#LIBRERIAS
library(agricolae)
## Warning: package 'agricolae' was built under R version 4.4.1
library(collapsibleTree)
library(dplyr)
##
## Adjuntando el paquete: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library(ggplot2)
library(lattice)
library(readxl)
FisioPro <- read_excel("C:/Users/Brandon S/Downloads/FisioPro.xlsx",
sheet = "15 Días", col_types = c("text",
"text", "text", "numeric", "numeric",
"numeric", "numeric", "numeric"))
View(FisioPro)
FisioPro
## # A tibble: 210 × 8
## muestreo trat rep hojas flores clor area diam
## <chr> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 1 1 1 16.5 1 69.8 110. 0
## 2 1 1 2 21.5 4.5 76.7 108. 0
## 3 1 1 3 15 4.5 50.1 84.1 0
## 4 1 1 4 20.5 9.5 53.4 111. 0
## 5 1 1 5 11.5 4.5 51.0 79.7 0
## 6 1 1 6 16.5 5 53.6 83.3 0
## 7 1 2 1 18.5 10 65.2 90.8 0
## 8 1 2 2 14 4.5 60.6 95.1 0
## 9 1 2 3 11 5 79.8 148. 0
## 10 1 2 4 10.5 6.5 84.2 139. 0
## # ℹ 200 more rows
#MUESTREOS CON DATOS DE ARANDANOS "DÍA 15" EXCEL.
M1 = FisioPro[1:42,]; M1
## # A tibble: 42 × 8
## muestreo trat rep hojas flores clor area diam
## <chr> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 1 1 1 16.5 1 69.8 110. 0
## 2 1 1 2 21.5 4.5 76.7 108. 0
## 3 1 1 3 15 4.5 50.1 84.1 0
## 4 1 1 4 20.5 9.5 53.4 111. 0
## 5 1 1 5 11.5 4.5 51.0 79.7 0
## 6 1 1 6 16.5 5 53.6 83.3 0
## 7 1 2 1 18.5 10 65.2 90.8 0
## 8 1 2 2 14 4.5 60.6 95.1 0
## 9 1 2 3 11 5 79.8 148. 0
## 10 1 2 4 10.5 6.5 84.2 139. 0
## # ℹ 32 more rows
M2 = FisioPro[43:84,]; M2
## # A tibble: 42 × 8
## muestreo trat rep hojas flores clor area diam
## <chr> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 2 1 1 17.6 1.5 35.8 132. 0
## 2 2 1 2 20.5 10 55.9 157. 0
## 3 2 1 3 19 5 42.6 38.3 0
## 4 2 1 4 20.5 9 35.4 139 0
## 5 2 1 5 11.5 4.5 47.2 32.1 0
## 6 2 1 6 16.5 4 54.2 78.0 0
## 7 2 2 1 23 14.5 40.1 62.8 0
## 8 2 2 2 13.5 9 42.8 54.2 0
## 9 2 2 3 12.5 6.5 29.5 237. 0
## 10 2 2 4 10.5 5.5 56 261. 0
## # ℹ 32 more rows
M3 = FisioPro[85:126,]; M3
## # A tibble: 42 × 8
## muestreo trat rep hojas flores clor area diam
## <chr> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 3 1 1 17 9 47.1 112. 7.8
## 2 3 1 2 19.5 12.5 60.8 163. 0
## 3 3 1 3 20 10.5 50.2 86.4 10
## 4 3 1 4 21.5 9 43.4 113. 0
## 5 3 1 5 11.5 4.5 42.1 56.6 0
## 6 3 1 6 17 9 54.6 84.4 0
## 7 3 2 1 28 18.5 40.6 80.4 9.5
## 8 3 2 2 14 7.5 51.2 81.7 0
## 9 3 2 3 14 6.5 32.6 164. 7
## 10 3 2 4 10.5 7 59.6 178. 0
## # ℹ 32 more rows
# M4 = FisioPro[1:42,]; M4 #NO SE ENCEUNTRAN EN EL EXCEL#
M5 = FisioPro[127:168,]; M5
## # A tibble: 42 × 8
## muestreo trat rep hojas flores clor area diam
## <chr> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 5 1 1 17 1 57.8 92.9 NA
## 2 5 1 2 21.5 13 50.1 168. NA
## 3 5 1 3 22.5 4.5 49.8 135. NA
## 4 5 1 4 23 9 41.3 86.8 NA
## 5 5 1 5 15.5 4 53.4 81.1 NA
## 6 5 1 6 18 6 57.2 90.8 NA
## 7 5 2 1 28.5 10.5 40.4 97.9 NA
## 8 5 2 2 16 5 62.8 109. NA
## 9 5 2 3 15 5.5 44 91.2 NA
## 10 5 2 4 6.5 6.5 61.8 94.9 NA
## # ℹ 32 more rows
# M6 = FisioPro[1:42,]; M6 #NO SE ENCEUNTRAN EN EL EXCEL#
M7 = FisioPro[169:210,]; M7
## # A tibble: 42 × 8
## muestreo trat rep hojas flores clor area diam
## <chr> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 7 1 1 16.5 4.5 53.1 22.6 NA
## 2 7 1 2 19.5 12 55.9 27.1 NA
## 3 7 1 3 18.5 8 50.3 10.3 NA
## 4 7 1 4 23 6.5 62.1 22.4 NA
## 5 7 1 5 10 3 60.4 24.8 NA
## 6 7 1 6 13 6 60.2 24 NA
## 7 7 2 1 22 7 55.2 24.2 NA
## 8 7 2 2 12 4 67 13.2 NA
## 9 7 2 3 14 5.5 54.7 17.0 NA
## 10 7 2 4 9 4.5 69.2 16.7 NA
## # ℹ 32 more rows
#ANÁLISIS DESCRIPTIVO
# NUMERO DE HOJAS
#MUESTREO 1
boxplot(hojas~trat, data=M1)
mod1=aov(hojas~trat, data=M1);mod1
## Call:
## aov(formula = hojas ~ trat, data = M1)
##
## Terms:
## trat Residuals
## Sum of Squares 189.7024 371.5417
## Deg. of Freedom 6 35
##
## Residual standard error: 3.25814
## Estimated effects may be unbalanced
anova(mod1)
## Analysis of Variance Table
##
## Response: hojas
## Df Sum Sq Mean Sq F value Pr(>F)
## trat 6 189.70 31.617 2.9784 0.01862 *
## Residuals 35 371.54 10.616
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Tt=TukeyHSD(mod1)
a=duncan.test(mod1, "trat", console=T)
##
## Study: mod1 ~ "trat"
##
## Duncan's new multiple range test
## for hojas
##
## Mean Square Error: 10.61548
##
## trat, means
##
## hojas std r se Min Max Q25 Q50 Q75
## 1 16.91667 3.666288 6 1.33013 11.5 21.5 15.375 16.50 19.500
## 2 14.58333 3.307819 6 1.33013 10.5 18.5 11.750 15.25 16.875
## 3 14.75000 3.921097 6 1.33013 10.0 19.0 11.250 15.75 17.625
## 4 14.83333 2.503331 6 1.33013 10.0 17.0 14.750 15.75 16.000
## 5 12.75000 4.192255 6 1.33013 8.0 20.5 11.000 12.50 12.500
## 6 10.08333 2.311205 6 1.33013 7.5 13.0 8.000 10.25 11.750
## 7 11.66667 2.316607 6 1.33013 9.0 15.0 9.875 11.50 13.125
##
## Alpha: 0.05 ; DF Error: 35
##
## Critical Range
## 2 3 4 5 6 7
## 3.818812 4.014414 4.141878 4.233379 4.302886 4.357681
##
## Means with the same letter are not significantly different.
##
## hojas groups
## 1 16.91667 a
## 4 14.83333 ab
## 3 14.75000 ab
## 2 14.58333 ab
## 5 12.75000 abc
## 7 11.66667 bc
## 6 10.08333 c
plot(a)
#MUESTREO 2
boxplot(hojas~trat, data=M2)
mod2=aov(hojas~trat, data=M2);mod2
## Call:
## aov(formula = hojas ~ trat, data = M2)
##
## Terms:
## trat Residuals
## Sum of Squares 179.0133 445.9917
## Deg. of Freedom 6 35
##
## Residual standard error: 3.569681
## Estimated effects may be unbalanced
anova(mod2)
## Analysis of Variance Table
##
## Response: hojas
## Df Sum Sq Mean Sq F value Pr(>F)
## trat 6 179.01 29.836 2.3414 0.05256 .
## Residuals 35 445.99 12.743
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Tt=TukeyHSD(mod2)
b=duncan.test(mod1, "trat", console=T)
##
## Study: mod1 ~ "trat"
##
## Duncan's new multiple range test
## for hojas
##
## Mean Square Error: 10.61548
##
## trat, means
##
## hojas std r se Min Max Q25 Q50 Q75
## 1 16.91667 3.666288 6 1.33013 11.5 21.5 15.375 16.50 19.500
## 2 14.58333 3.307819 6 1.33013 10.5 18.5 11.750 15.25 16.875
## 3 14.75000 3.921097 6 1.33013 10.0 19.0 11.250 15.75 17.625
## 4 14.83333 2.503331 6 1.33013 10.0 17.0 14.750 15.75 16.000
## 5 12.75000 4.192255 6 1.33013 8.0 20.5 11.000 12.50 12.500
## 6 10.08333 2.311205 6 1.33013 7.5 13.0 8.000 10.25 11.750
## 7 11.66667 2.316607 6 1.33013 9.0 15.0 9.875 11.50 13.125
##
## Alpha: 0.05 ; DF Error: 35
##
## Critical Range
## 2 3 4 5 6 7
## 3.818812 4.014414 4.141878 4.233379 4.302886 4.357681
##
## Means with the same letter are not significantly different.
##
## hojas groups
## 1 16.91667 a
## 4 14.83333 ab
## 3 14.75000 ab
## 2 14.58333 ab
## 5 12.75000 abc
## 7 11.66667 bc
## 6 10.08333 c
plot(b)
#MUESTREO 3
boxplot(hojas~trat, data=M3)
mod3=aov(hojas~trat, data=M3);mod3
## Call:
## aov(formula = hojas ~ trat, data = M3)
##
## Terms:
## trat Residuals
## Sum of Squares 191.1429 755.3333
## Deg. of Freedom 6 35
##
## Residual standard error: 4.64553
## Estimated effects may be unbalanced
anova(mod3)
## Analysis of Variance Table
##
## Response: hojas
## Df Sum Sq Mean Sq F value Pr(>F)
## trat 6 191.14 31.857 1.4762 0.2149
## Residuals 35 755.33 21.581
Tt=TukeyHSD(mod3)
c=duncan.test(mod3, "trat", console=T)
##
## Study: mod3 ~ "trat"
##
## Duncan's new multiple range test
## for hojas
##
## Mean Square Error: 21.58095
##
## trat, means
##
## hojas std r se Min Max Q25 Q50 Q75
## 1 17.75000 3.531997 6 1.89653 11.5 21.5 17.000 18.25 19.875
## 2 16.66667 6.013873 6 1.89653 10.5 28.0 14.000 15.25 16.875
## 3 15.16667 4.273952 6 1.89653 10.0 19.5 11.250 16.50 18.375
## 4 16.25000 1.695582 6 1.89653 13.5 18.0 15.375 16.75 17.375
## 5 16.25000 5.972855 6 1.89653 8.0 24.5 12.375 17.00 19.375
## 6 10.58333 3.555512 6 1.89653 6.0 16.5 9.500 9.50 11.750
## 7 15.66667 5.741661 6 1.89653 10.0 24.5 11.250 14.25 19.125
##
## Alpha: 0.05 ; DF Error: 35
##
## Critical Range
## 2 3 4 5 6 7
## 5.444949 5.723843 5.905585 6.036048 6.135153 6.213280
##
## Means with the same letter are not significantly different.
##
## hojas groups
## 1 17.75000 a
## 2 16.66667 ab
## 4 16.25000 ab
## 5 16.25000 ab
## 7 15.66667 ab
## 3 15.16667 ab
## 6 10.58333 b
plot(c)
#MUESTREO 5
boxplot(hojas~trat, data=M5)
mod5=aov(hojas~trat, data=M5);mod5
## Call:
## aov(formula = hojas ~ trat, data = M5)
##
## Terms:
## trat Residuals
## Sum of Squares 188.500 1461.958
## Deg. of Freedom 6 35
##
## Residual standard error: 6.46299
## Estimated effects may be unbalanced
anova(mod5)
## Analysis of Variance Table
##
## Response: hojas
## Df Sum Sq Mean Sq F value Pr(>F)
## trat 6 188.5 31.417 0.7521 0.612
## Residuals 35 1462.0 41.770
Tt=TukeyHSD(mod5)
d=duncan.test(mod1, "trat", console=T)
##
## Study: mod1 ~ "trat"
##
## Duncan's new multiple range test
## for hojas
##
## Mean Square Error: 10.61548
##
## trat, means
##
## hojas std r se Min Max Q25 Q50 Q75
## 1 16.91667 3.666288 6 1.33013 11.5 21.5 15.375 16.50 19.500
## 2 14.58333 3.307819 6 1.33013 10.5 18.5 11.750 15.25 16.875
## 3 14.75000 3.921097 6 1.33013 10.0 19.0 11.250 15.75 17.625
## 4 14.83333 2.503331 6 1.33013 10.0 17.0 14.750 15.75 16.000
## 5 12.75000 4.192255 6 1.33013 8.0 20.5 11.000 12.50 12.500
## 6 10.08333 2.311205 6 1.33013 7.5 13.0 8.000 10.25 11.750
## 7 11.66667 2.316607 6 1.33013 9.0 15.0 9.875 11.50 13.125
##
## Alpha: 0.05 ; DF Error: 35
##
## Critical Range
## 2 3 4 5 6 7
## 3.818812 4.014414 4.141878 4.233379 4.302886 4.357681
##
## Means with the same letter are not significantly different.
##
## hojas groups
## 1 16.91667 a
## 4 14.83333 ab
## 3 14.75000 ab
## 2 14.58333 ab
## 5 12.75000 abc
## 7 11.66667 bc
## 6 10.08333 c
plot(d)
#MUESTREO 7
boxplot(hojas~trat, data=M7)
mod7=aov(hojas~trat, data=M7);mod7
## Call:
## aov(formula = hojas ~ trat, data = M7)
##
## Terms:
## trat Residuals
## Sum of Squares 173.9524 723.7917
## Deg. of Freedom 6 35
##
## Residual standard error: 4.547501
## Estimated effects may be unbalanced
anova(mod7)
## Analysis of Variance Table
##
## Response: hojas
## Df Sum Sq Mean Sq F value Pr(>F)
## trat 6 173.95 28.992 1.402 0.2415
## Residuals 35 723.79 20.680
Tt=TukeyHSD(mod7)
e=duncan.test(mod7, "trat", console=T)
##
## Study: mod7 ~ "trat"
##
## Duncan's new multiple range test
## for hojas
##
## Mean Square Error: 20.67976
##
## trat, means
##
## hojas std r se Min Max Q25 Q50 Q75
## 1 16.75000 4.677072 6 1.856509 10.0 23.0 13.875 17.50 19.250
## 2 13.91667 4.340699 6 1.856509 9.0 22.0 12.250 13.25 13.875
## 3 12.16667 5.335416 6 1.856509 6.5 21.0 8.625 11.00 14.500
## 4 15.16667 1.437591 6 1.856509 13.0 16.5 14.250 15.50 16.375
## 5 14.66667 6.470446 6 1.856509 7.0 22.5 10.750 12.75 20.375
## 6 10.16667 3.600926 6 1.856509 6.5 17.0 8.625 9.25 10.250
## 7 15.25000 4.321458 6 1.856509 10.5 21.0 11.750 14.75 18.500
##
## Alpha: 0.05 ; DF Error: 35
##
## Critical Range
## 2 3 4 5 6 7
## 5.330050 5.603059 5.780965 5.908676 6.005690 6.082168
##
## Means with the same letter are not significantly different.
##
## hojas groups
## 1 16.75000 a
## 7 15.25000 ab
## 4 15.16667 ab
## 5 14.66667 ab
## 2 13.91667 ab
## 3 12.16667 ab
## 6 10.16667 b
plot(e)
#comparación muestreos del N_hojas
par(mfcol= c(3,2))
plot(a, main = "M1"); plot(b, main = "M2"); plot(c, main = "M3");plot(d, main = "M5"); plot(e, main = "M7")
FisioPro
## # A tibble: 210 × 8
## muestreo trat rep hojas flores clor area diam
## <chr> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 1 1 1 16.5 1 69.8 110. 0
## 2 1 1 2 21.5 4.5 76.7 108. 0
## 3 1 1 3 15 4.5 50.1 84.1 0
## 4 1 1 4 20.5 9.5 53.4 111. 0
## 5 1 1 5 11.5 4.5 51.0 79.7 0
## 6 1 1 6 16.5 5 53.6 83.3 0
## 7 1 2 1 18.5 10 65.2 90.8 0
## 8 1 2 2 14 4.5 60.6 95.1 0
## 9 1 2 3 11 5 79.8 148. 0
## 10 1 2 4 10.5 6.5 84.2 139. 0
## # ℹ 200 more rows
dats <- FisioPro %>%
group_by(muestreo,trat) %>%
summarise(media = mean(hojas),
desviacion = sd(hojas),
n = n()) %>%
mutate(error = 1.96 * desviacion / sqrt(n));dats
## `summarise()` has grouped output by 'muestreo'. You can override using the
## `.groups` argument.
## # A tibble: 35 × 6
## # Groups: muestreo [5]
## muestreo trat media desviacion n error
## <chr> <chr> <dbl> <dbl> <int> <dbl>
## 1 1 1 16.9 3.67 6 2.93
## 2 1 2 14.6 3.31 6 2.65
## 3 1 3 14.8 3.92 6 3.14
## 4 1 4 14.8 2.50 6 2.00
## 5 1 5 12.8 4.19 6 3.35
## 6 1 6 10.1 2.31 6 1.85
## 7 1 7 11.7 2.32 6 1.85
## 8 2 1 17.6 3.38 6 2.71
## 9 2 2 15.4 4.40 6 3.52
## 10 2 3 14.6 4.20 6 3.36
## # ℹ 25 more rows
dats$muestreo <- factor(dats$muestreo, labels = c("M1","M2","M3","M5","M7"))
dats$trat <- factor(dats$trat, labels = c("T_1", "T_2", "T_3", "T_4","T_5","T_6", "T_7"))
labels <- c("T_1", "T_2", "T_3", "T_4","T_5","T_6","T_7")
ggplot(dats)+
aes(x=dats$trat, y = media, fill=dats$trat)+
geom_col(strat = 'identity', position = 'dodge', color = 'black')+
geom_errorbar(aes(ymin = media - error, ymax = media + error),
width = 0.2, position = position_dodge(0.9))+
geom_text(aes(label = c("b","b","a","a","b","b","c",
"b","b","a","a","b","b","c",
"b","b","a","a","b","b","c",
"b","b","a","a","b","b","c",
"b","b","a","a","b","b","c")
, y = media+ 0.23), color = 'black', size = 4) +
facet_grid(~dats$muestreo)+
labs(title = "Número de hojas por tratamientos en los muestreos", x = "Muestreos", y = "#hojas")+
theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust = 1, size = 7))+
scale_fill_manual(values = c("#98F5FF", "#C1CDCD", "#CDCD00", "#FFD39B","#FF7F24", "#BF3EFF", "#9AFF9A"))+
scale_x_discrete(labels = labels)+
theme_bw()
## Warning in geom_col(strat = "identity", position = "dodge", color = "black"):
## Ignoring unknown parameters: `strat`
#ANALISIS DESCRIPTIVO
#NUMERO DE FLORES
#MUESTREO 1
boxplot(flores~trat, data=M1)
mod1f=aov(flores~trat, data=M1);mod1f
## Call:
## aov(formula = flores ~ trat, data = M1)
##
## Terms:
## trat Residuals
## Sum of Squares 60.33333 203.50000
## Deg. of Freedom 6 35
##
## Residual standard error: 2.411283
## Estimated effects may be unbalanced
anova(mod1f)
## Analysis of Variance Table
##
## Response: flores
## Df Sum Sq Mean Sq F value Pr(>F)
## trat 6 60.333 10.0556 1.7295 0.1432
## Residuals 35 203.500 5.8143
Tt=TukeyHSD(mod1f)
f=duncan.test(mod1f, "trat", console=T)
##
## Study: mod1f ~ "trat"
##
## Duncan's new multiple range test
## for flores
##
## Mean Square Error: 5.814286
##
## trat, means
##
## flores std r se Min Max Q25 Q50 Q75
## 1 4.833333 2.7141604 6 0.9844022 1.0 9.5 4.500 4.50 4.875
## 2 6.916667 2.3112046 6 0.9844022 4.5 10.0 5.250 6.25 8.750
## 3 4.416667 2.5182666 6 0.9844022 0.0 7.5 4.000 4.75 5.500
## 4 5.916667 2.0103897 6 0.9844022 4.0 9.0 4.250 5.50 7.125
## 5 3.000000 3.3615473 6 0.9844022 0.0 7.0 0.125 2.00 6.125
## 6 4.916667 0.8612007 6 0.9844022 4.0 6.0 4.125 5.00 5.500
## 7 3.833333 2.3593784 6 0.9844022 0.0 6.5 2.750 4.25 5.375
##
## Alpha: 0.05 ; DF Error: 35
##
## Critical Range
## 2 3 4 5 6 7
## 2.826225 2.970986 3.065320 3.133037 3.184478 3.225031
##
## Means with the same letter are not significantly different.
##
## flores groups
## 2 6.916667 a
## 4 5.916667 ab
## 6 4.916667 ab
## 1 4.833333 ab
## 3 4.416667 ab
## 7 3.833333 ab
## 5 3.000000 b
plot(f)
#MUESTREO 2
boxplot(flores~trat, data=M2)
mod2f=aov(flores~trat, data=M2);mod2f
## Call:
## aov(formula = flores ~ trat, data = M2)
##
## Terms:
## trat Residuals
## Sum of Squares 69.6667 316.2917
## Deg. of Freedom 6 35
##
## Residual standard error: 3.006145
## Estimated effects may be unbalanced
anova(mod2f)
## Analysis of Variance Table
##
## Response: flores
## Df Sum Sq Mean Sq F value Pr(>F)
## trat 6 69.67 11.6111 1.2849 0.2896
## Residuals 35 316.29 9.0369
Tt=TukeyHSD(mod2f)
g=duncan.test(mod2f, "trat", console=T)
##
## Study: mod2f ~ "trat"
##
## Duncan's new multiple range test
## for flores
##
## Mean Square Error: 9.036905
##
## trat, means
##
## flores std r se Min Max Q25 Q50 Q75
## 1 5.666667 3.219731 6 1.227253 1.5 10.0 4.125 4.75 8.000
## 2 7.916667 3.583527 6 1.227253 4.5 14.5 5.750 7.00 8.625
## 3 6.250000 2.962263 6 1.227253 3.0 9.5 3.750 6.00 9.000
## 4 7.333333 1.861899 6 1.227253 6.0 11.0 6.500 6.50 7.250
## 5 3.833333 3.920034 6 1.227253 0.0 10.5 1.625 2.25 5.500
## 6 6.583333 3.322900 6 1.227253 4.0 13.0 4.625 5.50 6.750
## 7 5.000000 1.183216 6 1.227253 3.5 6.0 4.000 5.50 5.875
##
## Alpha: 0.05 ; DF Error: 35
##
## Critical Range
## 2 3 4 5 6 7
## 3.523452 3.703926 3.821532 3.905955 3.970087 4.020643
##
## Means with the same letter are not significantly different.
##
## flores groups
## 2 7.916667 a
## 4 7.333333 ab
## 6 6.583333 ab
## 3 6.250000 ab
## 1 5.666667 ab
## 7 5.000000 ab
## 5 3.833333 b
plot(g)
#MUESTREO 3
boxplot(flores~trat, data=M3)
mod3f=aov(flores~trat, data=M3);mod3f
## Call:
## aov(formula = flores ~ trat, data = M3)
##
## Terms:
## trat Residuals
## Sum of Squares 68.5595 425.0417
## Deg. of Freedom 6 35
##
## Residual standard error: 3.484831
## Estimated effects may be unbalanced
anova(mod3f)
## Analysis of Variance Table
##
## Response: flores
## Df Sum Sq Mean Sq F value Pr(>F)
## trat 6 68.56 11.427 0.9409 0.4786
## Residuals 35 425.04 12.144
Tt=TukeyHSD(mod3f)
h=duncan.test(mod3f, "trat", console=T)
##
## Study: mod3f ~ "trat"
##
## Duncan's new multiple range test
## for flores
##
## Mean Square Error: 12.14405
##
## trat, means
##
## flores std r se Min Max Q25 Q50 Q75
## 1 9.083333 2.634704 6 1.422676 4.5 12.5 9.000 9.00 10.125
## 2 9.416667 4.565267 6 1.422676 6.5 18.5 7.125 7.50 9.000
## 3 8.416667 3.760541 6 1.422676 3.5 13.0 5.625 9.00 10.875
## 4 9.333333 4.377975 6 1.422676 6.0 18.0 7.125 8.00 8.875
## 5 5.583333 2.200379 6 1.422676 2.0 8.5 5.000 5.50 6.750
## 6 8.500000 4.135215 6 1.422676 4.5 16.5 6.750 7.75 8.000
## 7 7.250000 1.405347 6 1.422676 5.0 9.0 6.625 7.50 8.000
##
## Alpha: 0.05 ; DF Error: 35
##
## Critical Range
## 2 3 4 5 6 7
## 4.084513 4.293724 4.430057 4.527924 4.602267 4.660874
##
## Means with the same letter are not significantly different.
##
## flores groups
## 2 9.416667 a
## 4 9.333333 a
## 1 9.083333 a
## 6 8.500000 a
## 3 8.416667 a
## 7 7.250000 a
## 5 5.583333 a
plot(h)
#MUESTREO 5
boxplot(flores~trat, data=M5)
mod5f=aov(flores~trat, data=M5);mod5f
## Call:
## aov(formula = flores ~ trat, data = M5)
##
## Terms:
## trat Residuals
## Sum of Squares 81.11905 281.50000
## Deg. of Freedom 6 35
##
## Residual standard error: 2.835993
## Estimated effects may be unbalanced
anova(mod5f)
## Analysis of Variance Table
##
## Response: flores
## Df Sum Sq Mean Sq F value Pr(>F)
## trat 6 81.119 13.5198 1.681 0.1549
## Residuals 35 281.500 8.0429
Tt=TukeyHSD(mod5f)
i=duncan.test(mod5f, "trat", console=T)
##
## Study: mod5f ~ "trat"
##
## Duncan's new multiple range test
## for flores
##
## Mean Square Error: 8.042857
##
## trat, means
##
## flores std r se Min Max Q25 Q50 Q75
## 1 6.250000 4.216041 6 1.157789 1 13.0 4.125 5.25 8.250
## 2 6.833333 2.089657 6 1.157789 5 10.5 5.500 6.00 7.625
## 3 6.500000 3.098387 6 1.157789 4 11.0 4.000 5.25 8.750
## 4 8.750000 2.583602 6 1.157789 6 13.0 7.125 8.00 10.000
## 5 3.833333 2.804758 6 1.157789 0 8.0 2.125 4.25 4.875
## 6 6.416667 2.375219 6 1.157789 4 10.0 4.375 6.25 7.750
## 7 5.250000 2.091650 6 1.157789 2 8.0 4.250 5.50 6.375
##
## Alpha: 0.05 ; DF Error: 35
##
## Critical Range
## 2 3 4 5 6 7
## 3.324020 3.494279 3.605228 3.684873 3.745375 3.793070
##
## Means with the same letter are not significantly different.
##
## flores groups
## 4 8.750000 a
## 2 6.833333 ab
## 3 6.500000 ab
## 6 6.416667 ab
## 1 6.250000 ab
## 7 5.250000 ab
## 5 3.833333 b
plot(i)
#MUESTREO 7
boxplot(flores~trat, data=M7)
mod7f=aov(flores~trat, data=M7);mod7f
## Call:
## aov(formula = flores ~ trat, data = M7)
##
## Terms:
## trat Residuals
## Sum of Squares 59.0714 347.9583
## Deg. of Freedom 6 35
##
## Residual standard error: 3.153041
## Estimated effects may be unbalanced
anova(mod7f)
## Analysis of Variance Table
##
## Response: flores
## Df Sum Sq Mean Sq F value Pr(>F)
## trat 6 59.07 9.8452 0.9903 0.4469
## Residuals 35 347.96 9.9417
Tt=TukeyHSD(mod7f)
j=duncan.test(mod7f, "trat", console=T)
##
## Study: mod7f ~ "trat"
##
## Duncan's new multiple range test
## for flores
##
## Mean Square Error: 9.941667
##
## trat, means
##
## flores std r se Min Max Q25 Q50 Q75
## 1 6.666667 3.125167 6 1.287224 3.0 12.0 4.875 6.25 7.625
## 2 5.000000 1.140175 6 1.287224 4.0 7.0 4.125 4.75 5.375
## 3 6.750000 4.546977 6 1.287224 1.0 12.5 3.625 6.50 10.125
## 4 7.000000 2.280351 6 1.287224 5.0 10.0 5.000 6.50 8.750
## 5 4.250000 2.995830 6 1.287224 2.0 9.0 2.125 2.75 6.000
## 6 8.000000 4.147288 6 1.287224 4.0 14.5 5.000 6.75 10.375
## 7 5.750000 2.544602 6 1.287224 2.5 10.0 4.375 5.75 6.375
##
## Alpha: 0.05 ; DF Error: 35
##
## Critical Range
## 2 3 4 5 6 7
## 3.695627 3.884920 4.008272 4.096821 4.164086 4.217113
##
## Means with the same letter are not significantly different.
##
## flores groups
## 6 8.000000 a
## 4 7.000000 a
## 3 6.750000 a
## 1 6.666667 a
## 7 5.750000 a
## 2 5.000000 a
## 5 4.250000 a
plot(j)
#comparación muestreos del N_flores
par(mfcol= c(3,2))
plot(f, main = "M1"); plot(g, main = "M2"); plot(h, main = "M3");plot(i, main = "M5"); plot(j, main = "M7")
dats
## # A tibble: 35 × 6
## # Groups: muestreo [5]
## muestreo trat media desviacion n error
## <fct> <fct> <dbl> <dbl> <int> <dbl>
## 1 M1 T_1 16.9 3.67 6 2.93
## 2 M1 T_2 14.6 3.31 6 2.65
## 3 M1 T_3 14.8 3.92 6 3.14
## 4 M1 T_4 14.8 2.50 6 2.00
## 5 M1 T_5 12.8 4.19 6 3.35
## 6 M1 T_6 10.1 2.31 6 1.85
## 7 M1 T_7 11.7 2.32 6 1.85
## 8 M2 T_1 17.6 3.38 6 2.71
## 9 M2 T_2 15.4 4.40 6 3.52
## 10 M2 T_3 14.6 4.20 6 3.36
## # ℹ 25 more rows
dats <- FisioPro %>%
group_by(muestreo,trat) %>%
summarise(media = mean(flores),
desviacion = sd(flores),
n = n()) %>%
mutate(error = 1.96 * desviacion / sqrt(n));dats
## `summarise()` has grouped output by 'muestreo'. You can override using the
## `.groups` argument.
## # A tibble: 35 × 6
## # Groups: muestreo [5]
## muestreo trat media desviacion n error
## <chr> <chr> <dbl> <dbl> <int> <dbl>
## 1 1 1 4.83 2.71 6 2.17
## 2 1 2 6.92 2.31 6 1.85
## 3 1 3 4.42 2.52 6 2.02
## 4 1 4 5.92 2.01 6 1.61
## 5 1 5 3 3.36 6 2.69
## 6 1 6 4.92 0.861 6 0.689
## 7 1 7 3.83 2.36 6 1.89
## 8 2 1 5.67 3.22 6 2.58
## 9 2 2 7.92 3.58 6 2.87
## 10 2 3 6.25 2.96 6 2.37
## # ℹ 25 more rows
dats$muestreo <- factor(dats$muestreo, labels = c("M1","M2","M3","M5","M7"))
dats$trat <- factor(dats$trat, labels = c("T_1", "T_2", "T_3", "T_4","T_5","T_6", "T_7"))
labels <- c("T_1", "T_2", "T_3", "T_4","T_5","T_6","T_7")
ggplot(dats)+
aes(x=dats$trat, y = media, fill=dats$trat)+
geom_col(strat = 'identity', position = 'dodge', color = 'black')+
geom_errorbar(aes(ymin = media - error, ymax = media + error),
width = 0.2, position = position_dodge(0.9))+
geom_text(aes(label = c("b","b","a","a","b","b","c",
"b","b","a","a","b","b","c",
"b","b","a","a","b","b","c",
"b","b","a","a","b","b","c",
"b","b","a","a","b","b","c")
, y = media+ 0.23), color = 'black', size = 4) +
facet_grid(~dats$muestreo)+
theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust = 1, size = 7))+
scale_fill_manual(values = c("#98F5FF", "#C1CDCD", "#CDCD00", "#FFD39B","#FF7F24", "#BF3EFF", "#9AFF9A"))+
scale_x_discrete(labels = labels)+
theme_bw()
## Warning in geom_col(strat = "identity", position = "dodge", color = "black"):
## Ignoring unknown parameters: `strat`
