Two-way ANOVA From Chapter 6

#Call Packages
library(ggplot2)
library(dplyr)
## 
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
## 
##     filter, lag
## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union
library(lubridate)
## 
## Attaching package: 'lubridate'
## The following objects are masked from 'package:base':
## 
##     date, intersect, setdiff, union
library(ggfortify)

#Read csv file
growth.moo <- read.csv("C:/Users/samhe/OneDrive/Documents/Bio 4259/Bio4259_Labs/data/growth.csv")

#Check if imported correctly
glimpse(growth.moo)
## Rows: 48
## Columns: 3
## $ supplement <chr> "supergain", "supergain", "supergain", "supergain", "contro…
## $ diet       <chr> "wheat", "wheat", "wheat", "wheat", "wheat", "wheat", "whea…
## $ gain       <dbl> 17.37125, 16.81489, 18.08184, 15.78175, 17.70656, 18.22717,…
#Converts diet/supplement into factors
growth.moo$diet <- as.factor(growth.moo$diet)
growth.moo$supplement <- as.factor(growth.moo$supplement)

##See levels associated with a factor ($ grab column we want info)
levels(growth.moo$diet)
## [1] "barley" "oats"   "wheat"
levels(growth.moo$supplement)
## [1] "agrimore"  "control"   "supergain" "supersupp"
#Relevel (creates new referecen lvl by reordering) supplement column
growth.moo <-
  mutate(growth.moo,
         supplement = relevel(supplement, ref="control"))

#Check if it works
levels(growth.moo$supplement)
## [1] "control"   "agrimore"  "supergain" "supersupp"
#Calculate mean and sd of gain for all 12 combinations
sumMoo <- growth.moo %>%
  group_by(diet, supplement) %>%
    summarise(meanGrow = mean(gain))
## `summarise()` has regrouped the output.
## ℹ Summaries were computed grouped by diet and supplement.
## ℹ Output is grouped by diet.
## ℹ Use `summarise(.groups = "drop_last")` to silence this message.
## ℹ Use `summarise(.by = c(diet, supplement))` for per-operation grouping
##   (`?dplyr::dplyr_by`) instead.
#Check if it works
sumMoo
## # A tibble: 12 × 3
## # Groups:   diet [3]
##    diet   supplement meanGrow
##    <fct>  <fct>         <dbl>
##  1 barley control        23.3
##  2 barley agrimore       26.3
##  3 barley supergain      22.5
##  4 barley supersupp      25.6
##  5 oats   control        20.5
##  6 oats   agrimore       23.3
##  7 oats   supergain      19.7
##  8 oats   supersupp      21.9
##  9 wheat  control        17.4
## 10 wheat  agrimore       19.6
## 11 wheat  supergain      17.0
## 12 wheat  supersupp      19.7
#Plot Effect of Supplement on Cow Weight Gain (depends on diet)
ggplot(sumMoo, aes(x = supplement, y = meanGrow)) +
  geom_point() + 
  theme_bw()

#Plot Effect of Supplement on Cow Weight Gain depending on diet #(connecting supplement/growth according to diet)
ggplot(sumMoo, aes(x = supplement, y = meanGrow,
                   colour = diet, group = diet)) +
  geom_point() + 
  geom_line() +
  theme_bw()

#Expand combination of variable for interaction between main effect of #diet and main effect of supplement
model_cow <- lm(gain ~ diet * supplement, data = growth.moo)

#Building the 4 plots
autoplot(model_cow, smooth.colour = NA)
## Warning: `fortify(<lm>)` was deprecated in ggplot2 4.0.0.
## ℹ Please use `broom::augment(<lm>)` instead.
## ℹ The deprecated feature was likely used in the ggfortify package.
##   Please report the issue at <https://github.com/sinhrks/ggfortify/issues>.
## This warning is displayed once per session.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
## Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
## ℹ Please use `linewidth` instead.
## ℹ The deprecated feature was likely used in the ggfortify package.
##   Please report the issue at <https://github.com/sinhrks/ggfortify/issues>.
## This warning is displayed once per session.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
## Warning: Removed 48 rows containing missing values or values outside the scale range
## (`geom_line()`).
## Removed 48 rows containing missing values or values outside the scale range
## (`geom_line()`).

#ANOVA
anova(model_cow)
## Analysis of Variance Table
## 
## Response: gain
##                 Df  Sum Sq Mean Sq F value    Pr(>F)    
## diet             2 287.171 143.586 83.5201 2.999e-14 ***
## supplement       3  91.881  30.627 17.8150 2.952e-07 ***
## diet:supplement  6   3.406   0.568  0.3302    0.9166    
## Residuals       36  61.890   1.719                      
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
#Summary table
summary(model_cow)
## 
## Call:
## lm(formula = gain ~ diet * supplement, data = growth.moo)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -2.48756 -1.00368 -0.07452  1.03496  2.68069 
## 
## Coefficients:
##                                 Estimate Std. Error t value Pr(>|t|)    
## (Intercept)                   23.2966499  0.6555863  35.536  < 2e-16 ***
## dietoats                      -2.8029851  0.9271390  -3.023  0.00459 ** 
## dietwheat                     -5.8911317  0.9271390  -6.354 2.34e-07 ***
## supplementagrimore             3.0518277  0.9271390   3.292  0.00224 ** 
## supplementsupergain           -0.8305263  0.9271390  -0.896  0.37631    
## supplementsupersupp            2.2786527  0.9271390   2.458  0.01893 *  
## dietoats:supplementagrimore   -0.2471088  1.3111726  -0.188  0.85157    
## dietwheat:supplementagrimore  -0.8182729  1.3111726  -0.624  0.53651    
## dietoats:supplementsupergain  -0.0001351  1.3111726   0.000  0.99992    
## dietwheat:supplementsupergain  0.4374395  1.3111726   0.334  0.74060    
## dietoats:supplementsupersupp  -0.9120830  1.3111726  -0.696  0.49113    
## dietwheat:supplementsupersupp -0.0158299  1.3111726  -0.012  0.99043    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.311 on 36 degrees of freedom
## Multiple R-squared:  0.8607, Adjusted R-squared:  0.8182 
## F-statistic: 20.22 on 11 and 36 DF,  p-value: 3.295e-12
#Calculate mean and sd of gain for all 12 combinations
#n() counts the rows in each group (includes rows w/missing values)
sumMoo <- growth.moo %>%
  group_by(diet, supplement) %>%
    summarise(
      meanGrow = mean(gain),
      seGrow = sd(gain)/sqrt(n())
    )
## `summarise()` has regrouped the output.
## ℹ Summaries were computed grouped by diet and supplement.
## ℹ Output is grouped by diet.
## ℹ Use `summarise(.groups = "drop_last")` to silence this message.
## ℹ Use `summarise(.by = c(diet, supplement))` for per-operation grouping
##   (`?dplyr::dplyr_by`) instead.
#Two-way ANOVA
ggplot(sumMoo, aes(x = supplement, y = meanGrow,
                   colour = diet, group = diet)) +
  geom_point() +
  geom_line() +
  geom_errorbar(aes(ymin = meanGrow - seGrow,
                    ymax = meanGrow + seGrow), width = 0.1) +
  theme_bw()

ANCOVA From Chapter 6

#Call packages
library(ggplot2)
library(dplyr)
library(lubridate)
library(ggfortify)

#Clear the decks
rm(list=ls())

#Read csv file
limp <- read.csv("C:/Users/samhe/OneDrive/Documents/Bio 4259/Bio4259_Labs/data/limpet.csv")

#Check if it works
glimpse(limp)
## Rows: 24
## Columns: 3
## $ DENSITY <int> 8, 8, 8, 8, 8, 8, 15, 15, 15, 15, 15, 15, 30, 30, 30, 30, 30, …
## $ SEASON  <chr> "spring", "spring", "spring", "summer", "summer", "summer", "s…
## $ EGGS    <dbl> 2.875, 2.625, 1.750, 2.125, 1.500, 1.875, 2.600, 1.866, 2.066,…
#Plot window (egg production by limpets in two seasons and at four #limpet densities)
ggplot(limp, aes(x = DENSITY, y = EGGS, colour = SEASON)) +
  geom_point() +
  scale_color_manual(values = c(spring="green", summer="red")) +
  theme_bw()

#Construct ANCOVA
limp.mod <- lm(EGGS ~ DENSITY * SEASON, data = limp)

#See what's collected
names(limp.mod)
##  [1] "coefficients"  "residuals"     "effects"       "rank"         
##  [5] "fitted.values" "assign"        "qr"            "df.residual"  
##  [9] "contrasts"     "xlevels"       "call"          "terms"        
## [13] "model"
#Plot the 4 autoplots
autoplot(limp.mod, smooth.colour = NA)
## Warning: Removed 24 rows containing missing values or values outside the scale range
## (`geom_line()`).
## Removed 24 rows containing missing values or values outside the scale range
## (`geom_line()`).
## Removed 24 rows containing missing values or values outside the scale range
## (`geom_line()`).

#ANOVA
anova(limp.mod)
## Analysis of Variance Table
## 
## Response: EGGS
##                Df Sum Sq Mean Sq F value    Pr(>F)    
## DENSITY         1 5.0241  5.0241 30.1971 2.226e-05 ***
## SEASON          1 3.2502  3.2502 19.5350 0.0002637 ***
## DENSITY:SEASON  1 0.0118  0.0118  0.0711 0.7925333    
## Residuals      20 3.3275  0.1664                      
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
#Summary table
summary(limp.mod)
## 
## Call:
## lm(formula = EGGS ~ DENSITY * SEASON, data = limp)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -0.65468 -0.25021 -0.03318  0.28335  0.57532 
## 
## Coefficients:
##                       Estimate Std. Error t value Pr(>|t|)    
## (Intercept)           2.664166   0.234118  11.380 3.45e-10 ***
## DENSITY              -0.033650   0.008259  -4.074 0.000591 ***
## SEASONsummer         -0.812282   0.331092  -2.453 0.023450 *  
## DENSITY:SEASONsummer  0.003114   0.011680   0.267 0.792533    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 0.4079 on 20 degrees of freedom
## Multiple R-squared:  0.7135, Adjusted R-squared:  0.6705 
## F-statistic:  16.6 on 3 and 20 DF,  p-value: 1.186e-05
#Restates model repeating use of lm()
#Provides range, interquartile range, median of residuals as quick ##additional check of residuals
#Coefficient table
##67% of variation in egg production + significant fit to the data
##F = 16.6, df = 3,20, p>0.001, residual SE = 0.4079 w/20 df
#Equation for line fitted: EGGS = Intercept(b) + slope(m) x DENSITY
## EGGSspring = 2.66 - 0.033 x DENSITY
##EGGSsummer = (2.66-0.812)+(-0.033 + 0.033) x DENSITY,
###EGGSsummer = 1.84 - 0.03 x DENSITY
#Summer reduces egg prod. by ~0.812 eggs
#Expanding grid, generates grid of numbers (factorial representation ##of any variables you provide to it, returns a data frame)
expand.grid(FIRST = c("A", "B"), SECOND = c(1, 2))
##   FIRST SECOND
## 1     A      1
## 2     B      1
## 3     A      2
## 4     B      2
#Predict() generates fitted values from a model
predict(limp.mod)
##         1         2         3         4         5         6         7         8 
## 2.3949692 2.3949692 2.3949692 1.6075953 1.6075953 1.6075953 2.1594217 2.1594217 
##         9        10        11        12        13        14        15        16 
## 2.1594217 1.3938428 1.3938428 1.3938428 1.6546769 1.6546769 1.6546769 0.9358016 
##        17        18        19        20        21        22        23        24 
## 0.9358016 0.9358016 1.1499321 1.1499321 1.1499321 0.4777604 0.4777604 0.4777604
#Make some new DENSITY values at which we request predictions
new.x <- expand.grid(DENSITY =
                       seq(from = 8, to = 45, length.out = 10))

#Check if it works
head(new.x)
##    DENSITY
## 1  8.00000
## 2 12.11111
## 3 16.22222
## 4 20.33333
## 5 24.44444
## 6 28.55556
#Change SEASON into factor
limp$SEASON <- as.factor(limp$SEASON)

#Add SEASON to grid
new.x <- expand.grid(
  DENSITY = seq(from = 8, to = 45, length.out = 10),
  SEASON = levels(limp$SEASON))

#Check if it works
head(new.x)
##    DENSITY SEASON
## 1  8.00000 spring
## 2 12.11111 spring
## 3 16.22222 spring
## 4 20.33333 spring
## 5 24.44444 spring
## 6 28.55556 spring
#Generate fits and confidence interval at new.x values
new.y <- predict(limp.mod, newdata=new.x,
                  interval = 'confidence')

#Check if it works
head(new.y)
##        fit      lwr      upr
## 1 2.394969 2.019285 2.770654
## 2 2.256632 1.931230 2.582034
## 3 2.118294 1.834274 2.402315
## 4 1.979957 1.724062 2.235852
## 5 1.841619 1.595998 2.087241
## 6 1.703282 1.447918 1.958646
#Rename fit produced by predict to EGGS to match OG data
addThese <- data.frame(new.x, new.y)
addThese <- rename(addThese, EGGS = fit)

#Check if it works
head(addThese)
##    DENSITY SEASON     EGGS      lwr      upr
## 1  8.00000 spring 2.394969 2.019285 2.770654
## 2 12.11111 spring 2.256632 1.931230 2.582034
## 3 16.22222 spring 2.118294 1.834274 2.402315
## 4 20.33333 spring 1.979957 1.724062 2.235852
## 5 24.44444 spring 1.841619 1.595998 2.087241
## 6 28.55556 spring 1.703282 1.447918 1.958646
#New small data frame containing grid of seasons/densities, + ##predicted confidence values and 95% CI at each of the combinations

#new.x2 with DENSITY set to mean
new.x2 <-expand.grid(DENSITY=mean(limp$DENSITY),
                    SEASON = levels(limp$SEASON))
#predictions
predEgg <-predict(limp.mod, newdata = new.x2)

#housekeeping
EggAtMeanDens <- data.frame(new.x2, predEgg)
head(EggAtMeanDens)
##   DENSITY SEASON predEgg
## 1    24.5 spring 1.83975
## 2    24.5 summer 1.10375
#raw data plot
ggplot(limp, aes(x = DENSITY, y = EGGS, colour = SEASON)) +
  geom_point(size = 5) +
  #add fits and CIs, don't need to specify Density/Egg
  #they are inherited from above
  geom_smooth(data = addThese,
              aes(ymin = lwr, ymax = upr,
                  fill = SEASON), stat = 'identity') +
  #adjust colours
  scale_colour_manual(values = c(spring="green", summer="red")) +
  scale_fill_manual(values = c(spring="green", summer="red")) +
  #theme
  theme_bw()

R script modified from Zuur et al. 2009 for Bio 4259/9915.

Load libraries

library(dplyr)
library(ggplot2)
library(lattice) # for some statistical plots
library(plotly)  # for ggplotly, a wrapper for interactive ggplots
## 
## Attaching package: 'plotly'
## The following object is masked from 'package:ggplot2':
## 
##     last_plot
## The following object is masked from 'package:stats':
## 
##     filter
## The following object is masked from 'package:graphics':
## 
##     layout
library(Hmisc)   # for extra statistical functions e.g. correlation
## 
## Attaching package: 'Hmisc'
## The following object is masked from 'package:plotly':
## 
##     subplot
## The following objects are masked from 'package:dplyr':
## 
##     src, summarize
## The following objects are masked from 'package:base':
## 
##     format.pval, units
library(tidyverse) # Loads R packages for data manipulation, visualization and data handling
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ forcats 1.0.1     ✔ stringr 1.6.0
## ✔ purrr   1.2.2     ✔ tibble  3.3.1
## ✔ readr   2.2.0     ✔ tidyr   1.3.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ plotly::filter()   masks dplyr::filter(), stats::filter()
## ✖ dplyr::lag()       masks stats::lag()
## ✖ Hmisc::src()       masks dplyr::src()
## ✖ Hmisc::summarize() masks dplyr::summarize()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

Functions

define a function to make a correlation matrix

note: had to switch grid.circle and grid.polygon lines from original Zuur file

# Custom function to create a correlation plot.
# The function uses circles and colored sections to represent the correlation(s)
panel.corrgram.2 <- function(x, y, z, subscripts, at = pretty(z), scale = 0.8, ...)
{ #Loads grid package with tools, shapes, graph elements
  require("grid", quietly = TRUE)
  x <- as.numeric(x)[subscripts]
  y <- as.numeric(y)[subscripts]
  z <- as.numeric(z)[subscripts]
  # Converts x, y, z to numeric values and selects observations identified by subscripts
  zcol <- level.colors(z, at = at, ...) # Assigns color to z values
  for (i in seq(along = z)) # Repeats instructions for all z values that i identifies
  {
    lims <- range(0, z[i]) # Find range between 0 and z
    tval <- 2 * base::pi * # pi calculates angles
      seq(from = lims[1], to = lims[2], by = 0.01) # Sequence of values from lower to upper limit, increase by .01
    grid.circle(x = x[i], y = y[i], r = .5 * scale,
                default.units = "native") # Creates circle at x and y, r = radius
    grid.polygon(x = x[i] + .5 * scale * c(0, sin(tval)),
                 y = y[i] + .5 * scale * c(0, cos(tval)),
                 default.units = "native",
                 gp = gpar(fill = zcol[i]))
  } # Colored polygon section inside circle
  # Sin() and cos() calculate coordinates for shapes
  # zcoli[i] determines the fill collor for the current value
}

# Run additional R script to load additional functions.
source("C:/Users/samhe/OneDrive/Documents/Bio 4259/Bio4259_Labs/scripts/HighstatLib.R")

Get data

# Reading each data set in txt form rather than usual CSV
Sparrows <- read.table(file = "C:/Users/samhe/OneDrive/Documents/Bio 4259/Bio4259_Labs/data/SparrowsElphick.txt", header = TRUE)
Sparrows <- Sparrows[sample(1:nrow(Sparrows)), ] # randomize the order

Godwits <- read.table(file= "C:/Users/samhe/OneDrive/Documents/Bio 4259/Bio4259_Labs/data/Godwits.txt", header=TRUE)

RiceField <- read.table(file="C:/Users/samhe/OneDrive/Documents/Bio 4259/Bio4259_Labs/data/ElphickBirdData.txt", header = TRUE)

Sparrows2 <- read.table(file = "C:/Users/samhe/OneDrive/Documents/Bio 4259/Bio4259_Labs/data/VegSamplesV1.txt", header = TRUE)

Make Figure 2

# Boxplots and dot plots for the detection of outliers for continuous data.

# boxplot for a single variable
boxplot(Sparrows$wingcrd, range=1.5, ylab = "Wing length (mm)")

# dot plot of a single variable using ggplot
ggplot(data=Sparrows,aes(x=wingcrd,y=order(wingcrd)))+
  geom_point()+
  xlab("Wing length (mm)")+
  ylab("Order of the data")+
  theme(panel.grid.major = element_blank(), 
        panel.grid.minor = element_blank())

# dot plot of a single variable using ggplot with a ggplotly wrapper
ggplotly(ggplot(data=Sparrows,aes(x=tarsus,y=order(tarsus)))+
  geom_point()+
  xlab("Tarsus (mm)")+
  ylab("Order of the data")+
  theme(panel.grid.major = element_blank(), 
        panel.grid.minor = element_blank()))
# One way to report data with outlier
Sparrows %>% filter(tarsus==31.8)
##   wingcrd flatwing tarsus head culmen nalospi   wt bandstat initials Year Month
## 1      59       60   31.8 21.9   12.2     8.9 19.9        1        8 2002     6
##   Day Location SpeciesCode Sex Age
## 1  19        5           1   4   1

Make Figure 3

# Dot plots for multiple variables.

# Use Sparrows.

# Combine variables into a matrix
Z <- cbind(Sparrows$wingcrd, Sparrows$tarsus, Sparrows$head,
           Sparrows$culmen, Sparrows$nalospi, Sparrows$wt)

# Add column names
colnames(Z) <- c("wing length", "tarsus length", "head length",
                 "culmen length", "nalospi to bill tip", "weight")

# Reshape data into long format
df <- as.data.frame(Z) %>%
  mutate(row_order = row_number()) %>%
  pivot_longer(cols = -row_order, names_to = "variable", values_to = "value") %>%
  # Keep the exact order of columns instead of alphabetical
  mutate(variable = factor(variable, levels = colnames(Z)))

# Original lattice dotplot
dotplot(as.matrix(Z), groups = FALSE,
        strip = strip.custom(bg = 'white', par.strip.text = list(cex = 0.8)),
        scales = list(x = list(relation = "free"),
                      y = list(relation = "free"),
                      draw = FALSE),
        col = 1, cex = 0.5, pch = 16,
        xlab = "Value of the variable",
        ylab = "Order of the data from text file")

# Create faceted ggplot equivalent
Dotplot <- ggplot(df, aes(x = value, y = row_order)) +
  geom_point(size = 0.5, color = "darkred") +
  facet_wrap(~ variable, scales = "free") +
  labs(title = "Ggplotly Of Dotplot",
       x = "Value of the variable",
       y = "Order of the data from text file") +
  theme_bw()
# Task: translate Figure 3 into a ggplot with a ggplotly wrapper

# Render interactive plot
ggplotly(Dotplot)

Make Figure 4

# Boxplots for the detection of heterogeneity.

# Godwit intake rates

# Creating factors for Sex and Migration period
Godwits$fSEX <- factor(Godwits$SEX, levels = c(0, 1, 2),
                       labels = c("Not", "Female", "Male")) 
Godwits$fPERIOD <- factor(Godwits$PERIOD, levels = c(0, 1, 2),
                          labels = c("Summer", "Pre-migration", "Winter"))

# Original boxplot using lattice
bwplot(mgconsumed ~ fPERIOD | fSEX, data = Godwits,
   strip = strip.custom(bg = 'white'),   subset = SEX!=0,
   cex = .5, layout = c(2, 1),
   xlab = "Migration period", ylab = "Intake rate",
   par.settings = list(
      box.rectangle = list(col = 1),
      box.umbrella  = list(col = 1),
      plot.symbol   = list(cex = .5, col = 1)),
       scales = list(x = list(relation = "same"),
                     y = list(relation = "same")))

# Task: Change the colour scheme (was blue/green)

# ggplot equivalent plot
ggplot(data=filter(Godwits,fSEX != "Not"),
       aes(x=fPERIOD,y=mgconsumed,fill=fSEX))+
  geom_boxplot()+
  scale_fill_manual(values=c("red","skyblue"),name="Sex")+
  xlab("Migration period")+
  ylab("Intake rate")+
  theme(panel.grid.major = element_blank(), 
        panel.grid.minor = element_blank())+
  facet_grid(~fSEX)

# Task: Add a plot to show each sex within each period

# ggplotly equivalent with shown sex within each period
plotly_Godwits <- ggplot(data = filter(Godwits, fSEX != "Not"),
             aes(x = fPERIOD, y = mgconsumed, fill = fSEX)) +
  geom_boxplot() +
  # Updated color scheme
  scale_fill_manual(values = c("#1f77b4", "#ff7f0e"), name = "Sex") + 
  xlab("Migration period") +
  ylab("Intake rate") +
  theme_bw() + # Clean layout theme
  theme(panel.grid.major = element_blank(), 
        panel.grid.minor = element_blank()) +
  facet_grid(~fSEX)

# Add the plotly wrapper
ggplotly(plotly_Godwits)
# Show the values associated with a boxplot
?boxplot.stats # get help on what is shown in a boxplot
## starting httpd help server ... done
godwits2 <- Godwits %>%
  filter(fSEX=="Male",fPERIOD=="Summer")
boxplot.stats(godwits2$mgconsumed)
## $stats
## [1] 0.03 0.08 0.18 0.36 0.62
## 
## $n
## [1] 65
## 
## $conf
## [1] 0.125127 0.234873
## 
## $out
## [1] 1.07 0.93
IQR(godwits2$mgconsumed)*1.58+median(godwits2$mgconsumed) 
## [1] 0.6224
# proof of the extreme of the upper whisker

Make Figure 5

# Histograms for evaluating distributions and assessing heterogeneity.

# Create factor for Months
Sparrows$fMonth<-factor(Sparrows$Month,
                        levels = c(5, 6, 7, 8, 9, 10),
                        labels = c("May", "June", "July", "August",
                                   "Sept.", "Oct."))

# Create variable to identify Months
Sparrows$I1 <- Sparrows$fMonth =="June" |
               Sparrows$fMonth =="July" |
               Sparrows$fMonth =="August"


# Histogram using all data
hist(Sparrows$wt[Sparrows$I1],
     xlab = "Weight (g)", breaks = 30,
     main = "", ylab = "Frequency")

# Histograms separated by month
histogram( ~ wt | fMonth, type = "count",
    xlab = "Weight (g)",
    ylab = "Frequency",
    nint=30,layout=c(1,3),
    strip.left = strip.custom(bg = 'white'),
    strip = F,
    col.line = "black", col = "white",
    scales = list(x = list(relation = "same"),
                  y = list(relation = "same"),
                  draw = TRUE),
    subset = fMonth =="June" | fMonth == "July" |fMonth == "August",
    data = Sparrows)

# Task make the same plot faceted by month

# ggplot equivalent
Histo <- ggplot(data=filter(Sparrows,I1==TRUE),aes(x=wt))+
  geom_histogram(bins=30,col="red")+
  xlab("Weight (g)")+
  ylab("Frequency")+
  theme(panel.grid.major = element_blank(), 
        panel.grid.minor = element_blank())
# plot faceted by month
  facet_grid(~fMonth)
## <ggproto object: Class FacetGrid, Facet, gg>
##     attach_axes: function
##     attach_strips: function
##     compute_layout: function
##     draw_back: function
##     draw_front: function
##     draw_labels: function
##     draw_panel_content: function
##     draw_panels: function
##     finish_data: function
##     format_strip_labels: function
##     init_gtable: function
##     init_scales: function
##     map_data: function
##     params: list
##     set_panel_size: function
##     setup_data: function
##     setup_panel_params: function
##     setup_params: function
##     shrink: TRUE
##     train_scales: function
##     vars: function
##     super:  <ggproto object: Class FacetGrid, Facet, gg>
# ggplotly of ggplot histogram  
ggplotly(Histo)

Make Figure 7

# Plots to help identify excess of zeros.

# Use RiceField data.

# Creating a frequency plot
plot(table(round(RiceField$AREA * RiceField$AQBIRDS)),
    type = "h",
    xlim = c(0, 100),
    xlab = "Observed values", ylab = "Frequency")

# Recreates the frequency plot as ggplot with a ggplotly wrapper.
# plotly allow the user to interact with the plot (zoom, hover to show values)
ggplotly(ggplot(data=RiceField,aes(x=AREA*AQBIRDS))+
  geom_histogram(binwidth=1)+
  xlab("Observed values")+
  ylab("Frequency")+
  theme(panel.grid.major = element_blank(), 
        panel.grid.minor = element_blank()))

Make Figure 8

# A fun plot of joint species absence in rice fields

# Use RiceField data.

#These are all the bird species (variables in the df)
AllS <- c(
"TUSW",     "GWFG",     "WHGO",     "CAGO",     "MALL",
"GADW",     "GWTE",     "CITE",     "UNTE",     "AMWI",     "NOPI",
"NOSH",     "RIDU",     "CANV",     "BUFF",     "WODU",     "RUDU",
"EUWI",     "UNDU",     "PBGB",     "SORA",     "COOT",     "COMO",
"AMBI",     "BCNH",     "GBHE",     "SNEG",     "GREG",     "WFIB",
"SACR",     "AMAV",     "BNST",     "BBPL",     "KILL",     "LBCU",
"GRYE",     "LEYE",     "LBDO",     "SNIP",     "DUNL",     "WESA",
"LESA",     "PEEP",     "RUFF",     "UNSH",     "RBGU",     "HEGU",
"CAGU",     "GUSP")

#Determine species richness (note common and rare species)
Richness <- colSums(RiceField[,AllS] > 0, na.rm = TRUE)

#Remove all covariates, and just keep the species
Birds  <- RiceField[,AllS]

#To reduce the of variables in the figure, we only used the
#20 species that occurred at more than 40 sites.
#As a result, N = 20. Else it becomes a mess.
Birds2 <- Birds[, Richness > 40]
N <- ncol(Birds2)

AllNames <- names(Birds2)

# create and fill a matrix with the number of fields
# with neither species i or j

A <- matrix(nrow = N, ncol = N) # initialize matrix

for (i in 1:N){
  for (j in 1:N){
    A[i,j] <- sum(RiceField[,AllS[i]]==0  & RiceField[,AllS[j]]==0, na.rm=TRUE)
    }}

A1 <- A/2035 # convert # to proportion of fields with neither species
print(A1, digits = 2)
##       [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10] [,11] [,12] [,13]
##  [1,] 1.00 0.98 0.98 0.99 0.69 0.96 0.91 0.98 0.99  0.89  0.82  0.83  0.99
##  [2,] 0.98 0.98 0.97 0.98 0.69 0.95 0.90 0.97 0.98  0.88  0.81  0.82  0.98
##  [3,] 0.98 0.97 0.98 0.98 0.69 0.95 0.90 0.97 0.98  0.88  0.82  0.82  0.98
##  [4,] 0.99 0.98 0.98 1.00 0.69 0.96 0.91 0.98 0.99  0.89  0.82  0.83  0.99
##  [5,] 0.69 0.69 0.69 0.69 0.69 0.69 0.67 0.69 0.69  0.68  0.66  0.65  0.69
##  [6,] 0.96 0.95 0.95 0.96 0.69 0.96 0.89 0.95 0.96  0.87  0.81  0.82  0.96
##  [7,] 0.91 0.90 0.90 0.91 0.67 0.89 0.91 0.90 0.91  0.85  0.80  0.81  0.91
##  [8,] 0.98 0.97 0.97 0.98 0.69 0.95 0.90 0.98 0.98  0.88  0.81  0.83  0.98
##  [9,] 0.99 0.98 0.98 0.99 0.69 0.96 0.91 0.98 1.00  0.89  0.82  0.83  1.00
## [10,] 0.89 0.88 0.88 0.89 0.68 0.87 0.85 0.88 0.89  0.89  0.80  0.80  0.89
## [11,] 0.82 0.81 0.82 0.82 0.66 0.81 0.80 0.81 0.82  0.80  0.82  0.77  0.82
## [12,] 0.83 0.82 0.82 0.83 0.65 0.82 0.81 0.83 0.83  0.80  0.77  0.83  0.83
## [13,] 0.99 0.98 0.98 0.99 0.69 0.96 0.91 0.98 1.00  0.89  0.82  0.83  1.00
## [14,] 1.00 0.98 0.98 1.00 0.69 0.96 0.91 0.98 1.00  0.89  0.82  0.83  1.00
## [15,] 0.99 0.98 0.98 0.99 0.69 0.96 0.91 0.98 1.00  0.89  0.82  0.83  1.00
## [16,] 0.99 0.98 0.98 1.00 0.69 0.96 0.91 0.98 1.00  0.89  0.82  0.83  1.00
## [17,] 1.00 0.98 0.98 1.00 0.69 0.96 0.91 0.98 1.00  0.89  0.82  0.83  1.00
## [18,] 0.99 0.98 0.98 0.99 0.69 0.96 0.91 0.98 0.99  0.89  0.82  0.83  0.99
## [19,] 0.97 0.96 0.96 0.97 0.69 0.94 0.89 0.96 0.97  0.88  0.82  0.82  0.97
## [20,] 0.98 0.97 0.97 0.98 0.69 0.95 0.90 0.97 0.98  0.88  0.81  0.83  0.98
##       [,14] [,15] [,16] [,17] [,18] [,19] [,20]
##  [1,]  1.00  0.99  0.99  1.00  0.99  0.97  0.98
##  [2,]  0.98  0.98  0.98  0.98  0.98  0.96  0.97
##  [3,]  0.98  0.98  0.98  0.98  0.98  0.96  0.97
##  [4,]  1.00  0.99  1.00  1.00  0.99  0.97  0.98
##  [5,]  0.69  0.69  0.69  0.69  0.69  0.69  0.69
##  [6,]  0.96  0.96  0.96  0.96  0.96  0.94  0.95
##  [7,]  0.91  0.91  0.91  0.91  0.91  0.89  0.90
##  [8,]  0.98  0.98  0.98  0.98  0.98  0.96  0.97
##  [9,]  1.00  1.00  1.00  1.00  0.99  0.97  0.98
## [10,]  0.89  0.89  0.89  0.89  0.89  0.88  0.88
## [11,]  0.82  0.82  0.82  0.82  0.82  0.82  0.81
## [12,]  0.83  0.83  0.83  0.83  0.83  0.82  0.83
## [13,]  1.00  1.00  1.00  1.00  0.99  0.97  0.98
## [14,]  1.00  1.00  1.00  1.00  1.00  0.97  0.98
## [15,]  1.00  1.00  1.00  1.00  0.99  0.97  0.98
## [16,]  1.00  1.00  1.00  1.00  1.00  0.97  0.98
## [17,]  1.00  1.00  1.00  1.00  1.00  0.97  0.99
## [18,]  1.00  0.99  1.00  1.00  1.00  0.97  0.98
## [19,]  0.97  0.97  0.97  0.97  0.97  0.97  0.96
## [20,]  0.98  0.98  0.98  0.99  0.98  0.96  0.99
# adds species names to matrix
rownames(A1) <- AllNames
colnames(A1) <- AllNames

# create color coded matrix with levelplot
levelplot(A1,xlab=NULL,ylab=NULL,
    at=do.breaks(c(0.5,1.01),101),
    panel=panel.corrgram.2,
    scales=list(x=list(rot=90)),
    colorkey=list(space="top"),
    col.regions=colorRampPalette(c("red","white","blue")))

Make Figure 9

# Plots to evaluate collinearity.

# Use Sparrows2 data.

# Determine VIF's
# Select covariates
Z<-Sparrows2[,c("Avgmaxht", "Avgdens", "ht.thatch",
                "S.patens", "Distichlis", "S.alternifloraShort",
                "S.alternifloraTall", "Juncus", "Bare", "Other",
                "Phragmites", "Shrub", "Tallsedge", "Water")]
               
corvif(Z) # Part of Table 1
## Correlations of the variables
## 
##                        Avgmaxht     Avgdens    ht.thatch    S.patens
## Avgmaxht             1.00000000 -0.22841524  0.466218046 -0.17785017
## Avgdens             -0.22841524  1.00000000  0.062575238  0.67411203
## ht.thatch            0.46621805  0.06257524  1.000000000  0.16053731
## S.patens            -0.17785017  0.67411203  0.160537307  1.00000000
## Distichlis          -0.02337749  0.13160006  0.022321660 -0.10290139
## S.alternifloraShort -0.44042742 -0.35875821 -0.401407857 -0.41441467
## S.alternifloraTall   0.60074164 -0.51803067  0.254760430 -0.55521017
## Juncus               0.17293819  0.32490496 -0.003660471  0.03727048
## Bare                -0.23941028 -0.20344863 -0.155596279 -0.05769548
## Other               -0.36157539  0.13420907 -0.194936964  0.06081853
## Phragmites           0.38995648 -0.06910767  0.330766492  0.08310766
## Shrub               -0.07595686 -0.19996137 -0.141009710 -0.16031227
## Tallsedge            0.28552986 -0.07218760 -0.066039061  0.07970131
## Water               -0.25038911 -0.12840907 -0.120468982 -0.17287729
##                      Distichlis S.alternifloraShort S.alternifloraTall
## Avgmaxht            -0.02337749         -0.44042742        0.600741637
## Avgdens              0.13160006         -0.35875821       -0.518030668
## ht.thatch            0.02232166         -0.40140786        0.254760430
## S.patens            -0.10290139         -0.41441467       -0.555210170
## Distichlis           1.00000000         -0.17327011       -0.219076843
## S.alternifloraShort -0.17327011          1.00000000       -0.156590051
## S.alternifloraTall  -0.21907684         -0.15659005        1.000000000
## Juncus               0.04757495         -0.31812489       -0.231319555
## Bare                -0.24631400         -0.03848335       -0.012422149
## Other               -0.12816334          0.08430546       -0.201525783
## Phragmites           0.08813589         -0.32519571        0.027006156
## Shrub                0.21464963          0.16155126       -0.173082116
## Tallsedge           -0.09316033         -0.15043833       -0.050009373
## Water               -0.21243584          0.06676282        0.002440565
##                           Juncus        Bare       Other  Phragmites
## Avgmaxht             0.172938189 -0.23941028 -0.36157539  0.38995648
## Avgdens              0.324904964 -0.20344863  0.13420907 -0.06910767
## ht.thatch           -0.003660471 -0.15559628 -0.19493696  0.33076649
## S.patens             0.037270482 -0.05769548  0.06081853  0.08310766
## Distichlis           0.047574949 -0.24631400 -0.12816334  0.08813589
## S.alternifloraShort -0.318124889 -0.03848335  0.08430546 -0.32519571
## S.alternifloraTall  -0.231319555 -0.01242215 -0.20152578  0.02700616
## Juncus               1.000000000 -0.14345423 -0.11858986  0.08711016
## Bare                -0.143454233  1.00000000  0.18374555 -0.05895322
## Other               -0.118589860  0.18374555  1.00000000 -0.12488041
## Phragmites           0.087110160 -0.05895322 -0.12488041  1.00000000
## Shrub                0.045112426 -0.09935402  0.02376765  0.09161061
## Tallsedge           -0.070738224  0.14131312  0.26940954  0.09853599
## Water               -0.124503346  0.12718566 -0.07270756 -0.11213772
##                           Shrub   Tallsedge        Water
## Avgmaxht            -0.07595686  0.28552986 -0.250389111
## Avgdens             -0.19996137 -0.07218760 -0.128409073
## ht.thatch           -0.14100971 -0.06603906 -0.120468982
## S.patens            -0.16031227  0.07970131 -0.172877290
## Distichlis           0.21464963 -0.09316033 -0.212435845
## S.alternifloraShort  0.16155126 -0.15043833  0.066762825
## S.alternifloraTall  -0.17308212 -0.05000937  0.002440565
## Juncus               0.04511243 -0.07073822 -0.124503346
## Bare                -0.09935402  0.14131312  0.127185661
## Other                0.02376765  0.26940954 -0.072707562
## Phragmites           0.09161061  0.09853599 -0.112137724
## Shrub                1.00000000 -0.04012283 -0.098725195
## Tallsedge           -0.04012283  1.00000000 -0.059059880
## Water               -0.09872519 -0.05905988  1.000000000
## 
## 
## Variance inflation factors
## Warning in summary.lm(object, ...): essentially perfect fit: summary may be
## unreliable
##                           GVIF
## Avgmaxht              6.120018
## Avgdens               3.206401
## ht.thatch             1.671224
## S.patens            159.350658
## Distichlis           53.754540
## S.alternifloraShort 121.463782
## S.alternifloraTall  159.382860
## Juncus               44.995377
## Bare                 12.058665
## Other                 5.817015
## Phragmites            3.749027
## Shrub                 2.781804
## Tallsedge             4.409398
## Water                17.067777
# prepare data for plot
Z <- as.vector(as.matrix(Sparrows2[, c("Avgmaxht", "Avgdens",
              "ht.thatch", "S.patens", "Distichlis",
              "S.alternifloraShort", "S.alternifloraTall", "Juncus",
              "Bare", "Other", "Phragmites", "Shrub", "Tallsedge", "Water")]))

#Setup the data in vector format for the xyplot
Y10 <- rep(Sparrows2$Banded, 14)

# prepare covariate names
MyNames <- names(Sparrows2[,c("Avgmaxht", "Avgdens", "ht.thatch",
                "S.patens", "Distichlis", "S.alternifloraShort",
                "S.alternifloraTall", "Juncus", "Bare", "Other",
                "Phragmites", "Shrub", "Tallsedge", "Water")])

# repeat covariate names and create labelled factor for plot
ID10 <- rep(MyNames, each = length(Sparrows2$Banded))
ID11 <- factor(ID10, labels = c("% Juncus gerardii",
               "% Shrub", "Height of thatch", "% Spartina patens",
               "% Distichlis", "% Bare ground", "% Other vegetation",
               "% Phragmites australis", "% Tall sedge", "% Water",
               "% Spartina alterniflora (short)",
               "% Spartina alterniflora (tall)",
               "Maximum vegetation height",
               "Vegetation stem density"),
               levels = c("Juncus", "Shrub", "Avgmaxht", "S.patens",
                          "Distichlis", "Bare", "Other", "Phragmites",
                          "Tallsedge", "Water", "S.alternifloraShort",
                          "S.alternifloraTall", "ht.thatch", "Avgdens"))

# create scatterplot using xyplot
xyplot(Y10 ~ Z | ID11, col = 1,
  strip = function(bg='white',...) strip.default(bg='white',...),
  scales = list(alternating = T,
                x = list(relation = "free"),
                y = list(relation = "same")),
  xlab = "Covariates",
  par.strip.text = list(cex = 0.8),
  ylab = "Banded",
  panel=function(x, y, subscripts,...){
    panel.grid(h =- 1, v = 2)
    panel.points(x, y, col = 1, pch = 16)
    if(ID10[subscripts][1] != "Tallsedge") {panel.loess(x,y,col=1,lwd=2)}
    })
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, : at
## -0.0472
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## radius 0.0022278
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## all data on boundary of neighborhood. make span bigger
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## pseudoinverse used at -0.0472
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## neighborhood radius 0.0472
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## reciprocal condition number 1
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## zero-width neighborhood. make span bigger
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, : at
## -0.0472
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## radius 0.0022278
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## all data on boundary of neighborhood. make span bigger
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## pseudoinverse used at -0.0472
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## neighborhood radius 0.0472
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## reciprocal condition number 1
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## zero-width neighborhood. make span bigger
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, : at
## -0.0472
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## radius 0.0022278
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## all data on boundary of neighborhood. make span bigger
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## pseudoinverse used at -0.0472
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## neighborhood radius 0.0472
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## reciprocal condition number 1
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## zero-width neighborhood. make span bigger
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, : at
## -0.0472
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## radius 0.0022278
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## all data on boundary of neighborhood. make span bigger
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## pseudoinverse used at -0.0472
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## neighborhood radius 0.0472
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## reciprocal condition number 1
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## zero-width neighborhood. make span bigger
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, : at
## -0.0472
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## radius 0.0022278
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## all data on boundary of neighborhood. make span bigger
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## pseudoinverse used at -0.0472
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## neighborhood radius 0.0472
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## reciprocal condition number 1
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## zero-width neighborhood. make span bigger
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, : at
## -0.07
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## radius 0.0049
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## all data on boundary of neighborhood. make span bigger
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## pseudoinverse used at -0.07
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## neighborhood radius 0.07
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## reciprocal condition number 1
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## zero-width neighborhood. make span bigger
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, : at
## -0.07
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## radius 0.0049
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## all data on boundary of neighborhood. make span bigger
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## pseudoinverse used at -0.07
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## neighborhood radius 0.07
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## reciprocal condition number 1
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## zero-width neighborhood. make span bigger
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, : at
## -0.07
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## radius 0.0049
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## all data on boundary of neighborhood. make span bigger
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## pseudoinverse used at -0.07
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## neighborhood radius 0.07
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## reciprocal condition number 1
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## zero-width neighborhood. make span bigger
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, : at
## -0.07
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## radius 0.0049
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## all data on boundary of neighborhood. make span bigger
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## pseudoinverse used at -0.07
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## neighborhood radius 0.07
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## reciprocal condition number 1
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## zero-width neighborhood. make span bigger
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, : at
## -0.07
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## radius 0.0049
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## all data on boundary of neighborhood. make span bigger
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## pseudoinverse used at -0.07
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## neighborhood radius 0.07
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## reciprocal condition number 1
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## zero-width neighborhood. make span bigger
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, : at
## -0.1111
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## radius 0.012343
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## all data on boundary of neighborhood. make span bigger
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## pseudoinverse used at -0.1111
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## neighborhood radius 0.1111
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## reciprocal condition number 1
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## zero-width neighborhood. make span bigger
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, : at
## -0.1111
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## radius 0.012343
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## all data on boundary of neighborhood. make span bigger
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## pseudoinverse used at -0.1111
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## neighborhood radius 0.1111
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## reciprocal condition number 1
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## zero-width neighborhood. make span bigger
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, : at
## -0.1111
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## radius 0.012343
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## all data on boundary of neighborhood. make span bigger
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## pseudoinverse used at -0.1111
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## neighborhood radius 0.1111
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## reciprocal condition number 1
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## zero-width neighborhood. make span bigger
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, : at
## -0.1111
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## radius 0.012343
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## all data on boundary of neighborhood. make span bigger
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## pseudoinverse used at -0.1111
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## neighborhood radius 0.1111
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## reciprocal condition number 1
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## zero-width neighborhood. make span bigger
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, : at
## -0.1111
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## radius 0.012343
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## all data on boundary of neighborhood. make span bigger
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## pseudoinverse used at -0.1111
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## neighborhood radius 0.1111
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## reciprocal condition number 1
## Warning in simpleLoess(y, x, w, span, degree = degree, parametric = FALSE, :
## zero-width neighborhood. make span bigger

# get correlations
Sparrows2.df <- as.data.frame(Sparrows2)
cor(Sparrows2.df[,c("Avgmaxht", "Avgdens", "ht.thatch",
                             "S.patens", "Distichlis", "S.alternifloraShort",
                             "S.alternifloraTall", "Juncus", "Bare", "Other",
                             "Phragmites", "Shrub", "Tallsedge", "Water")])
##                        Avgmaxht     Avgdens    ht.thatch    S.patens
## Avgmaxht             1.00000000 -0.22841524  0.466218046 -0.17785017
## Avgdens             -0.22841524  1.00000000  0.062575238  0.67411203
## ht.thatch            0.46621805  0.06257524  1.000000000  0.16053731
## S.patens            -0.17785017  0.67411203  0.160537307  1.00000000
## Distichlis          -0.02337749  0.13160006  0.022321660 -0.10290139
## S.alternifloraShort -0.44042742 -0.35875821 -0.401407857 -0.41441467
## S.alternifloraTall   0.60074164 -0.51803067  0.254760430 -0.55521017
## Juncus               0.17293819  0.32490496 -0.003660471  0.03727048
## Bare                -0.23941028 -0.20344863 -0.155596279 -0.05769548
## Other               -0.36157539  0.13420907 -0.194936964  0.06081853
## Phragmites           0.38995648 -0.06910767  0.330766492  0.08310766
## Shrub               -0.07595686 -0.19996137 -0.141009710 -0.16031227
## Tallsedge            0.28552986 -0.07218760 -0.066039061  0.07970131
## Water               -0.25038911 -0.12840907 -0.120468982 -0.17287729
##                      Distichlis S.alternifloraShort S.alternifloraTall
## Avgmaxht            -0.02337749         -0.44042742        0.600741637
## Avgdens              0.13160006         -0.35875821       -0.518030668
## ht.thatch            0.02232166         -0.40140786        0.254760430
## S.patens            -0.10290139         -0.41441467       -0.555210170
## Distichlis           1.00000000         -0.17327011       -0.219076843
## S.alternifloraShort -0.17327011          1.00000000       -0.156590051
## S.alternifloraTall  -0.21907684         -0.15659005        1.000000000
## Juncus               0.04757495         -0.31812489       -0.231319555
## Bare                -0.24631400         -0.03848335       -0.012422149
## Other               -0.12816334          0.08430546       -0.201525783
## Phragmites           0.08813589         -0.32519571        0.027006156
## Shrub                0.21464963          0.16155126       -0.173082116
## Tallsedge           -0.09316033         -0.15043833       -0.050009373
## Water               -0.21243584          0.06676282        0.002440565
##                           Juncus        Bare       Other  Phragmites
## Avgmaxht             0.172938189 -0.23941028 -0.36157539  0.38995648
## Avgdens              0.324904964 -0.20344863  0.13420907 -0.06910767
## ht.thatch           -0.003660471 -0.15559628 -0.19493696  0.33076649
## S.patens             0.037270482 -0.05769548  0.06081853  0.08310766
## Distichlis           0.047574949 -0.24631400 -0.12816334  0.08813589
## S.alternifloraShort -0.318124889 -0.03848335  0.08430546 -0.32519571
## S.alternifloraTall  -0.231319555 -0.01242215 -0.20152578  0.02700616
## Juncus               1.000000000 -0.14345423 -0.11858986  0.08711016
## Bare                -0.143454233  1.00000000  0.18374555 -0.05895322
## Other               -0.118589860  0.18374555  1.00000000 -0.12488041
## Phragmites           0.087110160 -0.05895322 -0.12488041  1.00000000
## Shrub                0.045112426 -0.09935402  0.02376765  0.09161061
## Tallsedge           -0.070738224  0.14131312  0.26940954  0.09853599
## Water               -0.124503346  0.12718566 -0.07270756 -0.11213772
##                           Shrub   Tallsedge        Water
## Avgmaxht            -0.07595686  0.28552986 -0.250389111
## Avgdens             -0.19996137 -0.07218760 -0.128409073
## ht.thatch           -0.14100971 -0.06603906 -0.120468982
## S.patens            -0.16031227  0.07970131 -0.172877290
## Distichlis           0.21464963 -0.09316033 -0.212435845
## S.alternifloraShort  0.16155126 -0.15043833  0.066762825
## S.alternifloraTall  -0.17308212 -0.05000937  0.002440565
## Juncus               0.04511243 -0.07073822 -0.124503346
## Bare                -0.09935402  0.14131312  0.127185661
## Other                0.02376765  0.26940954 -0.072707562
## Phragmites           0.09161061  0.09853599 -0.112137724
## Shrub                1.00000000 -0.04012283 -0.098725195
## Tallsedge           -0.04012283  1.00000000 -0.059059880
## Water               -0.09872519 -0.05905988  1.000000000

Make Figure 10

# Multi-scatter plot to evaluate correlations among variables.

# requires the Sparrows data

# creates variable names
MyNames <- c("wing chord", "tarsus length", "head length",
             "culmen length", "nalospi to bill tip", "weight")
# creates scatterplot matrix
pairs(Sparrows[,c(1, 3, 4, 5, 6, 7)],
      lower.panel = panel.cor, # correlation coefficients
      cex.labels=1.3, # label size
      labels=MyNames) # apply labels
## Warning in par(usr): argument 1 does not name a graphical parameter
## Warning in par(usr): argument 1 does not name a graphical parameter
## Warning in par(usr): argument 1 does not name a graphical parameter
## Warning in par(usr): argument 1 does not name a graphical parameter
## Warning in par(usr): argument 1 does not name a graphical parameter
## Warning in par(usr): argument 1 does not name a graphical parameter
## Warning in par(usr): argument 1 does not name a graphical parameter
## Warning in par(usr): argument 1 does not name a graphical parameter
## Warning in par(usr): argument 1 does not name a graphical parameter
## Warning in par(usr): argument 1 does not name a graphical parameter
## Warning in par(usr): argument 1 does not name a graphical parameter
## Warning in par(usr): argument 1 does not name a graphical parameter
## Warning in par(usr): argument 1 does not name a graphical parameter
## Warning in par(usr): argument 1 does not name a graphical parameter
## Warning in par(usr): argument 1 does not name a graphical parameter