.772062 27 20.165157 43.85174 a
## 7 850 Manhattan AG 52.68674 5.772062 27 40.843442 64.53003 a
## 8 850 Manhattan NP 37.69254 5.772062 27 25.849249 49.53584 a
## 9 850 Manhattan EA 36.01735 5.772062 27 24.174053 47.86064 a
## location_f
## 1 Tribune
## 2 Tribune
## 3 Tribune
## 4 Hays
## 5 Hays
## 6 Hays
## 7 Manhattan
## 8 Manhattan
## 9 Manhattanx5wsa5315p## precip location treatment lsmean SE df lower.CL upper.CL .group
## 1 472 Tribune AG 54.06194 5.790714 27 42.180374 65.94350 a
## 2 472 Tribune EA 41.10064 5.790714 27 29.219080 52.98221 ab
## 3 472 Tribune NP 33.01473 5.790714 27 21.133171 44.89630 b
## 4 579 Hays EA 49.59674 5.790714 27 37.715174 61.47830 a
## 5 579 Hays AG 32.26746 5.790714 27 20.385893 44.14902 b
## 6 579 Hays NP 26.41757 5.790714 27 14.536007 38.29913 b
## 7 850 Manhattan AG 33.09569 5.790714 27 21.214123 44.97725 a
## 8 850 Manhattan EA 29.54047 5.790714 27 17.658910 41.42204 a
## 9 850 Manhattan NP 20.06624 5.790714 27 8.184675 31.94780 a
## location_f
## 1 Tribune
## 2 Tribune
## 3 Tribune
## 4 Hays
## 5 Hays
## 6 Hays
## 7 Manhattan
## 8 Manhattan
## 9 Manhattanx5wsa2015p## precip location treatment lsmean SE df lower.CL upper.CL .group
## 1 472 Tribune EA 5.6750 0.6737057 27 4.29267004 7.05733 a
## 2 472 Tribune AG 5.5575 0.6737057 27 4.17517004 6.93983 a
## 3 472 Tribune NP 5.0850 0.6737057 27 3.70267004 6.46733 a
## 4 579 Hays EA 10.8700 0.6737057 27 9.48767004 12.25233 a
## 5 579 Hays NP 8.9275 0.6737057 27 7.54517004 10.30983 a
## 6 579 Hays AG 5.8525 0.6737057 27 4.47017004 7.23483 b
## 7 850 Manhattan EA 4.2025 0.6737057 27 2.82017004 5.58483 a
## 8 850 Manhattan AG 3.0725 0.6737057 27 1.69017004 4.45483 ab
## 9 850 Manhattan NP 1.4100 0.6737057 27 0.02767004 2.79233 b
## location_f
## 1 Tribune
## 2 Tribune
## 3 Tribune
## 4 Hays
## 5 Hays
## 6 Hays
## 7 Manhattan
## 8 Manhattan
## 9 Manhattannaggp## precip location treatment lsmean SE df lower.CL upper.CL
## 1 472 Tribune NP 63.965361 3.395653 25.35995 56.976913 70.953809
## 2 472 Tribune EA 18.059249 3.395653 25.35995 11.070801 25.047697
## 3 472 Tribune AG 8.551010 3.395653 25.35995 1.562563 15.539458
## 4 579 Hays NP 79.341536 3.395653 25.35995 72.353089 86.329984
## 5 579 Hays EA 33.661765 3.395653 25.35995 26.673317 40.650213
## 6 579 Hays AG 8.396014 3.395653 25.35995 1.407567 15.384462
## 7 850 Manhattan NP 71.105925 3.395653 25.35995 64.117478 78.094373
## 8 850 Manhattan EA 45.922074 3.395653 25.35995 38.933627 52.910522
## 9 850 Manhattan AG 1.474729 3.972346 25.86318 -6.692648 9.642106
## .group location_f
## 1 a Tribune
## 2 b Tribune
## 3 b Tribune
## 4 a Hays
## 5 b Hays
## 6 c Hays
## 7 a Manhattan
## 8 b Manhattan
## 9 c Manhattannagg10p## precip location treatment lsmean SE df lower.CL upper.CL .group
## 1 472 Tribune NP 35.748582 2.917510 26 29.7515545 41.745610 a
## 2 472 Tribune AG 5.721995 2.917510 26 -0.2750325 11.719023 b
## 3 472 Tribune EA 3.686833 2.917510 26 -2.3101946 9.683861 b
## 4 579 Hays NP 67.060386 2.917510 26 61.0633580 73.057413 a
## 5 579 Hays EA 7.599869 2.917510 26 1.6028410 13.596896 b
## 6 579 Hays AG 6.400527 2.917510 26 0.4034990 12.397554 b
## 7 850 Manhattan NP 61.784932 2.917510 26 55.7879043 67.781959 a
## 8 850 Manhattan EA 32.138297 2.917510 26 26.1412695 38.135325 b
## 9 850 Manhattan AG 4.820744 3.452044 26 -2.2750349 11.916522 c
## location_f
## 1 Tribune
## 2 Tribune
## 3 Tribune
## 4 Hays
## 5 Hays
## 6 Hays
## 7 Manhattan
## 8 Manhattan
## 9 Manhattannagg15p## precip location treatment lsmean SE df lower.CL upper.CL
## 1 472 Tribune NP 19.990638 3.794838 26.96694 12.2038258 27.77745
## 2 472 Tribune EA 4.310915 3.794838 26.96694 -3.4758968 12.09773
## 3 472 Tribune AG 4.156583 3.794838 26.96694 -3.6302288 11.94339
## 4 579 Hays NP 51.534489 3.794838 26.96694 43.7476771 59.32130
## 5 579 Hays AG 17.442633 3.794838 26.96694 9.6558211 25.22944
## 6 579 Hays EA 7.009381 3.794838 26.96694 -0.7774306 14.79619
## 7 850 Manhattan NP 54.878590 3.794838 26.96694 47.0917776 62.66540
## 8 850 Manhattan EA 20.871680 3.794838 26.96694 13.0848680 28.65849
## 9 850 Manhattan AG 9.891704 3.794838 26.96694 2.1048916 17.67852
## .group location_f
## 1 a Tribune
## 2 b Tribune
## 3 b Tribune
## 4 a Hays
## 5 b Hays
## 6 b Hays
## 7 a Manhattan
## 8 b Manhattan
## 9 b Manhattan6 Adding location x to data frame
#8-2 gets 0.7, 1, 1.3 for AG, EA, NP
df8_2 <- data.frame (treatment = c("AG", "EA", "NP"),
xloc = c(".7", "1", "1.3"))
x20wsa2000p <- merge(x20wsa2000p, df8_2, by=c("treatment"))
x20wsa2000p## treatment precip location lsmean SE df lower.CL upper.CL .group
## 1 AG 579 Hays 0.9315208 3.527336 27 -6.305974 8.169016 b
## 2 AG 472 Tribune 8.7304187 3.527336 27 1.492924 15.967914 b
## 3 AG 850 Manhattan 1.9782694 3.527336 27 -5.259225 9.215764 b
## 4 EA 472 Tribune 8.8448459 3.527336 27 1.607351 16.082341 b
## 5 EA 579 Hays 9.3305850 3.527336 27 2.093090 16.568080 b
## 6 EA 850 Manhattan 11.4886335 3.527336 27 4.251139 18.726128 b
## 7 NP 472 Tribune 26.3313434 3.527336 27 19.093849 33.568838 a
## 8 NP 850 Manhattan 25.3077401 3.527336 27 18.070245 32.545235 a
## 9 NP 579 Hays 30.8387700 3.527336 27 23.601275 38.076265 a
## location_f xloc
## 1 Hays .7
## 2 Tribune .7
## 3 Manhattan .7
## 4 Tribune 1
## 5 Hays 1
## 6 Manhattan 1
## 7 Tribune 1.3
## 8 Manhattan 1.3
## 9 Hays 1.3x20wsa200010p<- merge(x20wsa200010p, df8_2, by=c("treatment"))
x20wsa200010p## treatment precip location lsmean SE df lower.CL upper.CL .group
## 1 AG 472 Tribune 7.158672 2.079862 27 2.89114749 11.426197 b
## 2 AG 850 Manhattan 3.003322 2.079862 27 -1.26420295 7.270846 b
## 3 AG 579 Hays 1.369402 2.079862 27 -2.89812306 5.636926 b
## 4 EA 472 Tribune 2.303734 2.079862 27 -1.96379035 6.571259 b
## 5 EA 850 Manhattan 8.197339 2.079862 27 3.92981461 12.464864 b
## 6 EA 579 Hays 4.312530 2.079862 27 0.04500509 8.580054 b
## 7 NP 472 Tribune 19.874634 2.079862 27 15.60710952 24.142159 a
## 8 NP 850 Manhattan 19.539639 2.079862 27 15.27211447 23.807164 a
## 9 NP 579 Hays 27.933098 2.079862 27 23.66557284 32.200622 a
## location_f xloc
## 1 Tribune .7
## 2 Manhattan .7
## 3 Hays .7
## 4 Tribune 1
## 5 Manhattan 1
## 6 Hays 1
## 7 Tribune 1.3
## 8 Manhattan 1.3
## 9 Hays 1.3x20wsa200015p<- merge(x20wsa200015p, df8_2, by=c("treatment"))
x20wsa200015p## treatment precip location lsmean SE df lower.CL upper.CL .group
## 1 AG 472 Tribune 7.344079 1.901863 27 3.4417780 11.246381 b
## 2 AG 850 Manhattan 2.653159 1.901863 27 -1.2491423 6.555460 b
## 3 AG 579 Hays 1.931631 1.901863 27 -1.9706708 5.833932 b
## 4 EA 472 Tribune 3.058975 1.901863 27 -0.8433266 6.961276 b
## 5 EA 850 Manhattan 4.378598 1.901863 27 0.4762962 8.280899 b
## 6 EA 579 Hays 2.561610 1.901863 27 -1.3406916 6.463911 b
## 7 NP 472 Tribune 26.297002 1.901863 27 22.3947003 30.199303 a
## 8 NP 850 Manhattan 25.368150 1.901863 27 21.4658488 29.270451 a
## 9 NP 579 Hays 23.871558 1.901863 27 19.9692562 27.773859 a
## location_f xloc
## 1 Tribune .7
## 2 Manhattan .7
## 3 Hays .7
## 4 Tribune 1
## 5 Manhattan 1
## 6 Hays 1
## 7 Tribune 1.3
## 8 Manhattan 1.3
## 9 Hays 1.3x5wsa2000p<- merge(x5wsa2000p, df8_2, by=c("treatment"))
x5wsa2000p## treatment precip location lsmean SE df lower.CL upper.CL
## 1 AG 579 Hays 1.563937 2.267247 21.87134 -3.139650 6.267523
## 2 AG 472 Tribune 6.619284 2.267247 21.87134 1.915697 11.322870
## 3 AG 850 Manhattan 2.857780 2.267247 21.87134 -1.845807 7.561367
## 4 EA 472 Tribune 10.186894 2.267247 21.87134 5.483308 14.890481
## 5 EA 850 Manhattan 14.241278 2.267247 21.87134 9.537691 18.944864
## 6 EA 579 Hays 25.901540 2.267247 21.87134 21.197953 30.605126
## 7 NP 472 Tribune 8.822787 2.267247 21.87134 4.119200 13.526373
## 8 NP 850 Manhattan 25.434619 2.267247 21.87134 20.731032 30.138205
## 9 NP 579 Hays 44.065476 2.267247 21.87134 39.361889 48.769062
## .group location_f xloc
## 1 c Hays .7
## 2 a Tribune .7
## 3 c Manhattan .7
## 4 a Tribune 1
## 5 b Manhattan 1
## 6 b Hays 1
## 7 a Tribune 1.3
## 8 a Manhattan 1.3
## 9 a Hays 1.3x5wsa200010p<- merge(x5wsa200010p, df8_2, by=c("treatment"))
x5wsa200010p## treatment precip location lsmean SE df lower.CL upper.CL
## 1 AG 472 Tribune 7.358129 2.481473 26.41131 2.261251 12.455007
## 2 AG 850 Manhattan 4.704605 2.481473 26.41131 -0.392273 9.801483
## 3 AG 579 Hays 3.551578 2.481473 26.41131 -1.545301 8.648456
## 4 EA 472 Tribune 3.989024 2.481473 26.41131 -1.107854 9.085902
## 5 EA 850 Manhattan 18.601440 2.481473 26.41131 13.504562 23.698318
## 6 EA 579 Hays 10.999532 2.481473 26.41131 5.902654 16.096410
## 7 NP 472 Tribune 7.784108 2.481473 26.41131 2.687230 12.880986
## 8 NP 850 Manhattan 27.719093 2.481473 26.41131 22.622215 32.815972
## 9 NP 579 Hays 47.950775 2.481473 26.41131 42.853897 53.047653
## .group location_f xloc
## 1 a Tribune .7
## 2 c Manhattan .7
## 3 c Hays .7
## 4 a Tribune 1
## 5 b Manhattan 1
## 6 b Hays 1
## 7 a Tribune 1.3
## 8 a Manhattan 1.3
## 9 a Hays 1.3x5wsa200015p<- merge(x5wsa200015p, df8_2, by=c("treatment"))
x5wsa200015p## treatment precip location lsmean SE df lower.CL upper.CL .group
## 1 AG 472 Tribune 6.606750 4.005528 27 -1.6119142 14.82541 a
## 2 AG 579 Hays 11.637256 4.005528 27 3.4185919 19.85592 b
## 3 AG 850 Manhattan 4.467970 4.005528 27 -3.7506942 12.68663 b
## 4 EA 579 Hays 7.687615 4.005528 27 -0.5310489 15.90628 b
## 5 EA 472 Tribune 6.572290 4.005528 27 -1.6463741 14.79095 a
## 6 EA 850 Manhattan 15.118422 4.005528 27 6.8997576 23.33709 ab
## 7 NP 472 Tribune 14.583834 4.005528 27 6.3651697 22.80250 a
## 8 NP 850 Manhattan 26.750084 4.005528 27 18.5314199 34.96875 a
## 9 NP 579 Hays 40.495560 4.005528 27 32.2768962 48.71422 a
## location_f xloc
## 1 Tribune .7
## 2 Hays .7
## 3 Manhattan .7
## 4 Hays 1
## 5 Tribune 1
## 6 Manhattan 1
## 7 Tribune 1.3
## 8 Manhattan 1.3
## 9 Hays 1.3#2-0.25 gets 1.7, 2, 2.3 for AG, EA, NP
df2_025 <- data.frame (treatment = c("AG", "EA", "NP"),
xloc = c("1.7", "2", "2.3"))
x20wsa250p<- merge(x20wsa250p, df2_025, by=c("treatment"))
x20wsa250p## treatment precip location lsmean SE df lower.CL upper.CL
## 1 AG 579 Hays 11.97343 2.634026 25.7468 6.556520 17.39034
## 2 AG 472 Tribune 14.44550 2.634026 25.7468 9.028589 19.86241
## 3 AG 850 Manhattan 17.62782 2.634026 25.7468 12.210914 23.04474
## 4 EA 472 Tribune 16.27820 2.634026 25.7468 10.861289 21.69511
## 5 EA 579 Hays 22.02193 2.634026 25.7468 16.605020 27.43884
## 6 EA 850 Manhattan 24.97329 2.634026 25.7468 19.556377 30.39020
## 7 NP 472 Tribune 25.60527 2.634026 25.7468 20.188356 31.02218
## 8 NP 850 Manhattan 37.24528 2.634026 25.7468 31.828368 42.66219
## 9 NP 579 Hays 28.53917 2.634026 25.7468 23.122260 33.95608
## .group location_f xloc
## 1 b Hays 1.7
## 2 b Tribune 1.7
## 3 c Manhattan 1.7
## 4 b Tribune 2
## 5 a Hays 2
## 6 b Manhattan 2
## 7 a Tribune 2.3
## 8 a Manhattan 2.3
## 9 a Hays 2.3x20wsa25010p<- merge(x20wsa25010p, df2_025, by=c("treatment"))
x20wsa25010p## treatment precip location lsmean SE df lower.CL upper.CL
## 1 AG 472 Tribune 31.38025 4.905017 26.37839 21.304875 41.45562
## 2 AG 579 Hays 12.44605 4.905017 26.37839 2.370679 22.52143
## 3 AG 850 Manhattan 19.00936 4.905017 26.37839 8.933983 29.08473
## 4 EA 579 Hays 29.76832 4.905017 26.37839 19.692944 39.84369
## 5 EA 472 Tribune 15.88541 4.905017 26.37839 5.810033 25.96078
## 6 EA 850 Manhattan 31.98805 4.905017 26.37839 21.912672 42.06342
## 7 NP 472 Tribune 33.76226 4.905017 26.37839 23.686887 43.83763
## 8 NP 850 Manhattan 35.21192 4.905017 26.37839 25.136550 45.28730
## 9 NP 579 Hays 22.88141 4.905017 26.37839 12.806039 32.95679
## .group location_f xloc
## 1 a Tribune 1.7
## 2 b Hays 1.7
## 3 b Manhattan 1.7
## 4 a Hays 2
## 5 b Tribune 2
## 6 ab Manhattan 2
## 7 a Tribune 2.3
## 8 a Manhattan 2.3
## 9 ab Hays 2.3x20wsa25015p<- merge(x20wsa25015p, df2_025, by=c("treatment"))
x20wsa25015p## treatment precip location lsmean SE df lower.CL upper.CL
## 1 AG 472 Tribune 27.33366 5.299915 24.42448 16.405226 38.26210
## 2 AG 579 Hays 32.94085 5.299915 24.42448 22.012414 43.86929
## 3 AG 850 Manhattan 29.49422 5.299915 24.42448 18.565782 40.42265
## 4 EA 579 Hays 18.86667 5.299915 24.42448 7.938236 29.79511
## 5 EA 472 Tribune 15.88228 5.299915 24.42448 4.953841 26.81071
## 6 EA 850 Manhattan 25.79500 5.299915 24.42448 14.866564 36.72344
## 7 NP 472 Tribune 31.52114 5.299915 24.42448 20.592709 42.44958
## 8 NP 850 Manhattan 37.56309 5.299915 24.42448 26.634649 48.49152
## 9 NP 579 Hays 23.26334 5.299915 24.42448 12.334906 34.19178
## .group location_f xloc
## 1 ab Tribune 1.7
## 2 a Hays 1.7
## 3 a Manhattan 1.7
## 4 a Hays 2
## 5 b Tribune 2
## 6 a Manhattan 2
## 7 a Tribune 2.3
## 8 a Manhattan 2.3
## 9 a Hays 2.3x5wsa250p<- merge(x5wsa250p, df2_025, by=c("treatment"))
x5wsa250p## treatment precip location lsmean SE df lower.CL upper.CL
## 1 AG 579 Hays 27.649027 3.940058 26.52673 19.557942 35.74011
## 2 AG 472 Tribune 9.931781 3.940058 26.52673 1.840697 18.02287
## 3 AG 850 Manhattan 28.049438 3.940058 26.52673 19.958353 36.14052
## 4 EA 472 Tribune 29.018520 3.940058 26.52673 20.927435 37.10960
## 5 EA 579 Hays 26.595305 3.940058 26.52673 18.504220 34.68639
## 6 EA 850 Manhattan 31.323713 3.940058 26.52673 23.232629 39.41480
## 7 NP 850 Manhattan 44.262281 3.940058 26.52673 36.171196 52.35337
## 8 NP 472 Tribune 27.005202 3.940058 26.52673 18.914117 35.09629
## 9 NP 579 Hays 32.570016 3.940058 26.52673 24.478931 40.66110
## .group location_f xloc
## 1 a Hays 1.7
## 2 b Tribune 1.7
## 3 b Manhattan 1.7
## 4 a Tribune 2
## 5 a Hays 2
## 6 b Manhattan 2
## 7 a Manhattan 2.3
## 8 a Tribune 2.3
## 9 a Hays 2.3x5wsa25010p<- merge(x5wsa25010p, df2_025, by=c("treatment"))
x5wsa25010p## treatment precip location lsmean SE df lower.CL upper.CL
## 1 AG 579 Hays 16.11014 4.391035 26.94418 7.099607 25.12067
## 2 AG 472 Tribune 15.92634 4.391035 26.94418 6.915812 24.93688
## 3 AG 850 Manhattan 41.27775 4.391035 26.94418 32.267214 50.28828
## 4 EA 472 Tribune 17.12701 4.391035 26.94418 8.116474 26.13754
## 5 EA 579 Hays 38.08866 4.391035 26.94418 29.078132 47.09920
## 6 EA 850 Manhattan 37.56607 4.391035 26.94418 28.555534 46.57660
## 7 NP 472 Tribune 36.00030 4.391035 26.94418 26.989762 45.01083
## 8 NP 850 Manhattan 44.20709 4.391035 26.94418 35.196554 53.21762
## 9 NP 579 Hays 37.44081 4.391035 26.94418 28.430276 46.45134
## .group location_f xloc
## 1 b Hays 1.7
## 2 b Tribune 1.7
## 3 a Manhattan 1.7
## 4 b Tribune 2
## 5 a Hays 2
## 6 a Manhattan 2
## 7 a Tribune 2.3
## 8 a Manhattan 2.3
## 9 a Hays 2.3x5wsa25015p<- merge(x5wsa25015p, df2_025, by=c("treatment"))
x5wsa25015p## treatment precip location lsmean SE df lower.CL upper.CL .group
## 1 AG 472 Tribune 19.59991 5.772062 27 7.756621 31.44321 a
## 2 AG 850 Manhattan 52.68674 5.772062 27 40.843442 64.53003 a
## 3 AG 579 Hays 32.00845 5.772062 27 20.165157 43.85174 a
## 4 EA 472 Tribune 32.71524 5.772062 27 20.871950 44.55854 a
## 5 EA 579 Hays 45.46467 5.772062 27 33.621372 57.30796 a
## 6 EA 850 Manhattan 36.01735 5.772062 27 24.174053 47.86064 a
## 7 NP 472 Tribune 18.03246 5.772062 27 6.189164 29.87575 a
## 8 NP 850 Manhattan 37.69254 5.772062 27 25.849249 49.53584 a
## 9 NP 579 Hays 32.09403 5.772062 27 20.250733 43.93732 a
## location_f xloc
## 1 Tribune 1.7
## 2 Manhattan 1.7
## 3 Hays 1.7
## 4 Tribune 2
## 5 Hays 2
## 6 Manhattan 2
## 7 Tribune 2.3
## 8 Manhattan 2.3
## 9 Hays 2.3#0.25-0.053 gets 2.7, 3, 3.3 for AG, EA, NP
df025_053 <- data.frame (treatment = c("AG", "EA", "NP"),
xloc = c("2.7", "3", "3.3"))
x20wsa53p<- merge(x20wsa53p, df025_053, by=c("treatment"))
x20wsa53p## treatment precip location lsmean SE df lower.CL upper.CL
## 1 AG 472 Tribune 53.07399 3.736594 22.78911 45.340296 60.80768
## 2 AG 850 Manhattan 61.16504 3.736594 22.78911 53.431345 68.89873
## 3 AG 579 Hays 69.79728 3.736594 22.78911 62.063591 77.53098
## 4 EA 472 Tribune 49.13078 3.736594 22.78911 41.397089 56.86447
## 5 EA 579 Hays 47.93665 3.736594 22.78911 40.202952 55.67034
## 6 EA 850 Manhattan 47.38140 3.736594 22.78911 39.647708 55.11509
## 7 NP 579 Hays 14.90930 3.736594 22.78911 7.175602 22.64299
## 8 NP 472 Tribune 22.29726 3.736594 22.78911 14.563572 30.03096
## 9 NP 850 Manhattan 16.56350 3.736594 22.78911 8.829805 24.29719
## .group location_f xloc
## 1 a Tribune 2.7
## 2 a Manhattan 2.7
## 3 a Hays 2.7
## 4 a Tribune 3
## 5 b Hays 3
## 6 b Manhattan 3
## 7 c Hays 3.3
## 8 b Tribune 3.3
## 9 c Manhattan 3.3x20wsa5310p<- merge(x20wsa5310p, df025_053, by=c("treatment"))
x20wsa5310p## treatment precip location lsmean SE df lower.CL upper.CL
## 1 AG 472 Tribune 40.25275 4.905302 20.96793 30.05067 50.45484
## 2 AG 850 Manhattan 60.48042 4.905302 20.96793 50.27834 70.68251
## 3 AG 579 Hays 61.04155 4.905302 20.96793 50.83947 71.24364
## 4 EA 472 Tribune 60.53863 4.905302 20.96793 50.33654 70.74071
## 5 EA 850 Manhattan 45.04338 4.905302 20.96793 34.84130 55.24547
## 6 EA 579 Hays 47.54742 4.905302 20.96793 37.34533 57.74950
## 7 NP 579 Hays 28.36159 4.905302 20.96793 18.15950 38.56367
## 8 NP 472 Tribune 24.33689 4.905302 20.96793 14.13481 34.53898
## 9 NP 850 Manhattan 23.59988 4.905302 20.96793 13.39779 33.80196
## .group location_f xloc
## 1 b Tribune 2.7
## 2 a Manhattan 2.7
## 3 a Hays 2.7
## 4 a Tribune 3
## 5 b Manhattan 3
## 6 b Hays 3
## 7 c Hays 3.3
## 8 c Tribune 3.3
## 9 c Manhattan 3.3x20wsa5315p<- merge(x20wsa5315p, df025_053, by=c("treatment"))
x20wsa5315p## treatment precip location lsmean SE df lower.CL upper.CL
## 1 AG 472 Tribune 43.85542 5.586198 26.3469 32.380181 55.33066
## 2 AG 850 Manhattan 54.04183 5.586198 26.3469 42.566587 65.51707
## 3 AG 579 Hays 44.03529 5.586198 26.3469 32.560046 55.51053
## 4 EA 472 Tribune 51.12957 5.586198 26.3469 39.654327 62.60481
## 5 EA 579 Hays 59.98533 5.586198 26.3469 48.510085 71.46056
## 6 EA 850 Manhattan 52.36527 5.586198 26.3469 40.890028 63.84051
## 7 NP 579 Hays 32.68928 5.586198 26.3469 21.214043 44.16452
## 8 NP 472 Tribune 20.87374 5.586198 26.3469 9.398503 32.34898
## 9 NP 850 Manhattan 19.45423 5.586198 26.3469 7.978991 30.92947
## .group location_f xloc
## 1 a Tribune 2.7
## 2 a Manhattan 2.7
## 3 b Hays 2.7
## 4 a Tribune 3
## 5 a Hays 3
## 6 a Manhattan 3
## 7 b Hays 3.3
## 8 b Tribune 3.3
## 9 b Manhattan 3.3x5wsa53p<- merge(x5wsa53p, df025_053, by=c("treatment"))
x5wsa53p## treatment precip location lsmean SE df lower.CL upper.CL
## 1 AG 472 Tribune 51.28463 4.308961 26.93583 42.442385 60.12687
## 2 AG 850 Manhattan 52.78271 4.308961 26.93583 43.940465 61.62495
## 3 AG 579 Hays 46.22015 4.308961 26.93583 37.377911 55.06240
## 4 EA 472 Tribune 35.12016 4.308961 26.93583 26.277920 43.96241
## 5 EA 579 Hays 39.81846 4.308961 26.93583 30.976213 48.66070
## 6 EA 850 Manhattan 30.85960 4.308961 26.93583 22.017359 39.70184
## 7 NP 579 Hays 18.92336 4.308961 26.93583 10.081112 27.76560
## 8 NP 472 Tribune 23.41428 4.308961 26.93583 14.572037 32.25652
## 9 NP 850 Manhattan 12.95212 4.308961 26.93583 4.109876 21.79436
## .group location_f xloc
## 1 a Tribune 2.7
## 2 a Manhattan 2.7
## 3 a Hays 2.7
## 4 b Tribune 3
## 5 a Hays 3
## 6 b Manhattan 3
## 7 b Hays 3.3
## 8 b Tribune 3.3
## 9 c Manhattan 3.3x5wsa5310p<- merge(x5wsa5310p, df025_053, by=c("treatment"))
x5wsa5310p## treatment precip location lsmean SE df lower.CL upper.CL
## 1 AG 472 Tribune 48.79037 4.646506 26.97369 39.256094 58.32465
## 2 AG 850 Manhattan 42.54411 4.646506 26.97369 33.009834 52.07839
## 3 AG 579 Hays 53.84427 4.646506 26.97369 44.309997 63.37855
## 4 EA 472 Tribune 56.26802 4.646506 26.97369 46.733745 65.80230
## 5 EA 850 Manhattan 23.87843 4.646506 26.97369 14.344149 33.41270
## 6 EA 579 Hays 52.73937 4.646506 26.97369 43.205095 62.27365
## 7 NP 579 Hays 26.00424 4.646506 26.97369 16.469966 35.53852
## 8 NP 472 Tribune 28.54305 4.646506 26.97369 19.008772 38.07733
## 9 NP 850 Manhattan 12.82837 4.646506 26.97369 3.294094 22.36265
## .group location_f xloc
## 1 a Tribune 2.7
## 2 a Manhattan 2.7
## 3 a Hays 2.7
## 4 a Tribune 3
## 5 b Manhattan 3
## 6 a Hays 3
## 7 b Hays 3.3
## 8 b Tribune 3.3
## 9 b Manhattan 3.3x5wsa5315p<- merge(x5wsa5315p, df025_053, by=c("treatment"))
x5wsa5315p## treatment precip location lsmean SE df lower.CL upper.CL .group
## 1 AG 472 Tribune 54.06194 5.790714 27 42.180374 65.94350 a
## 2 AG 850 Manhattan 33.09569 5.790714 27 21.214123 44.97725 a
## 3 AG 579 Hays 32.26746 5.790714 27 20.385893 44.14902 b
## 4 EA 472 Tribune 41.10064 5.790714 27 29.219080 52.98221 ab
## 5 EA 579 Hays 49.59674 5.790714 27 37.715174 61.47830 a
## 6 EA 850 Manhattan 29.54047 5.790714 27 17.658910 41.42204 a
## 7 NP 579 Hays 26.41757 5.790714 27 14.536007 38.29913 b
## 8 NP 472 Tribune 33.01473 5.790714 27 21.133171 44.89630 b
## 9 NP 850 Manhattan 20.06624 5.790714 27 8.184675 31.94780 a
## location_f xloc
## 1 Tribune 2.7
## 2 Manhattan 2.7
## 3 Hays 2.7
## 4 Tribune 3
## 5 Hays 3
## 6 Manhattan 3
## 7 Hays 3.3
## 8 Tribune 3.3
## 9 Manhattan 3.3#0.053-0.02 gets 3.7, 4, 4.3 for AG, EA, NP
df053_02 <- data.frame (treatment = c("AG", "EA", "NP"),
xloc = c("3.7", "4", "4.3"))
x20wsa20p<- merge(x20wsa20p, df053_02, by=c("treatment"))
x20wsa20p## treatment precip location lsmean SE df lower.CL upper.CL .group
## 1 AG 472 Tribune 6.1575 0.7752837 27 4.5667492 7.748251 a
## 2 AG 850 Manhattan 7.2450 0.7752837 27 5.6542492 8.835751 a
## 3 AG 579 Hays 5.2825 0.7752837 27 3.6917492 6.873251 a
## 4 EA 472 Tribune 3.9900 0.7752837 27 2.3992492 5.580751 ab
## 5 EA 579 Hays 3.3750 0.7752837 27 1.7842492 4.965751 a
## 6 EA 850 Manhattan 5.1450 0.7752837 27 3.5542492 6.735751 a
## 7 NP 579 Hays 1.0475 0.7752837 27 -0.5432508 2.638251 b
## 8 NP 472 Tribune 1.9500 0.7752837 27 0.3592492 3.540751 b
## 9 NP 850 Manhattan 1.9325 0.7752837 27 0.3417492 3.523251 b
## location_f xloc
## 1 Tribune 3.7
## 2 Manhattan 3.7
## 3 Hays 3.7
## 4 Tribune 4
## 5 Hays 4
## 6 Manhattan 4
## 7 Hays 4.3
## 8 Tribune 4.3
## 9 Manhattan 4.3x20wsa2010p<- merge(x20wsa2010p, df053_02, by=c("treatment"))
x20wsa2010p## treatment precip location lsmean SE df lower.CL upper.CL .group
## 1 AG 472 Tribune 4.1075 0.671795 27 2.7290905 5.48591 ab
## 2 AG 579 Hays 8.7775 0.671795 27 7.3990905 10.15591 a
## 3 AG 850 Manhattan 4.8125 0.671795 27 3.4340905 6.19091 ab
## 4 EA 472 Tribune 5.4100 0.671795 27 4.0315905 6.78841 a
## 5 EA 850 Manhattan 5.0475 0.671795 27 3.6690905 6.42591 a
## 6 EA 579 Hays 3.7775 0.671795 27 2.3990905 5.15591 b
## 7 NP 579 Hays 1.7575 0.671795 27 0.3790905 3.13591 c
## 8 NP 472 Tribune 2.1825 0.671795 27 0.8040905 3.56091 b
## 9 NP 850 Manhattan 3.0400 0.671795 27 1.6615905 4.41841 b
## location_f xloc
## 1 Tribune 3.7
## 2 Hays 3.7
## 3 Manhattan 3.7
## 4 Tribune 4
## 5 Manhattan 4
## 6 Hays 4
## 7 Hays 4.3
## 8 Tribune 4.3
## 9 Manhattan 4.3x20wsa2015p<- merge(x20wsa2015p, df053_02, by=c("treatment"))
x20wsa2015p## treatment precip location lsmean SE df lower.CL upper.CL
## 1 AG 472 Tribune 4.4125 1.094354 22.58634 2.1463605 6.678639
## 2 AG 579 Hays 7.8275 1.094354 22.58634 5.5613605 10.093639
## 3 AG 850 Manhattan 3.4700 1.094354 22.58634 1.2038605 5.736139
## 4 EA 472 Tribune 8.4225 1.094354 22.58634 6.1563605 10.688639
## 5 EA 850 Manhattan 6.9400 1.094354 22.58634 4.6738605 9.206139
## 6 EA 579 Hays 5.5625 1.094354 22.58634 3.2963605 7.828639
## 7 NP 579 Hays 2.4400 1.094354 22.58634 0.1738605 4.706139
## 8 NP 472 Tribune 1.6150 1.094354 22.58634 -0.6511395 3.881139
## 9 NP 850 Manhattan 1.7325 1.094354 22.58634 -0.5336395 3.998639
## .group location_f xloc
## 1 b Tribune 3.7
## 2 a Hays 3.7
## 3 b Manhattan 3.7
## 4 a Tribune 4
## 5 a Manhattan 4
## 6 a Hays 4
## 7 b Hays 4.3
## 8 b Tribune 4.3
## 9 b Manhattan 4.3x5wsa20p<- merge(x5wsa20p, df053_02, by=c("treatment"))
x5wsa20p## treatment precip location lsmean SE df lower.CL upper.CL
## 1 AG 472 Tribune 6.822500 2.423439 27 1.850013269 11.794987
## 2 AG 579 Hays 6.052500 2.423439 27 1.080013269 11.024987
## 3 AG 850 Manhattan 3.980000 2.423439 27 -0.992486731 8.952487
## 4 EA 579 Hays 16.817500 2.423439 27 11.845013269 21.789987
## 5 EA 472 Tribune 4.965000 2.423439 27 -0.007486731 9.937487
## 6 EA 850 Manhattan 3.775000 2.423439 27 -1.197486731 8.747487
## 7 NP 579 Hays 8.617500 2.423439 27 3.645013269 13.589987
## 8 NP 472 Tribune 5.255000 2.423439 27 0.282513269 10.227487
## 9 NP 850 Manhattan 1.433954 2.423439 27 -3.538532696 6.406441
## .group location_f xloc
## 1 a Tribune 3.7
## 2 b Hays 3.7
## 3 a Manhattan 3.7
## 4 a Hays 4
## 5 a Tribune 4
## 6 a Manhattan 4
## 7 b Hays 4.3
## 8 a Tribune 4.3
## 9 a Manhattan 4.3x5wsa2010p<- merge(x5wsa2010p, df053_02, by=c("treatment"))
x5wsa2010p## treatment precip location lsmean SE df lower.CL upper.CL .group
## 1 AG 472 Tribune 7.5800 0.9417107 27 5.6477693 9.512231 a
## 2 AG 579 Hays 5.6325 0.9417107 27 3.7002693 7.564731 b
## 3 AG 850 Manhattan 2.2525 0.9417107 27 0.3202693 4.184731 a
## 4 EA 850 Manhattan 4.2475 0.9417107 27 2.3152693 6.179731 a
## 5 EA 472 Tribune 6.5025 0.9417107 27 4.5702693 8.434731 a
## 6 EA 579 Hays 11.5525 0.9417107 27 9.6202693 13.484731 a
## 7 NP 579 Hays 9.0175 0.9417107 27 7.0852693 10.949731 a
## 8 NP 472 Tribune 4.8950 0.9417107 27 2.9627693 6.827231 a
## 9 NP 850 Manhattan 1.7150 0.9417107 27 -0.2172307 3.647231 a
## location_f xloc
## 1 Tribune 3.7
## 2 Hays 3.7
## 3 Manhattan 3.7
## 4 Manhattan 4
## 5 Tribune 4
## 6 Hays 4
## 7 Hays 4.3
## 8 Tribune 4.3
## 9 Manhattan 4.3x5wsa2015p<- merge(x5wsa2015p, df053_02, by=c("treatment"))
x5wsa2015p## treatment precip location lsmean SE df lower.CL upper.CL .group
## 1 AG 472 Tribune 5.5575 0.6737057 27 4.17517004 6.93983 a
## 2 AG 579 Hays 5.8525 0.6737057 27 4.47017004 7.23483 b
## 3 AG 850 Manhattan 3.0725 0.6737057 27 1.69017004 4.45483 ab
## 4 EA 472 Tribune 5.6750 0.6737057 27 4.29267004 7.05733 a
## 5 EA 850 Manhattan 4.2025 0.6737057 27 2.82017004 5.58483 a
## 6 EA 579 Hays 10.8700 0.6737057 27 9.48767004 12.25233 a
## 7 NP 579 Hays 8.9275 0.6737057 27 7.54517004 10.30983 a
## 8 NP 472 Tribune 5.0850 0.6737057 27 3.70267004 6.46733 a
## 9 NP 850 Manhattan 1.4100 0.6737057 27 0.02767004 2.79233 b
## location_f xloc
## 1 Tribune 3.7
## 2 Hays 3.7
## 3 Manhattan 3.7
## 4 Tribune 4
## 5 Manhattan 4
## 6 Hays 4
## 7 Hays 4.3
## 8 Tribune 4.3
## 9 Manhattan 4.37 Converted Dataframes
x20wsa2000vec <- rep(c("8-2"),9)
x20wsa250vec <- rep(c("2-0.25"),9)
x20wsa53vec <- rep(c("0.25-0.053"),9)
x20wsa20vec <- rep(c("0.053-0.020"),9)
x5wsa2000vec <- rep(c("8-2"),9)
x5wsa250vec <- rep(c("2-0.25"),9)
x5wsa53vec <- rep(c("0.25-0.053"),9)
x5wsa20vec <- rep(c("0.053-0.020"),9)
#20 minutes 0-5 cm
x20x20005 <- x20wsa2000p %>%
dplyr::select(precip, location, treatment, lsmean, .group, xloc) %>%
mutate(aggregate_size = x20wsa2000vec)
x20x2505 <- x20wsa250p %>%
dplyr::select(precip, location, treatment, lsmean, .group, xloc) %>%
mutate(aggregate_size = x20wsa250vec)
x20x535 <- x20wsa53p %>%
dplyr::select(precip, location, treatment, lsmean, .group, xloc) %>%
mutate(aggregate_size = x20wsa53vec)
x20x205 <- x20wsa20p %>%
dplyr::select(precip, location, treatment, lsmean, .group, xloc) %>%
mutate(aggregate_size = x20wsa20vec)
#rbind
x20minx5 <- rbind(x20x20005,x20x2505,x20x535,x20x205)
x20minx5## precip location treatment lsmean .group xloc aggregate_size
## 1 579 Hays AG 0.9315208 b .7 8-2
## 2 472 Tribune AG 8.7304187 b .7 8-2
## 3 850 Manhattan AG 1.9782694 b .7 8-2
## 4 472 Tribune EA 8.8448459 b 1 8-2
## 5 579 Hays EA 9.3305850 b 1 8-2
## 6 850 Manhattan EA 11.4886335 b 1 8-2
## 7 472 Tribune NP 26.3313434 a 1.3 8-2
## 8 850 Manhattan NP 25.3077401 a 1.3 8-2
## 9 579 Hays NP 30.8387700 a 1.3 8-2
## 10 579 Hays AG 11.9734301 b 1.7 2-0.25
## 11 472 Tribune AG 14.4454999 b 1.7 2-0.25
## 12 850 Manhattan AG 17.6278247 c 1.7 2-0.25
## 13 472 Tribune EA 16.2781993 b 2 2-0.25
## 14 579 Hays EA 22.0219300 a 2 2-0.25
## 15 850 Manhattan EA 24.9732871 b 2 2-0.25
## 16 472 Tribune NP 25.6052664 a 2.3 2-0.25
## 17 850 Manhattan NP 37.2452781 a 2.3 2-0.25
## 18 579 Hays NP 28.5391700 a 2.3 2-0.25
## 19 472 Tribune AG 53.0739889 a 2.7 0.25-0.053
## 20 850 Manhattan AG 61.1650379 a 2.7 0.25-0.053
## 21 579 Hays AG 69.7972833 a 2.7 0.25-0.053
## 22 472 Tribune EA 49.1307814 a 3 0.25-0.053
## 23 579 Hays EA 47.9366450 b 3 0.25-0.053
## 24 850 Manhattan EA 47.3814008 b 3 0.25-0.053
## 25 579 Hays NP 14.9092950 c 3.3 0.25-0.053
## 26 472 Tribune NP 22.2972642 b 3.3 0.25-0.053
## 27 850 Manhattan NP 16.5634973 c 3.3 0.25-0.053
## 28 472 Tribune AG 6.1575000 a 3.7 0.053-0.020
## 29 850 Manhattan AG 7.2450000 a 3.7 0.053-0.020
## 30 579 Hays AG 5.2825000 a 3.7 0.053-0.020
## 31 472 Tribune EA 3.9900000 ab 4 0.053-0.020
## 32 579 Hays EA 3.3750000 a 4 0.053-0.020
## 33 850 Manhattan EA 5.1450000 a 4 0.053-0.020
## 34 579 Hays NP 1.0475000 b 4.3 0.053-0.020
## 35 472 Tribune NP 1.9500000 b 4.3 0.053-0.020
## 36 850 Manhattan NP 1.9325000 b 4.3 0.053-0.020###########20 minutes 5-10 cm
x20x200010 <- x20wsa200010p %>%
dplyr::select(precip, location, treatment, lsmean, .group, xloc) %>%
mutate(aggregate_size = x20wsa2000vec)
x20x25010 <- x20wsa25010p %>%
dplyr::select(precip, location, treatment, lsmean, .group, xloc) %>%
mutate(aggregate_size = x20wsa250vec)
x20x5310 <- x20wsa5310p %>%
dplyr::select(precip, location, treatment, lsmean, .group, xloc) %>%
mutate(aggregate_size = x20wsa53vec)
x20x2010 <- x20wsa2010p %>%
dplyr::select(precip, location, treatment, lsmean, .group, xloc) %>%
mutate(aggregate_size = x20wsa20vec)
#rbind
x20minx10 <- rbind(x20x200010,x20x25010,x20x5310,x20x2010)
x20minx10## precip location treatment lsmean .group xloc aggregate_size
## 1 472 Tribune AG 7.158672 b .7 8-2
## 2 850 Manhattan AG 3.003322 b .7 8-2
## 3 579 Hays AG 1.369402 b .7 8-2
## 4 472 Tribune EA 2.303734 b 1 8-2
## 5 850 Manhattan EA 8.197339 b 1 8-2
## 6 579 Hays EA 4.312530 b 1 8-2
## 7 472 Tribune NP 19.874634 a 1.3 8-2
## 8 850 Manhattan NP 19.539639 a 1.3 8-2
## 9 579 Hays NP 27.933098 a 1.3 8-2
## 10 472 Tribune AG 31.380248 a 1.7 2-0.25
## 11 579 Hays AG 12.446052 b 1.7 2-0.25
## 12 850 Manhattan AG 19.009357 b 1.7 2-0.25
## 13 579 Hays EA 29.768317 a 2 2-0.25
## 14 472 Tribune EA 15.885406 b 2 2-0.25
## 15 850 Manhattan EA 31.988045 ab 2 2-0.25
## 16 472 Tribune NP 33.762260 a 2.3 2-0.25
## 17 850 Manhattan NP 35.211923 a 2.3 2-0.25
## 18 579 Hays NP 22.881412 ab 2.3 2-0.25
## 19 472 Tribune AG 40.252754 b 2.7 0.25-0.053
## 20 850 Manhattan AG 60.480425 a 2.7 0.25-0.053
## 21 579 Hays AG 61.041555 a 2.7 0.25-0.053
## 22 472 Tribune EA 60.538628 a 3 0.25-0.053
## 23 850 Manhattan EA 45.043383 b 3 0.25-0.053
## 24 579 Hays EA 47.547415 b 3 0.25-0.053
## 25 579 Hays NP 28.361588 c 3.3 0.25-0.053
## 26 472 Tribune NP 24.336891 c 3.3 0.25-0.053
## 27 850 Manhattan NP 23.599879 c 3.3 0.25-0.053
## 28 472 Tribune AG 4.107500 ab 3.7 0.053-0.020
## 29 579 Hays AG 8.777500 a 3.7 0.053-0.020
## 30 850 Manhattan AG 4.812500 ab 3.7 0.053-0.020
## 31 472 Tribune EA 5.410000 a 4 0.053-0.020
## 32 850 Manhattan EA 5.047500 a 4 0.053-0.020
## 33 579 Hays EA 3.777500 b 4 0.053-0.020
## 34 579 Hays NP 1.757500 c 4.3 0.053-0.020
## 35 472 Tribune NP 2.182500 b 4.3 0.053-0.020
## 36 850 Manhattan NP 3.040000 b 4.3 0.053-0.020##############20 minutes 10-15 cm
x20x200015 <- x20wsa200015p %>%
dplyr::select(precip, location, treatment, lsmean, .group, xloc) %>%
mutate(aggregate_size = x20wsa2000vec)
x20x25015 <- x20wsa25015p %>%
dplyr::select(precip, location, treatment, lsmean, .group, xloc) %>%
mutate(aggregate_size = x20wsa250vec)
x20x5315 <- x20wsa5315p %>%
dplyr::select(precip, location, treatment, lsmean, .group, xloc) %>%
mutate(aggregate_size = x20wsa53vec)
x20x2015 <- x20wsa2015p %>%
dplyr::select(precip, location, treatment, lsmean, .group, xloc) %>%
mutate(aggregate_size = x20wsa20vec)
#rbind
x20minx15 <- rbind(x20x200015,x20x25015,x20x5315,x20x2015)
x20minx15## precip location treatment lsmean .group xloc aggregate_size
## 1 472 Tribune AG 7.344079 b .7 8-2
## 2 850 Manhattan AG 2.653159 b .7 8-2
## 3 579 Hays AG 1.931631 b .7 8-2
## 4 472 Tribune EA 3.058975 b 1 8-2
## 5 850 Manhattan EA 4.378598 b 1 8-2
## 6 579 Hays EA 2.561610 b 1 8-2
## 7 472 Tribune NP 26.297002 a 1.3 8-2
## 8 850 Manhattan NP 25.368150 a 1.3 8-2
## 9 579 Hays NP 23.871558 a 1.3 8-2
## 10 472 Tribune AG 27.333662 ab 1.7 2-0.25
## 11 579 Hays AG 32.940850 a 1.7 2-0.25
## 12 850 Manhattan AG 29.494218 a 1.7 2-0.25
## 13 579 Hays EA 18.866673 a 2 2-0.25
## 14 472 Tribune EA 15.882277 b 2 2-0.25
## 15 850 Manhattan EA 25.795000 a 2 2-0.25
## 16 472 Tribune NP 31.521145 a 2.3 2-0.25
## 17 850 Manhattan NP 37.563085 a 2.3 2-0.25
## 18 579 Hays NP 23.263343 a 2.3 2-0.25
## 19 472 Tribune AG 43.855421 a 2.7 0.25-0.053
## 20 850 Manhattan AG 54.041827 a 2.7 0.25-0.053
## 21 579 Hays AG 44.035286 b 2.7 0.25-0.053
## 22 472 Tribune EA 51.129566 a 3 0.25-0.053
## 23 579 Hays EA 59.985325 a 3 0.25-0.053
## 24 850 Manhattan EA 52.365267 a 3 0.25-0.053
## 25 579 Hays NP 32.689282 b 3.3 0.25-0.053
## 26 472 Tribune NP 20.873743 b 3.3 0.25-0.053
## 27 850 Manhattan NP 19.454231 b 3.3 0.25-0.053
## 28 472 Tribune AG 4.412500 b 3.7 0.053-0.020
## 29 579 Hays AG 7.827500 a 3.7 0.053-0.020
## 30 850 Manhattan AG 3.470000 b 3.7 0.053-0.020
## 31 472 Tribune EA 8.422500 a 4 0.053-0.020
## 32 850 Manhattan EA 6.940000 a 4 0.053-0.020
## 33 579 Hays EA 5.562500 a 4 0.053-0.020
## 34 579 Hays NP 2.440000 b 4.3 0.053-0.020
## 35 472 Tribune NP 1.615000 b 4.3 0.053-0.020
## 36 850 Manhattan NP 1.732500 b 4.3 0.053-0.020##########
#5 minutes 0-5 cm
##########
x5x20005 <- x5wsa2000p %>%
dplyr::select(precip, location, treatment, lsmean, .group, xloc) %>%
mutate(aggregate_size = x5wsa2000vec)
x5x2505 <- x5wsa250p %>%
dplyr::select(precip, location, treatment, lsmean, .group, xloc) %>%
mutate(aggregate_size = x5wsa250vec)
x5x535 <- x5wsa53p %>%
dplyr::select(precip, location, treatment, lsmean, .group, xloc) %>%
mutate(aggregate_size = x5wsa53vec)
x5x205 <- x5wsa20p %>%
dplyr::select(precip, location, treatment, lsmean, .group, xloc) %>%
mutate(aggregate_size = x5wsa20vec)
#rbind
x5minx5 <- rbind(x5x20005,x5x2505,x5x535,x5x205)
x5minx5## precip location treatment lsmean .group xloc aggregate_size
## 1 579 Hays AG 1.563937 c .7 8-2
## 2 472 Tribune AG 6.619284 a .7 8-2
## 3 850 Manhattan AG 2.857780 c .7 8-2
## 4 472 Tribune EA 10.186894 a 1 8-2
## 5 850 Manhattan EA 14.241278 b 1 8-2
## 6 579 Hays EA 25.901540 b 1 8-2
## 7 472 Tribune NP 8.822787 a 1.3 8-2
## 8 850 Manhattan NP 25.434619 a 1.3 8-2
## 9 579 Hays NP 44.065476 a 1.3 8-2
## 10 579 Hays AG 27.649027 a 1.7 2-0.25
## 11 472 Tribune AG 9.931781 b 1.7 2-0.25
## 12 850 Manhattan AG 28.049438 b 1.7 2-0.25
## 13 472 Tribune EA 29.018520 a 2 2-0.25
## 14 579 Hays EA 26.595305 a 2 2-0.25
## 15 850 Manhattan EA 31.323713 b 2 2-0.25
## 16 850 Manhattan NP 44.262281 a 2.3 2-0.25
## 17 472 Tribune NP 27.005202 a 2.3 2-0.25
## 18 579 Hays NP 32.570016 a 2.3 2-0.25
## 19 472 Tribune AG 51.284628 a 2.7 0.25-0.053
## 20 850 Manhattan AG 52.782708 a 2.7 0.25-0.053
## 21 579 Hays AG 46.220153 a 2.7 0.25-0.053
## 22 472 Tribune EA 35.120163 b 3 0.25-0.053
## 23 579 Hays EA 39.818455 a 3 0.25-0.053
## 24 850 Manhattan EA 30.859602 b 3 0.25-0.053
## 25 579 Hays NP 18.923355 b 3.3 0.25-0.053
## 26 472 Tribune NP 23.414279 b 3.3 0.25-0.053
## 27 850 Manhattan NP 12.952119 c 3.3 0.25-0.053
## 28 472 Tribune AG 6.822500 a 3.7 0.053-0.020
## 29 579 Hays AG 6.052500 b 3.7 0.053-0.020
## 30 850 Manhattan AG 3.980000 a 3.7 0.053-0.020
## 31 579 Hays EA 16.817500 a 4 0.053-0.020
## 32 472 Tribune EA 4.965000 a 4 0.053-0.020
## 33 850 Manhattan EA 3.775000 a 4 0.053-0.020
## 34 579 Hays NP 8.617500 b 4.3 0.053-0.020
## 35 472 Tribune NP 5.255000 a 4.3 0.053-0.020
## 36 850 Manhattan NP 1.433954 a 4.3 0.053-0.020################ 5 minutes 5-10 cm
x5x200010 <- x5wsa200010p %>%
dplyr::select(precip, location, treatment, lsmean, .group, xloc) %>%
mutate(aggregate_size = x5wsa2000vec)
x5x25010 <- x5wsa25010p %>%
dplyr::select(precip, location, treatment, lsmean, .group, xloc) %>%
mutate(aggregate_size = x5wsa250vec)
x5x5310 <- x5wsa5310p %>%
dplyr::select(precip, location, treatment, lsmean, .group, xloc) %>%
mutate(aggregate_size = x5wsa53vec)
x5x2010 <- x5wsa2010p %>%
dplyr::select(precip, location, treatment, lsmean, .group, xloc) %>%
mutate(aggregate_size = x5wsa20vec)
#rbind
x5minx10 <- rbind(x5x200010,x5x25010,x5x5310,x5x2010)
x5minx10## precip location treatment lsmean .group xloc aggregate_size
## 1 472 Tribune AG 7.358129 a .7 8-2
## 2 850 Manhattan AG 4.704605 c .7 8-2
## 3 579 Hays AG 3.551578 c .7 8-2
## 4 472 Tribune EA 3.989024 a 1 8-2
## 5 850 Manhattan EA 18.601440 b 1 8-2
## 6 579 Hays EA 10.999532 b 1 8-2
## 7 472 Tribune NP 7.784108 a 1.3 8-2
## 8 850 Manhattan NP 27.719093 a 1.3 8-2
## 9 579 Hays NP 47.950775 a 1.3 8-2
## 10 579 Hays AG 16.110140 b 1.7 2-0.25
## 11 472 Tribune AG 15.926345 b 1.7 2-0.25
## 12 850 Manhattan AG 41.277747 a 1.7 2-0.25
## 13 472 Tribune EA 17.127007 b 2 2-0.25
## 14 579 Hays EA 38.088665 a 2 2-0.25
## 15 850 Manhattan EA 37.566067 a 2 2-0.25
## 16 472 Tribune NP 36.000295 a 2.3 2-0.25
## 17 850 Manhattan NP 44.207087 a 2.3 2-0.25
## 18 579 Hays NP 37.440809 a 2.3 2-0.25
## 19 472 Tribune AG 48.790371 a 2.7 0.25-0.053
## 20 850 Manhattan AG 42.544111 a 2.7 0.25-0.053
## 21 579 Hays AG 53.844274 a 2.7 0.25-0.053
## 22 472 Tribune EA 56.268022 a 3 0.25-0.053
## 23 850 Manhattan EA 23.878426 b 3 0.25-0.053
## 24 579 Hays EA 52.739372 a 3 0.25-0.053
## 25 579 Hays NP 26.004243 b 3.3 0.25-0.053
## 26 472 Tribune NP 28.543049 b 3.3 0.25-0.053
## 27 850 Manhattan NP 12.828371 b 3.3 0.25-0.053
## 28 472 Tribune AG 7.580000 a 3.7 0.053-0.020
## 29 579 Hays AG 5.632500 b 3.7 0.053-0.020
## 30 850 Manhattan AG 2.252500 a 3.7 0.053-0.020
## 31 850 Manhattan EA 4.247500 a 4 0.053-0.020
## 32 472 Tribune EA 6.502500 a 4 0.053-0.020
## 33 579 Hays EA 11.552500 a 4 0.053-0.020
## 34 579 Hays NP 9.017500 a 4.3 0.053-0.020
## 35 472 Tribune NP 4.895000 a 4.3 0.053-0.020
## 36 850 Manhattan NP 1.715000 a 4.3 0.053-0.020################ 5 minutes 10-15 cm
x5x200015 <- x5wsa200015p %>%
dplyr::select(precip, location, treatment, lsmean, .group, xloc) %>%
mutate(aggregate_size = x5wsa2000vec)
x5x25015 <- x5wsa25015p %>%
dplyr::select(precip, location, treatment, lsmean, .group, xloc) %>%
mutate(aggregate_size = x5wsa250vec)
x5x5315 <- x5wsa5315p %>%
dplyr::select(precip, location, treatment, lsmean, .group, xloc) %>%
mutate(aggregate_size = x5wsa53vec)
x5x2015 <- x5wsa2015p %>%
dplyr::select(precip, location, treatment, lsmean, .group, xloc) %>%
mutate(aggregate_size = x5wsa20vec)
#rbind
x5minx15 <- rbind(x5x200015,x5x25015,x5x5315,x5x2015)
x5minx15## precip location treatment lsmean .group xloc aggregate_size
## 1 472 Tribune AG 6.606750 a .7 8-2
## 2 579 Hays AG 11.637256 b .7 8-2
## 3 850 Manhattan AG 4.467970 b .7 8-2
## 4 579 Hays EA 7.687615 b 1 8-2
## 5 472 Tribune EA 6.572290 a 1 8-2
## 6 850 Manhattan EA 15.118422 ab 1 8-2
## 7 472 Tribune NP 14.583834 a 1.3 8-2
## 8 850 Manhattan NP 26.750084 a 1.3 8-2
## 9 579 Hays NP 40.495560 a 1.3 8-2
## 10 472 Tribune AG 19.599914 a 1.7 2-0.25
## 11 850 Manhattan AG 52.686735 a 1.7 2-0.25
## 12 579 Hays AG 32.008450 a 1.7 2-0.25
## 13 472 Tribune EA 32.715244 a 2 2-0.25
## 14 579 Hays EA 45.464665 a 2 2-0.25
## 15 850 Manhattan EA 36.017346 a 2 2-0.25
## 16 472 Tribune NP 18.032457 a 2.3 2-0.25
## 17 850 Manhattan NP 37.692543 a 2.3 2-0.25
## 18 579 Hays NP 32.094026 a 2.3 2-0.25
## 19 472 Tribune AG 54.061937 a 2.7 0.25-0.053
## 20 850 Manhattan AG 33.095686 a 2.7 0.25-0.053
## 21 579 Hays AG 32.267456 b 2.7 0.25-0.053
## 22 472 Tribune EA 41.100643 ab 3 0.25-0.053
## 23 579 Hays EA 49.596737 a 3 0.25-0.053
## 24 850 Manhattan EA 29.540473 a 3 0.25-0.053
## 25 579 Hays NP 26.417570 b 3.3 0.25-0.053
## 26 472 Tribune NP 33.014734 b 3.3 0.25-0.053
## 27 850 Manhattan NP 20.066238 a 3.3 0.25-0.053
## 28 472 Tribune AG 5.557500 a 3.7 0.053-0.020
## 29 579 Hays AG 5.852500 b 3.7 0.053-0.020
## 30 850 Manhattan AG 3.072500 ab 3.7 0.053-0.020
## 31 472 Tribune EA 5.675000 a 4 0.053-0.020
## 32 850 Manhattan EA 4.202500 a 4 0.053-0.020
## 33 579 Hays EA 10.870000 a 4 0.053-0.020
## 34 579 Hays NP 8.927500 a 4.3 0.053-0.020
## 35 472 Tribune NP 5.085000 a 4.3 0.053-0.020
## 36 850 Manhattan NP 1.410000 b 4.3 0.053-0.020############## NAGG
naggp## precip location treatment lsmean SE df lower.CL upper.CL
## 1 472 Tribune NP 63.965361 3.395653 25.35995 56.976913 70.953809
## 2 472 Tribune EA 18.059249 3.395653 25.35995 11.070801 25.047697
## 3 472 Tribune AG 8.551010 3.395653 25.35995 1.562563 15.539458
## 4 579 Hays NP 79.341536 3.395653 25.35995 72.353089 86.329984
## 5 579 Hays EA 33.661765 3.395653 25.35995 26.673317 40.650213
## 6 579 Hays AG 8.396014 3.395653 25.35995 1.407567 15.384462
## 7 850 Manhattan NP 71.105925 3.395653 25.35995 64.117478 78.094373
## 8 850 Manhattan EA 45.922074 3.395653 25.35995 38.933627 52.910522
## 9 850 Manhattan AG 1.474729 3.972346 25.86318 -6.692648 9.642106
## .group location_f
## 1 a Tribune
## 2 b Tribune
## 3 b Tribune
## 4 a Hays
## 5 b Hays
## 6 c Hays
## 7 a Manhattan
## 8 b Manhattan
## 9 c Manhattannagg10p## precip location treatment lsmean SE df lower.CL upper.CL .group
## 1 472 Tribune NP 35.748582 2.917510 26 29.7515545 41.745610 a
## 2 472 Tribune AG 5.721995 2.917510 26 -0.2750325 11.719023 b
## 3 472 Tribune EA 3.686833 2.917510 26 -2.3101946 9.683861 b
## 4 579 Hays NP 67.060386 2.917510 26 61.0633580 73.057413 a
## 5 579 Hays EA 7.599869 2.917510 26 1.6028410 13.596896 b
## 6 579 Hays AG 6.400527 2.917510 26 0.4034990 12.397554 b
## 7 850 Manhattan NP 61.784932 2.917510 26 55.7879043 67.781959 a
## 8 850 Manhattan EA 32.138297 2.917510 26 26.1412695 38.135325 b
## 9 850 Manhattan AG 4.820744 3.452044 26 -2.2750349 11.916522 c
## location_f
## 1 Tribune
## 2 Tribune
## 3 Tribune
## 4 Hays
## 5 Hays
## 6 Hays
## 7 Manhattan
## 8 Manhattan
## 9 Manhattannagg15p## precip location treatment lsmean SE df lower.CL upper.CL
## 1 472 Tribune NP 19.990638 3.794838 26.96694 12.2038258 27.77745
## 2 472 Tribune EA 4.310915 3.794838 26.96694 -3.4758968 12.09773
## 3 472 Tribune AG 4.156583 3.794838 26.96694 -3.6302288 11.94339
## 4 579 Hays NP 51.534489 3.794838 26.96694 43.7476771 59.32130
## 5 579 Hays AG 17.442633 3.794838 26.96694 9.6558211 25.22944
## 6 579 Hays EA 7.009381 3.794838 26.96694 -0.7774306 14.79619
## 7 850 Manhattan NP 54.878590 3.794838 26.96694 47.0917776 62.66540
## 8 850 Manhattan EA 20.871680 3.794838 26.96694 13.0848680 28.65849
## 9 850 Manhattan AG 9.891704 3.794838 26.96694 2.1048916 17.67852
## .group location_f
## 1 a Tribune
## 2 b Tribune
## 3 b Tribune
## 4 a Hays
## 5 b Hays
## 6 b Hays
## 7 a Manhattan
## 8 b Manhattan
## 9 b Manhattan#Final dataframes
x20minx5## precip location treatment lsmean .group xloc aggregate_size
## 1 579 Hays AG 0.9315208 b .7 8-2
## 2 472 Tribune AG 8.7304187 b .7 8-2
## 3 850 Manhattan AG 1.9782694 b .7 8-2
## 4 472 Tribune EA 8.8448459 b 1 8-2
## 5 579 Hays EA 9.3305850 b 1 8-2
## 6 850 Manhattan EA 11.4886335 b 1 8-2
## 7 472 Tribune NP 26.3313434 a 1.3 8-2
## 8 850 Manhattan NP 25.3077401 a 1.3 8-2
## 9 579 Hays NP 30.8387700 a 1.3 8-2
## 10 579 Hays AG 11.9734301 b 1.7 2-0.25
## 11 472 Tribune AG 14.4454999 b 1.7 2-0.25
## 12 850 Manhattan AG 17.6278247 c 1.7 2-0.25
## 13 472 Tribune EA 16.2781993 b 2 2-0.25
## 14 579 Hays EA 22.0219300 a 2 2-0.25
## 15 850 Manhattan EA 24.9732871 b 2 2-0.25
## 16 472 Tribune NP 25.6052664 a 2.3 2-0.25
## 17 850 Manhattan NP 37.2452781 a 2.3 2-0.25
## 18 579 Hays NP 28.5391700 a 2.3 2-0.25
## 19 472 Tribune AG 53.0739889 a 2.7 0.25-0.053
## 20 850 Manhattan AG 61.1650379 a 2.7 0.25-0.053
## 21 579 Hays AG 69.7972833 a 2.7 0.25-0.053
## 22 472 Tribune EA 49.1307814 a 3 0.25-0.053
## 23 579 Hays EA 47.9366450 b 3 0.25-0.053
## 24 850 Manhattan EA 47.3814008 b 3 0.25-0.053
## 25 579 Hays NP 14.9092950 c 3.3 0.25-0.053
## 26 472 Tribune NP 22.2972642 b 3.3 0.25-0.053
## 27 850 Manhattan NP 16.5634973 c 3.3 0.25-0.053
## 28 472 Tribune AG 6.1575000 a 3.7 0.053-0.020
## 29 850 Manhattan AG 7.2450000 a 3.7 0.053-0.020
## 30 579 Hays AG 5.2825000 a 3.7 0.053-0.020
## 31 472 Tribune EA 3.9900000 ab 4 0.053-0.020
## 32 579 Hays EA 3.3750000 a 4 0.053-0.020
## 33 850 Manhattan EA 5.1450000 a 4 0.053-0.020
## 34 579 Hays NP 1.0475000 b 4.3 0.053-0.020
## 35 472 Tribune NP 1.9500000 b 4.3 0.053-0.020
## 36 850 Manhattan NP 1.9325000 b 4.3 0.053-0.020x20minx10## precip location treatment lsmean .group xloc aggregate_size
## 1 472 Tribune AG 7.158672 b .7 8-2
## 2 850 Manhattan AG 3.003322 b .7 8-2
## 3 579 Hays AG 1.369402 b .7 8-2
## 4 472 Tribune EA 2.303734 b 1 8-2
## 5 850 Manhattan EA 8.197339 b 1 8-2
## 6 579 Hays EA 4.312530 b 1 8-2
## 7 472 Tribune NP 19.874634 a 1.3 8-2
## 8 850 Manhattan NP 19.539639 a 1.3 8-2
## 9 579 Hays NP 27.933098 a 1.3 8-2
## 10 472 Tribune AG 31.380248 a 1.7 2-0.25
## 11 579 Hays AG 12.446052 b 1.7 2-0.25
## 12 850 Manhattan AG 19.009357 b 1.7 2-0.25
## 13 579 Hays EA 29.768317 a 2 2-0.25
## 14 472 Tribune EA 15.885406 b 2 2-0.25
## 15 850 Manhattan EA 31.988045 ab 2 2-0.25
## 16 472 Tribune NP 33.762260 a 2.3 2-0.25
## 17 850 Manhattan NP 35.211923 a 2.3 2-0.25
## 18 579 Hays NP 22.881412 ab 2.3 2-0.25
## 19 472 Tribune AG 40.252754 b 2.7 0.25-0.053
## 20 850 Manhattan AG 60.480425 a 2.7 0.25-0.053
## 21 579 Hays AG 61.041555 a 2.7 0.25-0.053
## 22 472 Tribune EA 60.538628 a 3 0.25-0.053
## 23 850 Manhattan EA 45.043383 b 3 0.25-0.053
## 24 579 Hays EA 47.547415 b 3 0.25-0.053
## 25 579 Hays NP 28.361588 c 3.3 0.25-0.053
## 26 472 Tribune NP 24.336891 c 3.3 0.25-0.053
## 27 850 Manhattan NP 23.599879 c 3.3 0.25-0.053
## 28 472 Tribune AG 4.107500 ab 3.7 0.053-0.020
## 29 579 Hays AG 8.777500 a 3.7 0.053-0.020
## 30 850 Manhattan AG 4.812500 ab 3.7 0.053-0.020
## 31 472 Tribune EA 5.410000 a 4 0.053-0.020
## 32 850 Manhattan EA 5.047500 a 4 0.053-0.020
## 33 579 Hays EA 3.777500 b 4 0.053-0.020
## 34 579 Hays NP 1.757500 c 4.3 0.053-0.020
## 35 472 Tribune NP 2.182500 b 4.3 0.053-0.020
## 36 850 Manhattan NP 3.040000 b 4.3 0.053-0.020x20minx15## precip location treatment lsmean .group xloc aggregate_size
## 1 472 Tribune AG 7.344079 b .7 8-2
## 2 850 Manhattan AG 2.653159 b .7 8-2
## 3 579 Hays AG 1.931631 b .7 8-2
## 4 472 Tribune EA 3.058975 b 1 8-2
## 5 850 Manhattan EA 4.378598 b 1 8-2
## 6 579 Hays EA 2.561610 b 1 8-2
## 7 472 Tribune NP 26.297002 a 1.3 8-2
## 8 850 Manhattan NP 25.368150 a 1.3 8-2
## 9 579 Hays NP 23.871558 a 1.3 8-2
## 10 472 Tribune AG 27.333662 ab 1.7 2-0.25
## 11 579 Hays AG 32.940850 a 1.7 2-0.25
## 12 850 Manhattan AG 29.494218 a 1.7 2-0.25
## 13 579 Hays EA 18.866673 a 2 2-0.25
## 14 472 Tribune EA 15.882277 b 2 2-0.25
## 15 850 Manhattan EA 25.795000 a 2 2-0.25
## 16 472 Tribune NP 31.521145 a 2.3 2-0.25
## 17 850 Manhattan NP 37.563085 a 2.3 2-0.25
## 18 579 Hays NP 23.263343 a 2.3 2-0.25
## 19 472 Tribune AG 43.855421 a 2.7 0.25-0.053
## 20 850 Manhattan AG 54.041827 a 2.7 0.25-0.053
## 21 579 Hays AG 44.035286 b 2.7 0.25-0.053
## 22 472 Tribune EA 51.129566 a 3 0.25-0.053
## 23 579 Hays EA 59.985325 a 3 0.25-0.053
## 24 850 Manhattan EA 52.365267 a 3 0.25-0.053
## 25 579 Hays NP 32.689282 b 3.3 0.25-0.053
## 26 472 Tribune NP 20.873743 b 3.3 0.25-0.053
## 27 850 Manhattan NP 19.454231 b 3.3 0.25-0.053
## 28 472 Tribune AG 4.412500 b 3.7 0.053-0.020
## 29 579 Hays AG 7.827500 a 3.7 0.053-0.020
## 30 850 Manhattan AG 3.470000 b 3.7 0.053-0.020
## 31 472 Tribune EA 8.422500 a 4 0.053-0.020
## 32 850 Manhattan EA 6.940000 a 4 0.053-0.020
## 33 579 Hays EA 5.562500 a 4 0.053-0.020
## 34 579 Hays NP 2.440000 b 4.3 0.053-0.020
## 35 472 Tribune NP 1.615000 b 4.3 0.053-0.020
## 36 850 Manhattan NP 1.732500 b 4.3 0.053-0.020x5minx5## precip location treatment lsmean .group xloc aggregate_size
## 1 579 Hays AG 1.563937 c .7 8-2
## 2 472 Tribune AG 6.619284 a .7 8-2
## 3 850 Manhattan AG 2.857780 c .7 8-2
## 4 472 Tribune EA 10.186894 a 1 8-2
## 5 850 Manhattan EA 14.241278 b 1 8-2
## 6 579 Hays EA 25.901540 b 1 8-2
## 7 472 Tribune NP 8.822787 a 1.3 8-2
## 8 850 Manhattan NP 25.434619 a 1.3 8-2
## 9 579 Hays NP 44.065476 a 1.3 8-2
## 10 579 Hays AG 27.649027 a 1.7 2-0.25
## 11 472 Tribune AG 9.931781 b 1.7 2-0.25
## 12 850 Manhattan AG 28.049438 b 1.7 2-0.25
## 13 472 Tribune EA 29.018520 a 2 2-0.25
## 14 579 Hays EA 26.595305 a 2 2-0.25
## 15 850 Manhattan EA 31.323713 b 2 2-0.25
## 16 850 Manhattan NP 44.262281 a 2.3 2-0.25
## 17 472 Tribune NP 27.005202 a 2.3 2-0.25
## 18 579 Hays NP 32.570016 a 2.3 2-0.25
## 19 472 Tribune AG 51.284628 a 2.7 0.25-0.053
## 20 850 Manhattan AG 52.782708 a 2.7 0.25-0.053
## 21 579 Hays AG 46.220153 a 2.7 0.25-0.053
## 22 472 Tribune EA 35.120163 b 3 0.25-0.053
## 23 579 Hays EA 39.818455 a 3 0.25-0.053
## 24 850 Manhattan EA 30.859602 b 3 0.25-0.053
## 25 579 Hays NP 18.923355 b 3.3 0.25-0.053
## 26 472 Tribune NP 23.414279 b 3.3 0.25-0.053
## 27 850 Manhattan NP 12.952119 c 3.3 0.25-0.053
## 28 472 Tribune AG 6.822500 a 3.7 0.053-0.020
## 29 579 Hays AG 6.052500 b 3.7 0.053-0.020
## 30 850 Manhattan AG 3.980000 a 3.7 0.053-0.020
## 31 579 Hays EA 16.817500 a 4 0.053-0.020
## 32 472 Tribune EA 4.965000 a 4 0.053-0.020
## 33 850 Manhattan EA 3.775000 a 4 0.053-0.020
## 34 579 Hays NP 8.617500 b 4.3 0.053-0.020
## 35 472 Tribune NP 5.255000 a 4.3 0.053-0.020
## 36 850 Manhattan NP 1.433954 a 4.3 0.053-0.020x5minx10## precip location treatment lsmean .group xloc aggregate_size
## 1 472 Tribune AG 7.358129 a .7 8-2
## 2 850 Manhattan AG 4.704605 c .7 8-2
## 3 579 Hays AG 3.551578 c .7 8-2
## 4 472 Tribune EA 3.989024 a 1 8-2
## 5 850 Manhattan EA 18.601440 b 1 8-2
## 6 579 Hays EA 10.999532 b 1 8-2
## 7 472 Tribune NP 7.784108 a 1.3 8-2
## 8 850 Manhattan NP 27.719093 a 1.3 8-2
## 9 579 Hays NP 47.950775 a 1.3 8-2
## 10 579 Hays AG 16.110140 b 1.7 2-0.25
## 11 472 Tribune AG 15.926345 b 1.7 2-0.25
## 12 850 Manhattan AG 41.277747 a 1.7 2-0.25
## 13 472 Tribune EA 17.127007 b 2 2-0.25
## 14 579 Hays EA 38.088665 a 2 2-0.25
## 15 850 Manhattan EA 37.566067 a 2 2-0.25
## 16 472 Tribune NP 36.000295 a 2.3 2-0.25
## 17 850 Manhattan NP 44.207087 a 2.3 2-0.25
## 18 579 Hays NP 37.440809 a 2.3 2-0.25
## 19 472 Tribune AG 48.790371 a 2.7 0.25-0.053
## 20 850 Manhattan AG 42.544111 a 2.7 0.25-0.053
## 21 579 Hays AG 53.844274 a 2.7 0.25-0.053
## 22 472 Tribune EA 56.268022 a 3 0.25-0.053
## 23 850 Manhattan EA 23.878426 b 3 0.25-0.053
## 24 579 Hays EA 52.739372 a 3 0.25-0.053
## 25 579 Hays NP 26.004243 b 3.3 0.25-0.053
## 26 472 Tribune NP 28.543049 b 3.3 0.25-0.053
## 27 850 Manhattan NP 12.828371 b 3.3 0.25-0.053
## 28 472 Tribune AG 7.580000 a 3.7 0.053-0.020
## 29 579 Hays AG 5.632500 b 3.7 0.053-0.020
## 30 850 Manhattan AG 2.252500 a 3.7 0.053-0.020
## 31 850 Manhattan EA 4.247500 a 4 0.053-0.020
## 32 472 Tribune EA 6.502500 a 4 0.053-0.020
## 33 579 Hays EA 11.552500 a 4 0.053-0.020
## 34 579 Hays NP 9.017500 a 4.3 0.053-0.020
## 35 472 Tribune NP 4.895000 a 4.3 0.053-0.020
## 36 850 Manhattan NP 1.715000 a 4.3 0.053-0.020x5minx15## precip location treatment lsmean .group xloc aggregate_size
## 1 472 Tribune AG 6.606750 a .7 8-2
## 2 579 Hays AG 11.637256 b .7 8-2
## 3 850 Manhattan AG 4.467970 b .7 8-2
## 4 579 Hays EA 7.687615 b 1 8-2
## 5 472 Tribune EA 6.572290 a 1 8-2
## 6 850 Manhattan EA 15.118422 ab 1 8-2
## 7 472 Tribune NP 14.583834 a 1.3 8-2
## 8 850 Manhattan NP 26.750084 a 1.3 8-2
## 9 579 Hays NP 40.495560 a 1.3 8-2
## 10 472 Tribune AG 19.599914 a 1.7 2-0.25
## 11 850 Manhattan AG 52.686735 a 1.7 2-0.25
## 12 579 Hays AG 32.008450 a 1.7 2-0.25
## 13 472 Tribune EA 32.715244 a 2 2-0.25
## 14 579 Hays EA 45.464665 a 2 2-0.25
## 15 850 Manhattan EA 36.017346 a 2 2-0.25
## 16 472 Tribune NP 18.032457 a 2.3 2-0.25
## 17 850 Manhattan NP 37.692543 a 2.3 2-0.25
## 18 579 Hays NP 32.094026 a 2.3 2-0.25
## 19 472 Tribune AG 54.061937 a 2.7 0.25-0.053
## 20 850 Manhattan AG 33.095686 a 2.7 0.25-0.053
## 21 579 Hays AG 32.267456 b 2.7 0.25-0.053
## 22 472 Tribune EA 41.100643 ab 3 0.25-0.053
## 23 579 Hays EA 49.596737 a 3 0.25-0.053
## 24 850 Manhattan EA 29.540473 a 3 0.25-0.053
## 25 579 Hays NP 26.417570 b 3.3 0.25-0.053
## 26 472 Tribune NP 33.014734 b 3.3 0.25-0.053
## 27 850 Manhattan NP 20.066238 a 3.3 0.25-0.053
## 28 472 Tribune AG 5.557500 a 3.7 0.053-0.020
## 29 579 Hays AG 5.852500 b 3.7 0.053-0.020
## 30 850 Manhattan AG 3.072500 ab 3.7 0.053-0.020
## 31 472 Tribune EA 5.675000 a 4 0.053-0.020
## 32 850 Manhattan EA 4.202500 a 4 0.053-0.020
## 33 579 Hays EA 10.870000 a 4 0.053-0.020
## 34 579 Hays NP 8.927500 a 4.3 0.053-0.020
## 35 472 Tribune NP 5.085000 a 4.3 0.053-0.020
## 36 850 Manhattan NP 1.410000 b 4.3 0.053-0.020naggp## precip location treatment lsmean SE df lower.CL upper.CL
## 1 472 Tribune NP 63.965361 3.395653 25.35995 56.976913 70.953809
## 2 472 Tribune EA 18.059249 3.395653 25.35995 11.070801 25.047697
## 3 472 Tribune AG 8.551010 3.395653 25.35995 1.562563 15.539458
## 4 579 Hays NP 79.341536 3.395653 25.35995 72.353089 86.329984
## 5 579 Hays EA 33.661765 3.395653 25.35995 26.673317 40.650213
## 6 579 Hays AG 8.396014 3.395653 25.35995 1.407567 15.384462
## 7 850 Manhattan NP 71.105925 3.395653 25.35995 64.117478 78.094373
## 8 850 Manhattan EA 45.922074 3.395653 25.35995 38.933627 52.910522
## 9 850 Manhattan AG 1.474729 3.972346 25.86318 -6.692648 9.642106
## .group location_f
## 1 a Tribune
## 2 b Tribune
## 3 b Tribune
## 4 a Hays
## 5 b Hays
## 6 c Hays
## 7 a Manhattan
## 8 b Manhattan
## 9 c Manhattannagg10p## precip location treatment lsmean SE df lower.CL upper.CL .group
## 1 472 Tribune NP 35.748582 2.917510 26 29.7515545 41.745610 a
## 2 472 Tribune AG 5.721995 2.917510 26 -0.2750325 11.719023 b
## 3 472 Tribune EA 3.686833 2.917510 26 -2.3101946 9.683861 b
## 4 579 Hays NP 67.060386 2.917510 26 61.0633580 73.057413 a
## 5 579 Hays EA 7.599869 2.917510 26 1.6028410 13.596896 b
## 6 579 Hays AG 6.400527 2.917510 26 0.4034990 12.397554 b
## 7 850 Manhattan NP 61.784932 2.917510 26 55.7879043 67.781959 a
## 8 850 Manhattan EA 32.138297 2.917510 26 26.1412695 38.135325 b
## 9 850 Manhattan AG 4.820744 3.452044 26 -2.2750349 11.916522 c
## location_f
## 1 Tribune
## 2 Tribune
## 3 Tribune
## 4 Hays
## 5 Hays
## 6 Hays
## 7 Manhattan
## 8 Manhattan
## 9 Manhattannagg15p## precip location treatment lsmean SE df lower.CL upper.CL
## 1 472 Tribune NP 19.990638 3.794838 26.96694 12.2038258 27.77745
## 2 472 Tribune EA 4.310915 3.794838 26.96694 -3.4758968 12.09773
## 3 472 Tribune AG 4.156583 3.794838 26.96694 -3.6302288 11.94339
## 4 579 Hays NP 51.534489 3.794838 26.96694 43.7476771 59.32130
## 5 579 Hays AG 17.442633 3.794838 26.96694 9.6558211 25.22944
## 6 579 Hays EA 7.009381 3.794838 26.96694 -0.7774306 14.79619
## 7 850 Manhattan NP 54.878590 3.794838 26.96694 47.0917776 62.66540
## 8 850 Manhattan EA 20.871680 3.794838 26.96694 13.0848680 28.65849
## 9 850 Manhattan AG 9.891704 3.794838 26.96694 2.1048916 17.67852
## .group location_f
## 1 a Tribune
## 2 b Tribune
## 3 b Tribune
## 4 a Hays
## 5 b Hays
## 6 b Hays
## 7 a Manhattan
## 8 b Manhattan
## 9 b Manhattan7.1 end
7.2 1) Load packages
library(readxl)
library(dplyr)
library(tidyr)
library(ggplot2)
library(janitor)
library(grid)
library(ggthemes)
library(extrafont)
#font_import()
loadfonts(device = "win")
windowsFonts(Times = windowsFont("TT Times New Roman"))
library(tidyverse)
library(corrplot)
#library(plyr)
library(ggpubr)
library(dplyr)
library(ggforce)7.3 2) Import data
#import data
soilhealth <- read_excel("3-30-21 part 8.1 nrcs soil health agg.xlsx")7.4 3) Data Wrangling
#change column names
soilhealth1 <- soilhealth %>%
clean_names()
#str(soilhealth)
#View(soilhealth)
names(soilhealth1)## [1] "sample_name" "location" "treatment" "depth" "replication"
## [6] "bdepth" "nhorizon" "blk" "horizon" "x20wsa2000"
## [11] "x20wsa250" "x20wsa53" "x20wsa20" "x20mwd" "x5wsa2000"
## [16] "x5wsa250" "x5wsa53" "x5wsa20" "x5mwd" "nagg"soilhealth1 <- as.data.frame(soilhealth1)
# keeps aggregate data
agg <- soilhealth1 %>%
dplyr::select(location, treatment, bdepth, horizon, blk, replication, x20wsa2000, x20wsa250, x20wsa53, x20wsa20, x20mwd, x5wsa2000, x5wsa250, x5wsa53, x5wsa20, x5mwd, nagg)
soils <- agg %>%
filter(location!="Ottawa", treatment!="IR")
agg$location_f =factor(agg$location, levels=c('Tribune', 'Hays', 'Manhattan'))
#str(agg)
#View(agg)
agg1 <- agg%>%
filter(horizon=="1", location!="Ottawa", treatment!="IR")
agg2 <- agg%>%
filter(horizon=="2", location!="Ottawa", treatment!="IR")
agg3 <- agg%>%
filter(horizon=="3", location!="Ottawa", treatment!="IR")
agg4 <- agg%>%
filter(horizon=="4", location!="Ottawa", treatment!="IR")
aggmwd <- agg %>%
filter(location!="Ottawa", treatment!="IR") %>%
na.omit()
agg1$location_f =factor(agg1$location, levels=c('Tribune', 'Hays', 'Manhattan'))7.5 4) Theme James Bar
theme_James <- function(base_size=14, base_family="TT Times New Roman") {
(theme_foundation(base_size=base_size, base_family=base_family)+
theme_bw()+
theme(panel.background = element_rect(colour = NA),
plot.background = element_rect(colour = NA),
axis.title = element_text(color="black",size=rel(1.2)),
axis.text = element_text(color="black", size = 12),
legend.key = element_rect(colour = NA),
legend.spacing = unit(0, "cm"),
legend.text = element_text(size=12),
legend.title = element_blank(),
panel.grid = element_blank(),
plot.title = element_text(color="Black",size = rel(1.5),face = "bold",hjust = 0.5),
strip.text = element_text(color="Black",size = rel(1),face="bold")
))
}7.6 5) Theme James Correlation
theme_James2 <- function(base_size=14, base_family="TT Times New Roman") {
(theme_foundation(base_size=base_size, base_family=base_family)+
theme_bw()+
theme(panel.background = element_rect(colour = NA),
plot.background = element_rect(colour = NA),
axis.title = element_text(color="black",size=rel(1.2)),
axis.text = element_text(color="black", size = 12),
legend.key = element_rect(colour = NA),
legend.spacing = unit(0, "cm"),
legend.text = element_text(size=12),
panel.grid = element_blank(),
plot.title = element_text(color="Black",size = rel(1.5),face = "bold",hjust = 0.5),
strip.text = element_text(color="Black",size = rel(1),face="bold")
))
}8 Correlation Matrix
names(agg)## [1] "location" "treatment" "bdepth" "horizon" "blk"
## [6] "replication" "x20wsa2000" "x20wsa250" "x20wsa53" "x20wsa20"
## [11] "x20mwd" "x5wsa2000" "x5wsa250" "x5wsa53" "x5wsa20"
## [16] "x5mwd" "nagg" "location_f"aggmatrix <- agg %>%
filter(location!="Ottawa", treatment!="IR") %>%
dplyr::select(-location, -treatment, -bdepth, -horizon, -blk, -replication) %>%
dplyr::select(where(is.numeric)) %>% drop_na()
aggmatrix <- na.omit(aggmatrix)
aggmatrix1 <- aggmatrix[, c(5,1,2,3,4,10,6,7,8,9,11)]
#aggmatrix1
aggmat <- cor(aggmatrix1, method = "spearman")
#aggmat
#library("writexl")
#aggmatdf <- as.data.frame(aggmat)
#write_xlsx(aggmatdf,"aggmatdf.xlsx")
library("PerformanceAnalytics")
chart.Correlation(aggmatrix1, histogram = TRUE, pch = 19, method="spearman")
# use exact=FALSE
chart.Correlation(aggmatrix1, histogram = TRUE, pch = 19, method="spearman", exact=FALSE)
colnames(aggmat) <- c( "20 min MWD","20 min 2 mm", "20 min 0.250 mm", "20 min 0.053 mm", "20 min 0.020 mm", "5 min MWD", "5 min 2 mm", "5 min 0.25 mm", "5 min 0.053 mm", "5 min 0.020 mm", "NRCS")
rownames(aggmat) <- c( "20 min MWD","20 min 2 mm", "20 min 0.250 mm", "20 min 0.053 mm", "20 min 0.020 mm", "5 min MWD", "5 min 2 mm", "5 min 0.25 mm", "5 min 0.053 mm", "5 min 0.020 mm", "NRCS")
corrplot(aggmat, method = "square", tl.col = "black", type = "lower", tl.srt = 45, tl.cex = 0.7)
#corrplot.mixed(aggmat, lower.col = "black", number.cex = .7)
#corrplot(aggmat, type = "lower")
corrplot(aggmat, method = "pie",type = "lower", tl.srt = 20, tl.col="black")
#head(p.matr[,])
# cl.* is for color legend, and tl.* if for text legend.
res1<- cor.mtest(aggmat, conf.level=0.95)
#Significance level
fcor <- corrplot(aggmat, method = "pie",type = "upper", tl.srt = 20, tl.col="black", p.mat=res1$p, sig.level = 0.05, title = "Spearman Correlation Matrix p > 0.05")
corrplot(aggmat, method = "number",type = "upper", tl.srt = 20, tl.col="black", p.mat=res1$p, sig.level = 0.05, title = "Spearman Correlation Matrix p > 0.05")
9 20 min Aggregate Graphs
9.1 Aggregate function
#function to calculate the mean and standard error
#0-5 cm
mean_se_fx_20_1 <- function(select_variable, aggregate_size, aggregate_size_conversion){
subset_data <- agg1[, select_variable]
subset_data_1 <- gather(subset_data, aggregate_size , value, - treatment, - location)
subset_data_1$aggregate_size <- factor(subset_data_1$aggregate_size,
levels = aggregate_size)
subset_data_1$aggregate_size <- plyr::mapvalues(subset_data_1$aggregate_size,
from=aggregate_size, to=aggregate_size_conversion)
se <- function(x, na.rm=TRUE) {
if (na.rm) x <- na.omit(x)
sqrt(var(x)/length(x))
}
subset_data_2 <- subset_data_1 %>% group_by(location, treatment, aggregate_size) %>%
summarize(mean_data = mean(value, na.rm = TRUE), standard_error = se(value))
#Reposition location labels
subset_data_2$location <- factor(subset_data_2$location, levels = c("Tribune", "Hays", "Manhattan"))
return(subset_data_2)
}
#5-10 cm
mean_se_fx_20_2 <- function(select_variable, aggregate_size, aggregate_size_conversion){
subset_data <- agg2[, select_variable]
subset_data_1 <- gather(subset_data, aggregate_size , value, - treatment, - location)
subset_data_1$aggregate_size <- factor(subset_data_1$aggregate_size,
levels = aggregate_size)
subset_data_1$aggregate_size <- plyr::mapvalues(subset_data_1$aggregate_size,
from=aggregate_size, to=aggregate_size_conversion)
se <- function(x, na.rm=TRUE) {
if (na.rm) x <- na.omit(x)
sqrt(var(x)/length(x))
}
subset_data_2 <- subset_data_1 %>% group_by(location, treatment, aggregate_size) %>%
summarize(mean_data = mean(value, na.rm = TRUE), standard_error = se(value))
#Reposition location labels
subset_data_2$location <- factor(subset_data_2$location, levels = c("Tribune", "Hays", "Manhattan"))
return(subset_data_2)
}
#10-15 cm
mean_se_fx_20_3 <- function(select_variable, aggregate_size, aggregate_size_conversion){
subset_data <- agg3[, select_variable]
subset_data_1 <- gather(subset_data, aggregate_size , value, - treatment, - location)
subset_data_1$aggregate_size <- factor(subset_data_1$aggregate_size,
levels = aggregate_size)
subset_data_1$aggregate_size <- plyr::mapvalues(subset_data_1$aggregate_size,
from=aggregate_size, to=aggregate_size_conversion)
se <- function(x, na.rm=TRUE) {
if (na.rm) x <- na.omit(x)
sqrt(var(x)/length(x))
}
subset_data_2 <- subset_data_1 %>% group_by(location, treatment, aggregate_size) %>%
summarize(mean_data = mean(value, na.rm = TRUE), standard_error = se(value))
#Reposition location labels
subset_data_2$location <- factor(subset_data_2$location, levels = c("Tribune", "Hays", "Manhattan"))
return(subset_data_2)
}
#15- 25 or 40 cm
mean_se_fx_20_4 <- function(select_variable, aggregate_size, aggregate_size_conversion){
subset_data <- agg4[, select_variable]
subset_data_1 <- gather(subset_data, aggregate_size , value, - treatment, - location)
subset_data_1$aggregate_size <- factor(subset_data_1$aggregate_size,
levels = aggregate_size)
subset_data_1$aggregate_size <- plyr::mapvalues(subset_data_1$aggregate_size,
from=aggregate_size, to=aggregate_size_conversion)
se <- function(x, na.rm=TRUE) {
if (na.rm) x <- na.omit(x)
sqrt(var(x)/length(x))
}
subset_data_2 <- subset_data_1 %>% group_by(location, treatment, aggregate_size) %>%
summarize(mean_data = mean(value, na.rm = TRUE), standard_error = se(value))
#Reposition location labels
subset_data_2$location <- factor(subset_data_2$location, levels = c("Tribune", "Hays", "Manhattan"))
return(subset_data_2)
}
#the color palette for the Treatments
colsnp <- c( "AG" = "black", "EA" = "grey40", "NP" = "grey90")
library(dplyr)9.2 0-5 cm 20 minutes
method_20_1 <- mean_se_fx_20_1(c("treatment", "location", "x20wsa2000",
"x20wsa250", "x20wsa53", "x20wsa20"),
c("x20wsa2000", "x20wsa250", "x20wsa53", "x20wsa20"),
c("8-2", "2-0.25", "0.25-0.053", "0.053-0.020"))
method_20_1$location_f =factor(method_20_1$location, levels=c('Tribune', 'Hays', 'Manhattan'))
method20min5cm <- merge(method_20_1, x20minx5, by=c("location", "treatment", "aggregate_size"))
ggplot(data=method20min5cm, aes(x=aggregate_size, y=mean_data, fill = treatment)) +
geom_bar(position=position_dodge(), stat="identity", colour = "black") +
geom_errorbar(aes(ymin=mean_data-standard_error, ymax=mean_data+standard_error),
width=.2, # Width of the error bars
position=position_dodge(.9)) + ylab("Mean value") +
scale_y_continuous(limits=c(0,80)) + facet_wrap(facets=vars(location_f), strip.position="bottom") +
theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
panel.background = element_blank(), axis.line = element_line(colour = "black"),
legend.position="top",
panel.border = element_rect(colour = "black", fill=NA, size=0.5),
strip.background=element_rect(size=0.5, colour = "black"),
axis.text.x=element_text(colour="black", size=10)) + xlab("Aggregate size fractions (mm)") +
ylab(expression(g ~100 ~g^{-1} ~soil)) +
ggtitle("20 Minute Aggregate Fractions in 0-5 cm Depth") + scale_fill_manual(values = colsnp) +
theme_James()+
theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1)) +
geom_text(aes(label=.group, y=mean_data + standard_error + 3), position = position_dodge(0.9), vjust=0) 
#+ ggsave("20min0_5cm.png", height=6, width=9)9.3 5-10 cm 20 minutes
method_20_2 <- mean_se_fx_20_2(c("treatment", "location", "x20wsa2000",
"x20wsa250", "x20wsa53", "x20wsa20"),
c("x20wsa2000", "x20wsa250", "x20wsa53", "x20wsa20"),
c("8-2", "2-0.25", "0.25-0.053", "0.053-0.020"))
method_20_2$location_f =factor(method_20_2$location, levels=c('Tribune', 'Hays', 'Manhattan'))
method20min10cm <- merge(method_20_2, x20minx10, by=c("location", "treatment", "aggregate_size"))
ggplot(data=method20min10cm, aes(x=aggregate_size, y=mean_data, fill = treatment)) +
geom_bar(position=position_dodge(), stat="identity", colour = "black") +
geom_errorbar(aes(ymin=mean_data-standard_error, ymax=mean_data+standard_error),
width=.2, # Width of the error bars
position=position_dodge(.9)) + ylab("Mean value") +
scale_y_continuous(limits=c(0,80)) + facet_wrap(facets=vars(location_f), strip.position="bottom") +
theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
panel.background = element_blank(), axis.line = element_line(colour = "black"),
legend.position="top",
panel.border = element_rect(colour = "black", fill=NA, size=0.5),
strip.background=element_rect(size=0.5, colour = "black"),
axis.text.x=element_text(colour="black", size=10)) + xlab("Aggregate size fractions (mm)") +
ylab(expression(g ~100 ~g^{-1} ~soil)) +
ggtitle("20 Minute Aggregate Fractions in 5-10 cm Depth") + scale_fill_manual(values = colsnp) +
theme_James()+
theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1)) +
geom_text(aes(label=.group, y=mean_data + standard_error + 3), position = position_dodge(0.9), vjust=0) 
#+ ggsave("20min5_10cm.png", height=6, width=9)9.4 10-15 cm 20 minutes
method_20_3 <- mean_se_fx_20_3(c("treatment", "location", "x20wsa2000",
"x20wsa250", "x20wsa53", "x20wsa20"),
c("x20wsa2000", "x20wsa250", "x20wsa53", "x20wsa20"),
c("8-2", "2-0.25", "0.25-0.053", "0.053-0.020"))
method_20_3$location_f =factor(method_20_3$location, levels=c('Tribune', 'Hays', 'Manhattan'))
method20min15cm <- merge(method_20_3, x20minx15, by=c("location", "treatment", "aggregate_size"))
ggplot(data=method20min15cm, aes(x=aggregate_size, y=mean_data, fill = treatment)) +
geom_bar(position=position_dodge(), stat="identity", colour = "black") +
geom_errorbar(aes(ymin=mean_data-standard_error, ymax=mean_data+standard_error),
width=.2, # Width of the error bars
position=position_dodge(.9)) + ylab("Mean value") +
scale_y_continuous(limits=c(0,80)) + facet_wrap(facets=vars(location_f), strip.position="bottom") +
theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
panel.background = element_blank(), axis.line = element_line(colour = "black"),
legend.position="top",
panel.border = element_rect(colour = "black", fill=NA, size=0.5),
strip.background=element_rect(size=0.5, colour = "black"),
axis.text.x=element_text(colour="black", size=10)) + xlab("Aggregate size fractions (mm)") +
ylab(expression(g ~100 ~g^{-1} ~soil)) +
ggtitle("20 Minute Aggregate Fractions in 10-15 cm Depth") + scale_fill_manual(values = colsnp) +
theme_James()+
theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1)) +
geom_text(aes(label=.group, y=mean_data + standard_error + 3), position = position_dodge(0.9), vjust=0) 
#+ ggsave("20min10_15cm.png", height=6, width=9)9.5 15-25 cm 20 minutes
method_20_4 <- mean_se_fx_20_4(c("treatment", "location", "x20wsa2000",
"x20wsa250", "x20wsa53", "x20wsa20"),
c("x20wsa2000", "x20wsa250", "x20wsa53", "x20wsa20"),
c("8-2", "2-0.25", "0.25-0.053", "0.053-0.020"))
method_20_4$location_f =factor(method_20_4$location, levels=c('Tribune', 'Hays', 'Manhattan'))
ggplot(data=method_20_4, aes(x=aggregate_size, y=mean_data, fill = treatment)) +
geom_bar(position=position_dodge(), stat="identity", colour = "black") +
geom_errorbar(aes(ymin=mean_data-standard_error, ymax=mean_data+standard_error),
width=.2, # Width of the error bars
position=position_dodge(.9)) + ylab("Mean value") +
scale_y_continuous(limits=c(0,80)) + facet_wrap(facets=vars(location_f), strip.position="bottom") +
theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
panel.background = element_blank(), axis.line = element_line(colour = "black"),
legend.position="top",
panel.border = element_rect(colour = "black", fill=NA, size=0.5),
strip.background=element_rect(size=0.5, colour = "black"),
axis.text.x=element_text(colour="black", size=10)) + xlab("Aggregate size fractions (mm)") +
ylab(expression(g ~100 ~g^{-1} ~soil)) +
ggtitle("20 Minute Aggregate Fractions in 15-25 cm Depth") + scale_fill_manual(values = colsnp) +
theme_James()+
theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1))
10 5 min Aggregate Graphs
10.1 Aggregate function
#function to calculate the mean and standard error
#0-5 cm
mean_se_fx_5_1 <- function(select_variable, aggregate_size, aggregate_size_conversion){
subset_data <- agg1[, select_variable]
subset_data_1 <- gather(subset_data, aggregate_size , value, - treatment, - location)
subset_data_1$aggregate_size <- factor(subset_data_1$aggregate_size,
levels = aggregate_size)
subset_data_1$aggregate_size <- plyr::mapvalues(subset_data_1$aggregate_size,
from=aggregate_size, to=aggregate_size_conversion)
se <- function(x, na.rm=TRUE) {
if (na.rm) x <- na.omit(x)
sqrt(var(x)/length(x))
}
subset_data_2 <- subset_data_1 %>% group_by(location, treatment, aggregate_size) %>%
summarize(mean_data = mean(value, na.rm = TRUE), standard_error = se(value))
#Reposition location labels
subset_data_2$location <- factor(subset_data_2$location, levels = c("Tribune", "Hays", "Manhattan"))
return(subset_data_2)
}
#5-10 cm
mean_se_fx_5_2 <- function(select_variable, aggregate_size, aggregate_size_conversion){
subset_data <- agg2[, select_variable]
subset_data_1 <- gather(subset_data, aggregate_size , value, - treatment, - location)
subset_data_1$aggregate_size <- factor(subset_data_1$aggregate_size,
levels = aggregate_size)
subset_data_1$aggregate_size <- plyr::mapvalues(subset_data_1$aggregate_size,
from=aggregate_size, to=aggregate_size_conversion)
se <- function(x, na.rm=TRUE) {
if (na.rm) x <- na.omit(x)
sqrt(var(x)/length(x))
}
subset_data_2 <- subset_data_1 %>% group_by(location, treatment, aggregate_size) %>%
summarize(mean_data = mean(value, na.rm = TRUE), standard_error = se(value))
#Reposition location labels
subset_data_2$location <- factor(subset_data_2$location, levels = c("Tribune", "Hays", "Manhattan"))
return(subset_data_2)
}
#10-15 cm
mean_se_fx_5_3 <- function(select_variable, aggregate_size, aggregate_size_conversion){
subset_data <- agg3[, select_variable]
subset_data_1 <- gather(subset_data, aggregate_size , value, - treatment, - location)
subset_data_1$aggregate_size <- factor(subset_data_1$aggregate_size,
levels = aggregate_size)
subset_data_1$aggregate_size <- plyr::mapvalues(subset_data_1$aggregate_size,
from=aggregate_size, to=aggregate_size_conversion)
se <- function(x, na.rm=TRUE) {
if (na.rm) x <- na.omit(x)
sqrt(var(x)/length(x))
}
subset_data_2 <- subset_data_1 %>% group_by(location, treatment, aggregate_size) %>%
summarize(mean_data = mean(value, na.rm = TRUE), standard_error = se(value))
#Reposition location labels
subset_data_2$location <- factor(subset_data_2$location, levels = c("Tribune", "Hays", "Manhattan"))
return(subset_data_2)
}
#15- 25 or 40 cm
mean_se_fx_5_4 <- function(select_variable, aggregate_size, aggregate_size_conversion){
subset_data <- agg4[, select_variable]
subset_data_1 <- gather(subset_data, aggregate_size , value, - treatment, - location)
subset_data_1$aggregate_size <- factor(subset_data_1$aggregate_size,
levels = aggregate_size)
subset_data_1$aggregate_size <- plyr::mapvalues(subset_data_1$aggregate_size,
from=aggregate_size, to=aggregate_size_conversion)
se <- function(x, na.rm=TRUE) {
if (na.rm) x <- na.omit(x)
sqrt(var(x)/length(x))
}
subset_data_2 <- subset_data_1 %>% group_by(location, treatment, aggregate_size) %>%
summarize(mean_data = mean(value, na.rm = TRUE), standard_error = se(value))
#Reposition location labels
subset_data_2$location <- factor(subset_data_2$location, levels = c("Tribune", "Hays", "Manhattan"))
return(subset_data_2)
}
#the color palette for the Treatments
colsnp <- c( "AG" = "black", "EA" = "grey40", "NP" = "grey90")10.2 0-5 cm 5 minutes
method_5_1 <- mean_se_fx_5_1(c("treatment", "location", "x5wsa2000",
"x5wsa250", "x5wsa53", "x5wsa20"),
c("x5wsa2000", "x5wsa250", "x5wsa53", "x5wsa20"),
c("8-2", "2-0.25", "0.25-0.053", "0.053-0.020"))
method_5_1$location_f =factor(method_5_1$location, levels=c('Tribune', 'Hays', 'Manhattan'))
method5min5cm <- merge(method_5_1, x5minx5, by=c("location", "treatment", "aggregate_size"))
ggplot(data=method5min5cm, aes(x=aggregate_size, y=mean_data, fill = treatment)) +
geom_bar(position=position_dodge(), stat="identity", colour = "black") +
geom_errorbar(aes(ymin=mean_data-standard_error, ymax=mean_data+standard_error),
width=.2, # Width of the error bars
position=position_dodge(.9)) + ylab("Mean value") +
scale_y_continuous(limits=c(0,80)) + facet_wrap(facets=vars(location_f), strip.position="bottom") +
theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
panel.background = element_blank(), axis.line = element_line(colour = "black"),
legend.position="top",
panel.border = element_rect(colour = "black", fill=NA, size=0.5),
strip.background=element_rect(size=0.5, colour = "black"),
axis.text.x=element_text(colour="black", size=10)) + xlab("Aggregate size fractions (mm)") +
ylab(expression(g ~100 ~g^{-1} ~soil)) +
ggtitle("5 Minute Aggregate Fractions in 0-5 cm Depth") + scale_fill_manual(values = colsnp) +
theme_James()+
theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1)) +
geom_text(aes(label=.group, y=mean_data + standard_error + 3), position = position_dodge(0.9), vjust=0) 
#+ ggsave("5min0_5cm.png", height=6, width=9)10.3 5-10 cm 5 minutes
method_5_2 <- mean_se_fx_5_2(c("treatment", "location", "x5wsa2000",
"x5wsa250", "x5wsa53", "x5wsa20"),
c("x5wsa2000", "x5wsa250", "x5wsa53", "x5wsa20"),
c("8-2", "2-0.25", "0.25-0.053", "0.053-0.020"))
method_5_2$location_f =factor(method_5_2$location, levels=c('Tribune', 'Hays', 'Manhattan'))
method5min10cm <- merge(method_5_2, x5minx10, by=c("location", "treatment", "aggregate_size"))
ggplot(data=method5min10cm, aes(x=aggregate_size, y=mean_data, fill = treatment)) +
geom_bar(position=position_dodge(), stat="identity", colour = "black") +
geom_errorbar(aes(ymin=mean_data-standard_error, ymax=mean_data+standard_error),
width=.2, # Width of the error bars
position=position_dodge(.9)) + ylab("Mean value") +
scale_y_continuous(limits=c(0,80)) + facet_wrap(facets=vars(location_f), strip.position="bottom") +
theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
panel.background = element_blank(), axis.line = element_line(colour = "black"),
legend.position="top",
panel.border = element_rect(colour = "black", fill=NA, size=0.5),
strip.background=element_rect(size=0.5, colour = "black"),
axis.text.x=element_text(colour="black", size=10)) + xlab("Aggregate size fractions (mm)") +
ylab(expression(g ~100 ~g^{-1} ~soil)) +
ggtitle("5 Minute Aggregate Fractions in 5-10 cm Depth") +
scale_fill_manual(values = colsnp) +
theme_James()+
theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1)) +
geom_text(aes(label=.group, y=mean_data + standard_error + 3), position = position_dodge(0.9), vjust=0) 
#+ ggsave("5min5-10cm.png", height=6, width=9)10.4 10-15 cm 5 minutes
method_5_3 <- mean_se_fx_5_3(c("treatment", "location", "x5wsa2000",
"x5wsa250", "x5wsa53", "x5wsa20"),
c("x5wsa2000", "x5wsa250", "x5wsa53", "x5wsa20"),
c("8-2", "2-0.25", "0.25-0.053", "0.053-0.020"))
method_5_3$location_f =factor(method_5_3$location, levels=c('Tribune', 'Hays', 'Manhattan'))
method5min15cm <- merge(method_5_3, x5minx15, by=c("location", "treatment", "aggregate_size"))
ggplot(data=method5min15cm, aes(x=aggregate_size, y=mean_data, fill = treatment)) +
geom_bar(position=position_dodge(), stat="identity", colour = "black") +
geom_errorbar(aes(ymin=mean_data-standard_error, ymax=mean_data+standard_error),
width=.2, # Width of the error bars
position=position_dodge(.9)) + ylab("Mean value") +
scale_y_continuous(limits=c(0,80)) + facet_wrap(facets=vars(location_f), strip.position="bottom") +
theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
panel.background = element_blank(), axis.line = element_line(colour = "black"),
legend.position="top",
panel.border = element_rect(colour = "black", fill=NA, size=0.5),
strip.background=element_rect(size=0.5, colour = "black"),
axis.text.x=element_text(colour="black", size=10)) + xlab("Aggregate size fractions (mm)") +
ylab(expression(g ~100 ~g^{-1} ~soil)) +
ggtitle("5 Minute Aggregate Fractions in 10-15 cm Depth") +
scale_fill_manual(values = colsnp) +
theme_James()+
theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1)) +
geom_text(aes(label=.group, y=mean_data + standard_error + 3), position = position_dodge(0.9), vjust=0) 
#+ ggsave("5min10_15cm.png", height=6, width=9)10.5 15-25 cm 5 minutes
method_5_4 <- mean_se_fx_5_4(c("treatment", "location", "x5wsa2000",
"x5wsa250", "x5wsa53", "x5wsa20"),
c("x5wsa2000", "x5wsa250", "x5wsa53", "x5wsa20"),
c("8-2", "2-0.25", "0.25-0.053", "0.053-0.020"))
method_5_4$location_f =factor(method_5_4$location, levels=c('Tribune', 'Hays', 'Manhattan'))
ggplot(data=method_5_4, aes(x=aggregate_size, y=mean_data, fill = treatment)) +
geom_bar(position=position_dodge(), stat="identity", colour = "black") +
geom_errorbar(aes(ymin=mean_data-standard_error, ymax=mean_data+standard_error),
width=.2, # Width of the error bars
position=position_dodge(.9)) + ylab("Mean value") +
scale_y_continuous(limits=c(0,80)) + facet_wrap(facets=vars(location_f), strip.position="bottom") +
theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
panel.background = element_blank(), axis.line = element_line(colour = "black"),
legend.position="top",
panel.border = element_rect(colour = "black", fill=NA, size=0.5),
strip.background=element_rect(size=0.5, colour = "black"),
axis.text.x=element_text(colour="black", size=10)) + xlab("Aggregate size fractions (mm)") +
ylab(expression(g ~100 ~g^{-1} ~soil)) +
ggtitle("5 Minute Aggregate Fractions in 15-25 cm Depth") +
scale_fill_manual(values = colsnp) +
theme_James()+
theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1))
#Final dataframes
x20minx5## precip location treatment lsmean .group xloc aggregate_size
## 1 579 Hays AG 0.9315208 b .7 8-2
## 2 472 Tribune AG 8.7304187 b .7 8-2
## 3 850 Manhattan AG 1.9782694 b .7 8-2
## 4 472 Tribune EA 8.8448459 b 1 8-2
## 5 579 Hays EA 9.3305850 b 1 8-2
## 6 850 Manhattan EA 11.4886335 b 1 8-2
## 7 472 Tribune NP 26.3313434 a 1.3 8-2
## 8 850 Manhattan NP 25.3077401 a 1.3 8-2
## 9 579 Hays NP 30.8387700 a 1.3 8-2
## 10 579 Hays AG 11.9734301 b 1.7 2-0.25
## 11 472 Tribune AG 14.4454999 b 1.7 2-0.25
## 12 850 Manhattan AG 17.6278247 c 1.7 2-0.25
## 13 472 Tribune EA 16.2781993 b 2 2-0.25
## 14 579 Hays EA 22.0219300 a 2 2-0.25
## 15 850 Manhattan EA 24.9732871 b 2 2-0.25
## 16 472 Tribune NP 25.6052664 a 2.3 2-0.25
## 17 850 Manhattan NP 37.2452781 a 2.3 2-0.25
## 18 579 Hays NP 28.5391700 a 2.3 2-0.25
## 19 472 Tribune AG 53.0739889 a 2.7 0.25-0.053
## 20 850 Manhattan AG 61.1650379 a 2.7 0.25-0.053
## 21 579 Hays AG 69.7972833 a 2.7 0.25-0.053
## 22 472 Tribune EA 49.1307814 a 3 0.25-0.053
## 23 579 Hays EA 47.9366450 b 3 0.25-0.053
## 24 850 Manhattan EA 47.3814008 b 3 0.25-0.053
## 25 579 Hays NP 14.9092950 c 3.3 0.25-0.053
## 26 472 Tribune NP 22.2972642 b 3.3 0.25-0.053
## 27 850 Manhattan NP 16.5634973 c 3.3 0.25-0.053
## 28 472 Tribune AG 6.1575000 a 3.7 0.053-0.020
## 29 850 Manhattan AG 7.2450000 a 3.7 0.053-0.020
## 30 579 Hays AG 5.2825000 a 3.7 0.053-0.020
## 31 472 Tribune EA 3.9900000 ab 4 0.053-0.020
## 32 579 Hays EA 3.3750000 a 4 0.053-0.020
## 33 850 Manhattan EA 5.1450000 a 4 0.053-0.020
## 34 579 Hays NP 1.0475000 b 4.3 0.053-0.020
## 35 472 Tribune NP 1.9500000 b 4.3 0.053-0.020
## 36 850 Manhattan NP 1.9325000 b 4.3 0.053-0.020x20minx10## precip location treatment lsmean .group xloc aggregate_size
## 1 472 Tribune AG 7.158672 b .7 8-2
## 2 850 Manhattan AG 3.003322 b .7 8-2
## 3 579 Hays AG 1.369402 b .7 8-2
## 4 472 Tribune EA 2.303734 b 1 8-2
## 5 850 Manhattan EA 8.197339 b 1 8-2
## 6 579 Hays EA 4.312530 b 1 8-2
## 7 472 Tribune NP 19.874634 a 1.3 8-2
## 8 850 Manhattan NP 19.539639 a 1.3 8-2
## 9 579 Hays NP 27.933098 a 1.3 8-2
## 10 472 Tribune AG 31.380248 a 1.7 2-0.25
## 11 579 Hays AG 12.446052 b 1.7 2-0.25
## 12 850 Manhattan AG 19.009357 b 1.7 2-0.25
## 13 579 Hays EA 29.768317 a 2 2-0.25
## 14 472 Tribune EA 15.885406 b 2 2-0.25
## 15 850 Manhattan EA 31.988045 ab 2 2-0.25
## 16 472 Tribune NP 33.762260 a 2.3 2-0.25
## 17 850 Manhattan NP 35.211923 a 2.3 2-0.25
## 18 579 Hays NP 22.881412 ab 2.3 2-0.25
## 19 472 Tribune AG 40.252754 b 2.7 0.25-0.053
## 20 850 Manhattan AG 60.480425 a 2.7 0.25-0.053
## 21 579 Hays AG 61.041555 a 2.7 0.25-0.053
## 22 472 Tribune EA 60.538628 a 3 0.25-0.053
## 23 850 Manhattan EA 45.043383 b 3 0.25-0.053
## 24 579 Hays EA 47.547415 b 3 0.25-0.053
## 25 579 Hays NP 28.361588 c 3.3 0.25-0.053
## 26 472 Tribune NP 24.336891 c 3.3 0.25-0.053
## 27 850 Manhattan NP 23.599879 c 3.3 0.25-0.053
## 28 472 Tribune AG 4.107500 ab 3.7 0.053-0.020
## 29 579 Hays AG 8.777500 a 3.7 0.053-0.020
## 30 850 Manhattan AG 4.812500 ab 3.7 0.053-0.020
## 31 472 Tribune EA 5.410000 a 4 0.053-0.020
## 32 850 Manhattan EA 5.047500 a 4 0.053-0.020
## 33 579 Hays EA 3.777500 b 4 0.053-0.020
## 34 579 Hays NP 1.757500 c 4.3 0.053-0.020
## 35 472 Tribune NP 2.182500 b 4.3 0.053-0.020
## 36 850 Manhattan NP 3.040000 b 4.3 0.053-0.020x20minx15## precip location treatment lsmean .group xloc aggregate_size
## 1 472 Tribune AG 7.344079 b .7 8-2
## 2 850 Manhattan AG 2.653159 b .7 8-2
## 3 579 Hays AG 1.931631 b .7 8-2
## 4 472 Tribune EA 3.058975 b 1 8-2
## 5 850 Manhattan EA 4.378598 b 1 8-2
## 6 579 Hays EA 2.561610 b 1 8-2
## 7 472 Tribune NP 26.297002 a 1.3 8-2
## 8 850 Manhattan NP 25.368150 a 1.3 8-2
## 9 579 Hays NP 23.871558 a 1.3 8-2
## 10 472 Tribune AG 27.333662 ab 1.7 2-0.25
## 11 579 Hays AG 32.940850 a 1.7 2-0.25
## 12 850 Manhattan AG 29.494218 a 1.7 2-0.25
## 13 579 Hays EA 18.866673 a 2 2-0.25
## 14 472 Tribune EA 15.882277 b 2 2-0.25
## 15 850 Manhattan EA 25.795000 a 2 2-0.25
## 16 472 Tribune NP 31.521145 a 2.3 2-0.25
## 17 850 Manhattan NP 37.563085 a 2.3 2-0.25
## 18 579 Hays NP 23.263343 a 2.3 2-0.25
## 19 472 Tribune AG 43.855421 a 2.7 0.25-0.053
## 20 850 Manhattan AG 54.041827 a 2.7 0.25-0.053
## 21 579 Hays AG 44.035286 b 2.7 0.25-0.053
## 22 472 Tribune EA 51.129566 a 3 0.25-0.053
## 23 579 Hays EA 59.985325 a 3 0.25-0.053
## 24 850 Manhattan EA 52.365267 a 3 0.25-0.053
## 25 579 Hays NP 32.689282 b 3.3 0.25-0.053
## 26 472 Tribune NP 20.873743 b 3.3 0.25-0.053
## 27 850 Manhattan NP 19.454231 b 3.3 0.25-0.053
## 28 472 Tribune AG 4.412500 b 3.7 0.053-0.020
## 29 579 Hays AG 7.827500 a 3.7 0.053-0.020
## 30 850 Manhattan AG 3.470000 b 3.7 0.053-0.020
## 31 472 Tribune EA 8.422500 a 4 0.053-0.020
## 32 850 Manhattan EA 6.940000 a 4 0.053-0.020
## 33 579 Hays EA 5.562500 a 4 0.053-0.020
## 34 579 Hays NP 2.440000 b 4.3 0.053-0.020
## 35 472 Tribune NP 1.615000 b 4.3 0.053-0.020
## 36 850 Manhattan NP 1.732500 b 4.3 0.053-0.020x5minx5## precip location treatment lsmean .group xloc aggregate_size
## 1 579 Hays AG 1.563937 c .7 8-2
## 2 472 Tribune AG 6.619284 a .7 8-2
## 3 850 Manhattan AG 2.857780 c .7 8-2
## 4 472 Tribune EA 10.186894 a 1 8-2
## 5 850 Manhattan EA 14.241278 b 1 8-2
## 6 579 Hays EA 25.901540 b 1 8-2
## 7 472 Tribune NP 8.822787 a 1.3 8-2
## 8 850 Manhattan NP 25.434619 a 1.3 8-2
## 9 579 Hays NP 44.065476 a 1.3 8-2
## 10 579 Hays AG 27.649027 a 1.7 2-0.25
## 11 472 Tribune AG 9.931781 b 1.7 2-0.25
## 12 850 Manhattan AG 28.049438 b 1.7 2-0.25
## 13 472 Tribune EA 29.018520 a 2 2-0.25
## 14 579 Hays EA 26.595305 a 2 2-0.25
## 15 850 Manhattan EA 31.323713 b 2 2-0.25
## 16 850 Manhattan NP 44.262281 a 2.3 2-0.25
## 17 472 Tribune NP 27.005202 a 2.3 2-0.25
## 18 579 Hays NP 32.570016 a 2.3 2-0.25
## 19 472 Tribune AG 51.284628 a 2.7 0.25-0.053
## 20 850 Manhattan AG 52.782708 a 2.7 0.25-0.053
## 21 579 Hays AG 46.220153 a 2.7 0.25-0.053
## 22 472 Tribune EA 35.120163 b 3 0.25-0.053
## 23 579 Hays EA 39.818455 a 3 0.25-0.053
## 24 850 Manhattan EA 30.859602 b 3 0.25-0.053
## 25 579 Hays NP 18.923355 b 3.3 0.25-0.053
## 26 472 Tribune NP 23.414279 b 3.3 0.25-0.053
## 27 850 Manhattan NP 12.952119 c 3.3 0.25-0.053
## 28 472 Tribune AG 6.822500 a 3.7 0.053-0.020
## 29 579 Hays AG 6.052500 b 3.7 0.053-0.020
## 30 850 Manhattan AG 3.980000 a 3.7 0.053-0.020
## 31 579 Hays EA 16.817500 a 4 0.053-0.020
## 32 472 Tribune EA 4.965000 a 4 0.053-0.020
## 33 850 Manhattan EA 3.775000 a 4 0.053-0.020
## 34 579 Hays NP 8.617500 b 4.3 0.053-0.020
## 35 472 Tribune NP 5.255000 a 4.3 0.053-0.020
## 36 850 Manhattan NP 1.433954 a 4.3 0.053-0.020x5minx10## precip location treatment lsmean .group xloc aggregate_size
## 1 472 Tribune AG 7.358129 a .7 8-2
## 2 850 Manhattan AG 4.704605 c .7 8-2
## 3 579 Hays AG 3.551578 c .7 8-2
## 4 472 Tribune EA 3.989024 a 1 8-2
## 5 850 Manhattan EA 18.601440 b 1 8-2
## 6 579 Hays EA 10.999532 b 1 8-2
## 7 472 Tribune NP 7.784108 a 1.3 8-2
## 8 850 Manhattan NP 27.719093 a 1.3 8-2
## 9 579 Hays NP 47.950775 a 1.3 8-2
## 10 579 Hays AG 16.110140 b 1.7 2-0.25
## 11 472 Tribune AG 15.926345 b 1.7 2-0.25
## 12 850 Manhattan AG 41.277747 a 1.7 2-0.25
## 13 472 Tribune EA 17.127007 b 2 2-0.25
## 14 579 Hays EA 38.088665 a 2 2-0.25
## 15 850 Manhattan EA 37.566067 a 2 2-0.25
## 16 472 Tribune NP 36.000295 a 2.3 2-0.25
## 17 850 Manhattan NP 44.207087 a 2.3 2-0.25
## 18 579 Hays NP 37.440809 a 2.3 2-0.25
## 19 472 Tribune AG 48.790371 a 2.7 0.25-0.053
## 20 850 Manhattan AG 42.544111 a 2.7 0.25-0.053
## 21 579 Hays AG 53.844274 a 2.7 0.25-0.053
## 22 472 Tribune EA 56.268022 a 3 0.25-0.053
## 23 850 Manhattan EA 23.878426 b 3 0.25-0.053
## 24 579 Hays EA 52.739372 a 3 0.25-0.053
## 25 579 Hays NP 26.004243 b 3.3 0.25-0.053
## 26 472 Tribune NP 28.543049 b 3.3 0.25-0.053
## 27 850 Manhattan NP 12.828371 b 3.3 0.25-0.053
## 28 472 Tribune AG 7.580000 a 3.7 0.053-0.020
## 29 579 Hays AG 5.632500 b 3.7 0.053-0.020
## 30 850 Manhattan AG 2.252500 a 3.7 0.053-0.020
## 31 850 Manhattan EA 4.247500 a 4 0.053-0.020
## 32 472 Tribune EA 6.502500 a 4 0.053-0.020
## 33 579 Hays EA 11.552500 a 4 0.053-0.020
## 34 579 Hays NP 9.017500 a 4.3 0.053-0.020
## 35 472 Tribune NP 4.895000 a 4.3 0.053-0.020
## 36 850 Manhattan NP 1.715000 a 4.3 0.053-0.020x5minx15## precip location treatment lsmean .group xloc aggregate_size
## 1 472 Tribune AG 6.606750 a .7 8-2
## 2 579 Hays AG 11.637256 b .7 8-2
## 3 850 Manhattan AG 4.467970 b .7 8-2
## 4 579 Hays EA 7.687615 b 1 8-2
## 5 472 Tribune EA 6.572290 a 1 8-2
## 6 850 Manhattan EA 15.118422 ab 1 8-2
## 7 472 Tribune NP 14.583834 a 1.3 8-2
## 8 850 Manhattan NP 26.750084 a 1.3 8-2
## 9 579 Hays NP 40.495560 a 1.3 8-2
## 10 472 Tribune AG 19.599914 a 1.7 2-0.25
## 11 850 Manhattan AG 52.686735 a 1.7 2-0.25
## 12 579 Hays AG 32.008450 a 1.7 2-0.25
## 13 472 Tribune EA 32.715244 a 2 2-0.25
## 14 579 Hays EA 45.464665 a 2 2-0.25
## 15 850 Manhattan EA 36.017346 a 2 2-0.25
## 16 472 Tribune NP 18.032457 a 2.3 2-0.25
## 17 850 Manhattan NP 37.692543 a 2.3 2-0.25
## 18 579 Hays NP 32.094026 a 2.3 2-0.25
## 19 472 Tribune AG 54.061937 a 2.7 0.25-0.053
## 20 850 Manhattan AG 33.095686 a 2.7 0.25-0.053
## 21 579 Hays AG 32.267456 b 2.7 0.25-0.053
## 22 472 Tribune EA 41.100643 ab 3 0.25-0.053
## 23 579 Hays EA 49.596737 a 3 0.25-0.053
## 24 850 Manhattan EA 29.540473 a 3 0.25-0.053
## 25 579 Hays NP 26.417570 b 3.3 0.25-0.053
## 26 472 Tribune NP 33.014734 b 3.3 0.25-0.053
## 27 850 Manhattan NP 20.066238 a 3.3 0.25-0.053
## 28 472 Tribune AG 5.557500 a 3.7 0.053-0.020
## 29 579 Hays AG 5.852500 b 3.7 0.053-0.020
## 30 850 Manhattan AG 3.072500 ab 3.7 0.053-0.020
## 31 472 Tribune EA 5.675000 a 4 0.053-0.020
## 32 850 Manhattan EA 4.202500 a 4 0.053-0.020
## 33 579 Hays EA 10.870000 a 4 0.053-0.020
## 34 579 Hays NP 8.927500 a 4.3 0.053-0.020
## 35 472 Tribune NP 5.085000 a 4.3 0.053-0.020
## 36 850 Manhattan NP 1.410000 b 4.3 0.053-0.02011 NRCS Aggregate Graphs
11.1 Aggregate function
#function to calculate the mean and standard error
#0-5 cm
mean_se_fx_n_1 <- function(select_variable, aggregate_size, aggregate_size_conversion){
subset_data <- agg1[, select_variable]
subset_data_1 <- gather(subset_data, aggregate_size , value, - treatment, - location)
subset_data_1$aggregate_size <- factor(subset_data_1$aggregate_size,
levels = aggregate_size)
subset_data_1$aggregate_size <- plyr::mapvalues(subset_data_1$aggregate_size,
from=aggregate_size, to=aggregate_size_conversion)
se <- function(x, na.rm=TRUE) {
if (na.rm) x <- na.omit(x)
sqrt(var(x)/length(x))
}
subset_data_2 <- subset_data_1 %>% group_by(location, treatment, aggregate_size) %>%
summarize(mean_data = mean(value, na.rm = TRUE), standard_error = se(value))
#Reposition location labels
subset_data_2$location <- factor(subset_data_2$location, levels = c("Tribune", "Hays", "Manhattan"))
return(subset_data_2)
}
#5-10 cm
mean_se_fx_n_2 <- function(select_variable, aggregate_size, aggregate_size_conversion){
subset_data <- agg2[, select_variable]
subset_data_1 <- gather(subset_data, aggregate_size , value, - treatment, - location)
subset_data_1$aggregate_size <- factor(subset_data_1$aggregate_size,
levels = aggregate_size)
subset_data_1$aggregate_size <- plyr::mapvalues(subset_data_1$aggregate_size,
from=aggregate_size, to=aggregate_size_conversion)
se <- function(x, na.rm=TRUE) {
if (na.rm) x <- na.omit(x)
sqrt(var(x)/length(x))
}
subset_data_2 <- subset_data_1 %>% group_by(location, treatment, aggregate_size) %>%
summarize(mean_data = mean(value, na.rm = TRUE), standard_error = se(value))
#Reposition location labels
subset_data_2$location <- factor(subset_data_2$location, levels = c("Tribune", "Hays", "Manhattan"))
return(subset_data_2)
}
#10-15 cm
mean_se_fx_n_3 <- function(select_variable, aggregate_size, aggregate_size_conversion){
subset_data <- agg3[, select_variable]
subset_data_1 <- gather(subset_data, aggregate_size , value, - treatment, - location)
subset_data_1$aggregate_size <- factor(subset_data_1$aggregate_size,
levels = aggregate_size)
subset_data_1$aggregate_size <- plyr::mapvalues(subset_data_1$aggregate_size,
from=aggregate_size, to=aggregate_size_conversion)
se <- function(x, na.rm=TRUE) {
if (na.rm) x <- na.omit(x)
sqrt(var(x)/length(x))
}
subset_data_2 <- subset_data_1 %>% group_by(location, treatment, aggregate_size) %>%
summarize(mean_data = mean(value, na.rm = TRUE), standard_error = se(value))
#Reposition location labels
subset_data_2$location <- factor(subset_data_2$location, levels = c("Tribune", "Hays", "Manhattan"))
return(subset_data_2)
}
#15- 25 or 40 cm
mean_se_fx_n_4 <- function(select_variable, aggregate_size, aggregate_size_conversion){
subset_data <- agg4[, select_variable]
subset_data_1 <- gather(subset_data, aggregate_size , value, - treatment, - location)
subset_data_1$aggregate_size <- factor(subset_data_1$aggregate_size,
levels = aggregate_size)
subset_data_1$aggregate_size <- plyr::mapvalues(subset_data_1$aggregate_size,
from=aggregate_size, to=aggregate_size_conversion)
se <- function(x, na.rm=TRUE) {
if (na.rm) x <- na.omit(x)
sqrt(var(x)/length(x))
}
subset_data_2 <- subset_data_1 %>% group_by(location, treatment, aggregate_size) %>%
summarize(mean_data = mean(value, na.rm = TRUE), standard_error = se(value))
#Reposition location labels
subset_data_2$location <- factor(subset_data_2$location, levels = c("Tribune", "Hays", "Manhattan"))
return(subset_data_2)
}
#the color palette for the Treatments
colsnp <- c( "AG" = "black", "EA" = "grey40", "NP" = "grey90")11.2 0-5 cm NRCS
method_n_1 <- mean_se_fx_n_1(c("treatment", "location", "nagg"),
c("nagg"),
c(""))
method_n_1$location_f =factor(method_n_1$location, levels=c('Tribune', 'Hays', 'Manhattan'))
methodnagg5cm <- merge(method_n_1, naggp, by=c("location", "treatment", "location_f"))
ggplot(data=methodnagg5cm, aes(x=aggregate_size, y=mean_data, fill = treatment)) +
geom_bar(position=position_dodge(), stat="identity", colour = "black") +
geom_errorbar(aes(ymin=mean_data-standard_error, ymax=mean_data+standard_error),
width=.2, # Width of the error bars
position=position_dodge(.9)) + ylab("Mean value") +
scale_y_continuous(limits=c(0,90)) + facet_wrap(facets=vars(location_f), strip.position="bottom") +
theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
panel.background = element_blank(), axis.line = element_line(colour = "black"),
legend.position="top",
panel.border = element_rect(colour = "black", fill=NA, size=0.5),
strip.background=element_rect(size=0.5, colour = "black"),
axis.text.x=element_text(colour="black", size=10)) + xlab("% aggregate between 2 mm to 0.25 mm size fraction") +
ylab("Aggregate Retained (%)") +
ggtitle("NRCS Aggregate Fractions in 0-5 cm Depth") +
scale_fill_manual(values = colsnp) +
theme_James() +
geom_text(aes(label=.group, y=mean_data + standard_error + 3), position = position_dodge(0.9), vjust=0) 
#+ ggsave("nagg5cm.png", height=6, width=9)11.3 5-10 cm NRCS
method_n_2 <- mean_se_fx_n_2(c("treatment", "location", "nagg"),
c("nagg"),
c(""))
method_n_2$location_f =factor(method_n_2$location, levels=c('Tribune', 'Hays', 'Manhattan'))
methodnagg10cm <- merge(method_n_2, nagg10p, by=c("location", "treatment", "location_f"))
ggplot(data=methodnagg10cm, aes(x=aggregate_size, y=mean_data, fill = treatment)) +
geom_bar(position=position_dodge(), stat="identity", colour = "black") +
geom_errorbar(aes(ymin=mean_data-standard_error, ymax=mean_data+standard_error),
width=.2, # Width of the error bars
position=position_dodge(.9)) + ylab("Mean value") +
scale_y_continuous(limits=c(0,80)) + facet_wrap(facets=vars(location_f), strip.position="bottom") +
theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
panel.background = element_blank(), axis.line = element_line(colour = "black"),
legend.position="top",
panel.border = element_rect(colour = "black", fill=NA, size=0.5),
strip.background=element_rect(size=0.5, colour = "black"),
axis.text.x=element_text(colour="black", size=10)) + xlab("% aggregate between 2 mm to 0.25 mm size fraction") +
ylab("Aggregate Retained (%)") +
ggtitle("NRCS Aggregate Fractions in 5-10 cm Depth") +
scale_fill_manual(values = colsnp) +
theme_James() +
geom_text(aes(label=.group, y=mean_data + standard_error + 3), position = position_dodge(0.9), vjust=0) 
#+ ggsave("nagg10cm.png", height=6, width=9)11.4 10-15 cm NRCS
method_n_3 <- mean_se_fx_n_3(c("treatment", "location", "nagg"),
c("nagg"),
c(""))
method_n_3$location_f =factor(method_n_3$location, levels=c('Tribune', 'Hays', 'Manhattan'))
methodnagg15cm <- merge(method_n_3, nagg15p, by=c("location", "treatment", "location_f"))
ggplot(data=methodnagg15cm, aes(x=aggregate_size, y=mean_data, fill = treatment)) +
geom_bar(position=position_dodge(), stat="identity", colour = "black") +
geom_errorbar(aes(ymin=mean_data-standard_error, ymax=mean_data+standard_error),
width=.2, # Width of the error bars
position=position_dodge(.9)) + ylab("Mean value") +
scale_y_continuous(limits=c(0,80)) + facet_wrap(facets=vars(location_f), strip.position="bottom") +
theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
panel.background = element_blank(), axis.line = element_line(colour = "black"),
legend.position="top",
panel.border = element_rect(colour = "black", fill=NA, size=0.5),
strip.background=element_rect(size=0.5, colour = "black"),
axis.text.x=element_text(colour="black", size=10)) + xlab("% aggregate between 2 mm to 0.25 mm size fraction") +
ylab("Aggregate Retained (%)") +
ggtitle("NRCS Aggregate Fractions in 10-15 cm Depth") +
scale_fill_manual(values = colsnp) +
theme_James() +
geom_text(aes(label=.group, y=mean_data + standard_error + 3), position = position_dodge(0.9), vjust=0)
#+ ggsave("nagg15cm.png", height=6, width=9)11.5 15-25 cm NRCS
method_n_4 <- mean_se_fx_n_4(c("treatment", "location", "nagg"),
c("nagg"),
c(""))
method_n_4$location_f =factor(method_n_4$location, levels=c('Tribune', 'Hays', 'Manhattan'))
ggplot(data=method_n_4, aes(x=aggregate_size, y=mean_data, fill = treatment)) +
geom_bar(position=position_dodge(), stat="identity", colour = "black") +
geom_errorbar(aes(ymin=mean_data-standard_error, ymax=mean_data+standard_error),
width=.2, # Width of the error bars
position=position_dodge(.9)) + ylab("Mean value") +
scale_y_continuous(limits=c(0,80)) + facet_wrap(facets=vars(location_f), strip.position="bottom") +
theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
panel.background = element_blank(), axis.line = element_line(colour = "black"),
legend.position="top",
panel.border = element_rect(colour = "black", fill=NA, size=0.5),
strip.background=element_rect(size=0.5, colour = "black"),
axis.text.x=element_text(colour="black", size=10)) + xlab("% aggregate between 2 mm to 0.25 mm size fraction") +
ylab("Aggregate Retained (%)") +
ggtitle("NRCS Aggregate Fractions in 15-25 cm Depth") +
scale_fill_manual(values = colsnp) +
theme_James()
#20 and 5 minute MWD
11.6 0-5 cm 5 minutes
method_n_1 <- mean_se_fx_n_1(c("treatment", "location", "nagg"),
c("nagg"),
c(""))
method_n_1$location_f =factor(method_n_1$location, levels=c('Tribune', 'Hays', 'Manhattan'))
methodnagg5cm <- merge(method_n_1, naggp, by=c("location", "treatment", "location_f"))
ggplot(data=methodnagg5cm, aes(x=aggregate_size, y=mean_data, fill = treatment)) +
geom_bar(position=position_dodge(), stat="identity", colour = "black") +
geom_errorbar(aes(ymin=mean_data-standard_error, ymax=mean_data+standard_error),
width=.2, # Width of the error bars
position=position_dodge(.9)) + ylab("Mean value") +
scale_y_continuous(limits=c(0,90)) + facet_wrap(facets=vars(location_f), strip.position="bottom") +
theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
panel.background = element_blank(), axis.line = element_line(colour = "black"),
legend.position="top",
panel.border = element_rect(colour = "black", fill=NA, size=0.5),
strip.background=element_rect(size=0.5, colour = "black"),
axis.text.x=element_text(colour="black", size=10)) + xlab("% aggregate between 2 mm to 0.25 mm size fraction") +
ylab("Aggregate Retained (%)") +
ggtitle("NRCS Aggregate Fractions in 0-5 cm Depth") +
scale_fill_manual(values = colsnp) +
theme_James() +
geom_text(aes(label=.group, y=mean_data + standard_error + 3), position = position_dodge(0.9), vjust=0)
#+ ggsave("nagg5cm.png", height=6, width=9)12 Methods Comparison
12.1 Data Manipulation
#remove Ottawa and irrigation dataset since 5MWD isnt available
# data frame for (20 minutes vs 5 minutes) & (5 minutes vs NRCS)- only has 4 horizons
soils <- agg %>%
filter(location!="Ottawa", treatment!="IR") %>%
na.omit()
soils$location_a =factor(soils$location, levels=c('Tribune', 'Hays', 'Manhattan'))
soils$horizon_a =factor(soils$horizon, levels=c('1', '2', '3', '4'))
# data frame for 20 minutes vs NRCS- has all horizons
soils_b <- agg %>%
dplyr::select(-x5mwd, -x5wsa2000, -x5wsa250, -x5wsa53, -x5wsa20) %>%
dplyr::filter(location!="Ottawa", treatment!="IR") %>%
na.omit()
soils_b$location_b =factor(soils_b$location, levels=c('Tribune', 'Hays', 'Manhattan'))
soils_b$horizon_b =factor(soils_b$horizon, levels=c('1', '2', '3', '4', '5', '6', '7'))12.2 20mwd and 5mwd Correlation graphs
use soils data frame and location_a and horizon_a
#20 minute Mean Weight Diameter vs 5 minute Method
soils %>%
ggplot(aes(x=x20mwd, y= x5mwd))+
geom_point(size=.5)+
labs(x="20 Minute Method (mm)",
y="5 Minute Method (mm)",
title="Correlation between 20 vs 5 minute MWD") +
theme_bw(base_size=12, base_family='TT Times New Roman')+
geom_smooth(method="lm", se=FALSE)+
theme(panel.grid.major = element_blank(),
panel.grid.minor = element_blank()) +
theme_James() +
stat_cor(aes(label = paste(..rr.label.., sep = "~`,`~")), method="spearman", na.rm=F, label.x=.1, label.y=3.4, p.accuracy = 0.001, show.legend = F) +
stat_regline_equation(label.y=3)
#cor(soils$x20mwd, soils$x5mwd, method="spearman", use="complete.obs")
#One graph by location
soils %>%
ggplot(aes(x=x20mwd, y= x5mwd, color=location_a, shape=location_a))+
geom_point(size=1)+
labs(x="20 Minute Method (mm)",
y="5 Minute Method (mm)",
title="Correlation between 20 vs 5 minute MWD") +
theme_classic()+
geom_smooth(method="lm", se=FALSE)+
theme_James() +
stat_cor(aes(color=location_a, label = paste(..rr.label.., sep = "~`,`~")), method="spearman", na.rm=F, label.x=.01, p.accuracy = 0.001, show.legend = F) +
stat_regline_equation(label.x=.5, show.legend = F)
#group by location
soils %>%
ggplot(aes(x=x20mwd, y= x5mwd))+
facet_wrap(~location_a)+
labs(x="20 Minute Method (mm)",
y="5 Minute Method (mm)",
title="Correlation between 20 vs 5 minute MWD by Location") +
theme_classic()+
geom_smooth(method="lm", se=FALSE, color= "black") +
geom_point(size=.5)+
theme_James() +
stat_cor(aes(color=location_a, label = paste(..rr.label.., sep = "~`,`~")), method="spearman", na.rm=F, label.y=.01, p.accuracy = 0.001, show.legend = F) +
stat_regline_equation(label.x=.5, show.legend = F)
# just to find p value for tribune
soils %>%
ggplot(aes(x=x20mwd, y= x5mwd))+
facet_wrap(~location_a)+
labs(x="20 Minute Method (mm)",
y="5 Minute Method (mm)",
title="Correlation between 20 vs 5 minute MWD by Location") +
theme_classic()+
geom_smooth(method="lm", se=FALSE, color= "black") +
geom_point(size=.5)+
theme_James() +
stat_cor(aes(color=location_a, label = paste(..rr.label.., sep = "~`,`~")), method="spearman", na.rm=F, label.y=.01, show.legend = F)+
stat_regline_equation(label.x=.5, show.legend = F) ### Correlation plots for group depths
#20 minute Mean Weight Diameter vs 5 minute Method
#group by location
soils %>%
ggplot(aes(x=x20mwd, y= x5mwd, color=treatment))+
facet_wrap(~location_a)+
labs(x="20 Minute Method (mm)",
y="5 Minute Method (mm)",
title="Correlation between 20 vs 5 minute MWD by Location", shape="Horizon", color="Treatment") +
scale_y_continuous(limits=c(0,5)) +
theme_classic()+
geom_point(size=2)+
theme_James2()+
stat_cor(aes(label = paste(..r.label..,..rr.label.., ..p.label.., sep = "~`,`~")), method="spearman", na.rm=F, p.accuracy = 0.001, show.legend = F)
#Has correlation by treatment by location
soils %>%
ggplot(aes(x=x20mwd, y= x5mwd, color=treatment))+
facet_wrap(~location_a)+
stat_cor(aes(label = paste(..rr.label.., sep = "~`,`~")), method="spearman", na.rm=F, p.accuracy = 0.001, show.legend = F)+ labs(x="20 Minute Method (mm)",
y="5 Minute Method (mm)",
title="Correlation between 20 vs 5 minute MWD by Location", shape="Horizon", color="Treatment") +
scale_y_continuous(limits=c(0,5)) +
theme_classic()+
geom_point(size=2, aes(shape=horizon_a))+
theme_James2() +
stat_regline_equation(label.x=1.3, show.legend = F) 
ggsave("20min5mincor.png", height=6, width=9)
#Has correlation by treatment by location and has eclipses
soils %>%
ggplot(aes(x=x20mwd, y= x5mwd, color=treatment))+
facet_wrap(~location_a)+
stat_cor(aes(label = paste(..rr.label.., sep = "~`,`~")), method="spearman", na.rm=F, p.accuracy = 0.001, show.legend = F)+ labs(x="20 Minute Method (mm)",
y="5 Minute Method (mm)",
title="Correlation between 20 vs 5 minute MWD by Location", shape="Horizon", color="Treatment") +
scale_y_continuous(limits=c(0,5)) +
theme_classic()+
geom_point(size=2, aes(shape=horizon_a))+
theme_James2() +
geom_mark_ellipse(expand=0, aes(fill=treatment), show.legend = F)
12.3 20mwd and NRCS Correlation graphs
use soils_b data frame and location_b and horizon_b
#20 minute Mean Weight Diameter vs NRCS Hand Method
soils_b %>%
ggplot(aes(x=x20mwd, y= nagg))+
geom_point(size=.5)+
labs(x="20 minute method (mm)",
y="NRCS Hand Method (%)",
title="Correlation between 20 Minute MWD vs NRCS") +
theme_classic()+
geom_smooth(method="lm", se=FALSE) +
theme_James() +
stat_cor(aes(label = paste(..rr.label.., sep = "~`,`~")), method="spearman", na.rm=F, label.x=.1, label.y=85, p.accuracy = 0.001) +
stat_regline_equation(label.y=75)
#One graph by location
soils_b %>%
ggplot(aes(x=x20mwd, y= nagg, color=location_b, shape=location_b))+
geom_point(size=1)+
labs(x="20 minute method (mm)",
y="NRCS Hand Method (%)",
title="Correlation between 20 Minute MWD vs NRCS") +
theme_classic()+
geom_smooth(method="lm", se=FALSE) +
theme_James() +
stat_cor(aes(color=location_b, label = paste(..rr.label.., sep = "~`,`~")), method="spearman", na.rm=F, label.x=.01, p.accuracy = 0.001, show.legend = F) +
stat_regline_equation(label.x=.5, show.legend = F)
#group by location
soils_b %>%
ggplot(aes(x=x20mwd, y= nagg))+
facet_wrap(~location_b)+
labs(x="20 Minute Method (mm)",
y="NRCS Hand Method (%)",
title="Correlation between 20 Minute MWD vs NRCS by Location") +
theme_classic()+
geom_smooth(method="lm", se=FALSE, color= "black") +
geom_point(size=.5) +
theme_James() +
stat_cor(aes(color=location_b, label = paste(..rr.label.., sep = "~`,`~")), method="spearman", na.rm=F, label.y=.01, p.accuracy = 0.001, show.legend = F) +
stat_regline_equation(label.x=.5, show.legend = F)
12.3.1 Correlation plots for group depths
#20 minute Mean Weight Diameter vs NRCS
#group by location
soils_b %>%
ggplot(aes(x=x20mwd, y= nagg, color=treatment))+
facet_wrap(~location_b)+
labs(x="20 Minute Method (mm)",
y="NRCS Hand Method (%)",
title="Correlation between 20 Minute MWD vs NRCS by Location", shape="Horizon", color="Treatment") +
scale_y_continuous(limits=c(0,100)) +
theme_classic()+
geom_point(size=2)+
theme_James2()+
stat_cor(aes(label = paste(..r.label..,..rr.label.., ..p.label.., sep = "~`,`~")), method="spearman", na.rm=F, p.accuracy = 0.001, show.legend = F)
#Has correlation by treatment by location
soils_b %>%
ggplot(aes(x=x20mwd, y= nagg, color=treatment))+
facet_wrap(~location_b)+
stat_cor(aes(label = paste(..rr.label.., sep = "~`,`~")), method="spearman", na.rm=F, p.accuracy = 0.001, show.legend = F)+ labs(x="20 Minute Method (mm)",
y="NRCS Hand Method (%)",
title="Correlation between 20 Minute MWD vs NRCS by Location", shape="Horizon", color="Treatment") +
scale_y_continuous(limits=c(0,100)) +
theme_classic()+
geom_point(size=2, aes(shape=horizon_b))+
scale_shape_manual(values=c(19, 17, 15, 3, 7, 8, 10)) +
theme_James2() +
stat_regline_equation(label.x=1.3, show.legend = F) 
ggsave("20minNRCScor.png", height=6, width=9)
#Has correlation by treatment by location and has eclipses
soils_b %>%
ggplot(aes(x=x20mwd, y= nagg, color=treatment))+
facet_wrap(~location_b)+
stat_cor(aes(label = paste(..r.label..,..rr.label.., ..p.label.., sep = "~`,`~")), method="spearman", na.rm=F, p.accuracy = 0.001, show.legend = F)+ labs(x="20 Minute Method (mm)",
y="NRCS Hand Method (%)",
title="Correlation between 20 Minute MWD vs NRCS by Location", shape="Horizon", color="Treatment") +
scale_y_continuous(limits=c(0,100)) +
theme_classic()+
geom_point(size=2, aes(shape=horizon_b), na.rm = T)+
scale_shape_manual(values=c(19, 17, 15, 3, 7, 8, 10)) +
theme_James2() +
geom_mark_ellipse(expand=0, aes(fill=treatment), show.legend = F)
12.4 NRCS and 5mwd Correlation graphs
use soils data frame and location_a and horizon_a
#NRCS vs 5 minute Method
soils %>%
ggplot(aes(x=nagg, y= x5mwd))+
geom_point(size=.5)+
labs(x="NRCS Hand Method (%)",
y="5 Minute Method (mm)",
title="Correlation between NRCS vs 5 minute MWD") +
theme_bw(base_size=12, base_family='TT Times New Roman')+
geom_smooth(method="lm", se=FALSE)+
theme(panel.grid.major = element_blank(),
panel.grid.minor = element_blank()) +
theme_James() +
stat_cor(aes(label = paste(..rr.label.., sep = "~`,`~")), method="spearman", na.rm=F, label.x=1, label.y=3.4, p.accuracy = 0.001, show.legend = F) +
stat_regline_equation(label.y=3)
#One graph by location
soils %>%
ggplot(aes(x=nagg, y= x5mwd, color=location_a, shape=location_a))+
geom_point(size=1)+
labs(x="NRCS Hand Method (%)",
y="5 Minute Method (mm)",
title="Correlation between NRCS vs 5 minute MWD") +
theme_classic()+
geom_smooth(method="lm", se=FALSE)+
theme_James() +
stat_cor(aes(color=location_a, label = paste(..rr.label.., sep = "~`,`~")), method="spearman", na.rm=F, label.x=.01, p.accuracy = 0.001, show.legend = F) +
stat_regline_equation(label.x=15, show.legend = F)
#group by location
soils %>%
ggplot(aes(x=nagg, y= x5mwd))+
facet_wrap(~location_a)+
labs(x="NRCS Hand Method (%)",
y="5 Minute Method (mm)",
title="Correlation between NRCS vs 5 minute MWD by Location") +
theme_classic()+
geom_smooth(method="lm", se=FALSE, color= "black") +
geom_point(size=.5)+
theme_James() +
stat_cor(aes(color=location_a, label = paste(..rr.label.., sep = "~`,`~")), method="spearman", na.rm=F, label.y=.01, p.accuracy = 0.001, show.legend = F) +
stat_regline_equation(label.x=.5, show.legend = F)
12.4.1 Correlation plots for group depths
#NRCS vs 5 minute Method
#group by location
soils %>%
ggplot(aes(x=nagg, y= x5mwd, color=treatment))+
facet_wrap(~location_a)+
labs(x="NRCS Hand Method (%)",
y="5 Minute Method (mm)",
title="Correlation between NRCS vs 5 minute MWD by Location", shape="Horizon", color="Treatment") +
scale_y_continuous(limits=c(0,5)) +
theme_classic()+
geom_point(size=2)+
theme_James2()+
stat_cor(aes(label = paste(..r.label..,..rr.label.., ..p.label.., sep = "~`,`~")), method="spearman", na.rm=F, p.accuracy = 0.001, show.legend = F)
#Has correlation by treatment by location
soils %>%
ggplot(aes(x=nagg, y= x5mwd, color=treatment))+
facet_wrap(~location_a)+
stat_cor(aes(label = paste(..rr.label.., sep = "~`,`~")), method="spearman", na.rm=F, p.accuracy = 0.001, show.legend = F)+ labs(x="NRCS Hand Method (%)",
y="5 Minute Method (mm)",
title="Correlation between NRCS vs 5 minute MWD by Location", shape="Horizon", color="Treatment") +
scale_y_continuous(limits=c(0,5)) +
theme_classic()+
geom_point(size=2, aes(shape=horizon_a))+
theme_James2() +
stat_regline_equation(label.x=30, show.legend = F) 
ggsave("NRCS5mincor.png", height=6, width=9)
#Has correlation by treatment by location and has eclipses
soils %>%
ggplot(aes(x=nagg, y= x5mwd, color=treatment))+
facet_wrap(~location_a)+
stat_cor(aes(label = paste(..r.label..,..rr.label.., ..p.label.., sep = "~`,`~")), method="spearman", na.rm=F, p.accuracy = 0.001, show.legend = F)+ labs(x="NRCS Hand Method (%)",
y="5 Minute Method (mm)",
title="Correlation between NRCS vs 5 minute MWD by Location", shape="Horizon", color="Treatment") +
scale_y_continuous(limits=c(0,5)) +
theme_classic()+
geom_point(size=2, aes(shape=horizon_a))+
theme_James2() +
geom_mark_ellipse(expand=0, aes(fill=treatment), show.legend = F)
12.5 MWD Bland-Altman plots
library(BlandAltmanLeh)
nrcs <-as.numeric(soils$nagg, na.rm=FALSE)
n20mwd <- as.numeric(soils$x20mwd, na.rm=FALSE)
n5mwd <- as.numeric(soils$x5mwd, na.rm=FALSE)
#Bland-Altman Plots for 20 minute Mean Weight Diameter vs NRCS Hand Method
soils %>%
ggplot(aes(x=((x20mwd+nagg)/2), y= (x20mwd-nagg)))+
geom_point(size=.5)+
labs(x="20 minute method",
y="NRCS hand method",
title="Bland-Altman Plots for 20 minute Mean Weight Diameter vs NRCS Hand Method") +
theme_classic()
bland.altman.plot(n20mwd, nrcs, xlab="Means", ylab="Differences", na.rm=FALSE)
## NULL#Bland-Altman Plots for 20 minute Mean Weight Diameter vs 5 minute Method
soils %>%
ggplot(aes(x=((x20mwd+x5mwd)/2), y= (x5mwd-x20mwd)))+
geom_point(size=.5)+
labs(x="Means",
y="Differences",
title="Bland-Altman Plots for 20 minute Mean Weight Diameter vs 5 minute Method") +
theme_classic()
bland.altman.plot(n5mwd, n20mwd, xlab="Means", ylab="Differences")
## NULLmodmwd <- lm(x5mwd ~ x20mwd, data=soils)
summary(modmwd)##
## Call:
## lm(formula = x5mwd ~ x20mwd, data = soils)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.80182 -0.29896 -0.05003 0.25248 1.69542
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.47598 0.08690 5.477 1.97e-07 ***
## x20mwd 0.77398 0.07955 9.730 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.5386 on 139 degrees of freedom
## Multiple R-squared: 0.4051, Adjusted R-squared: 0.4009
## F-statistic: 94.67 on 1 and 139 DF, p-value: < 2.2e-1612.5.1 Correlation plots for group depths
#20 minute Mean Weight Diameter vs 5 minute Method
#group by location
soils %>%
ggplot(aes(x=x20mwd, y= x5mwd, color=treatment))+
facet_wrap(~location_a)+
labs(x="20 Minute Method (mm)",
y="5 Minute Method (mm)",
title="Correlation between 20 vs 5 minute MWD by Location", shape="Horizon", color="Treatment") +
scale_y_continuous(limits=c(0,5)) +
theme_classic()+
geom_point(size=2)+
theme_James2()+
stat_cor(aes(label = paste(..r.label..,..rr.label.., ..p.label.., sep = "~`,`~")), method="spearman", na.rm=F, p.accuracy = 0.001, show.legend = F)
#Has correlation by treatment by location
soils %>%
ggplot(aes(x=x20mwd, y= x5mwd, color=treatment))+
facet_wrap(~location_a)+
stat_cor(aes(label = paste(..r.label..,..rr.label.., ..p.label.., sep = "~`,`~")), method="spearman", na.rm=F, p.accuracy = 0.001, show.legend = F)+ labs(x="20 Minute Method (mm)",
y="5 Minute Method (mm)",
title="Correlation between 20 vs 5 minute MWD by Location", shape="Horizon", color="Treatment") +
scale_y_continuous(limits=c(0,5)) +
theme_classic()+
geom_point(size=2, aes(shape=horizon_a))+
theme_James2()
#Has correlation by treatment by location and has eclipses
soils %>%
ggplot(aes(x=x20mwd, y= x5mwd, color=treatment))+
facet_wrap(~location_a)+
stat_cor(aes(label = paste(..r.label..,..rr.label.., ..p.label.., sep = "~`,`~")), method="spearman", na.rm=F, p.accuracy = 0.001, show.legend = F)+ labs(x="20 Minute Method (mm)",
y="5 Minute Method (mm)",
title="Correlation between 20 vs 5 minute MWD by Location", shape="Horizon", color="Treatment") +
scale_y_continuous(limits=c(0,5)) +
theme_classic()+
geom_point(size=2, aes(shape=horizon_a))+
theme_James2() +
geom_mark_ellipse(expand=0, aes(fill=treatment), show.legend = F)
1.6 Comments
#Shapiro Wilks test