birds
Charlie
12/05/2020
library(readxl)
ab <- read_excel("bird.xlsx", sheet = "sp ab")
small <- read_excel("bird.xlsx", sheet = "smallsp ab")## New names:
## * Species -> Species...1
## * SYDP -> SYDP...2
## * USYD -> USYD...3
## * `` -> ...5
## * `` -> ...6
## * … and 4 more problemsbirds <- read_excel("bird.xlsx", sheet = "Sheet2")
count <- read_excel("bird.xlsx", sheet = "count")
str(count)## Classes 'tbl_df', 'tbl' and 'data.frame': 21 obs. of 3 variables:
## $ Location: chr "SYDP" "TZ" "USYD" "SYDP" ...
## $ Species : chr "Willie Wagtail" "Willie Wagtail" "Willie Wagtail" "Welcome Swallow" ...
## $ Count : num 5 0 0 72 2 5 20 0 1 0 ...sp <- as.factor(count$Species)
counts <- count$Count
miner <- as.factor(birds$Miner)Visualise the data
Small species
boxplot(count$Count ~ count$Location)
barplot(birds$`Simpsons Evenness` ~ birds$Location)
TZ has the most evenness.
ANOVA
## Total count for each location
mod1 <- aov(Count ~ Location, data = count)
summary(mod1)## Df Sum Sq Mean Sq F value Pr(>F)
## Location 2 1049 524.3 2.327 0.126
## Residuals 18 4056 225.3anova(mod1)## Analysis of Variance Table
##
## Response: Count
## Df Sum Sq Mean Sq F value Pr(>F)
## Location 2 1048.7 524.33 2.3268 0.1263
## Residuals 18 4056.3 225.35library(emmeans)
comp <- emmeans(mod1, "Location")
pairs(comp)## contrast estimate SE df t.ratio p.value
## SYDP - TZ 14.14 8.02 18 1.763 0.2103
## SYDP - USYD 15.71 8.02 18 1.958 0.1515
## TZ - USYD 1.57 8.02 18 0.196 0.9791
##
## P value adjustment: tukey method for comparing a family of 3 estimatesplot(comp)
# Simpson's index with miner abundance as a factor
smp <- aov(birds$`Simpsons Index` ~ as.factor(birds$Miner) + birds$Location, data = birds)
summary(smp)## Df Sum Sq Mean Sq
## as.factor(birds$Miner) 2 0.04059 0.02029smp1 <- aov(`Simpsons Index` ~ Miner, data = birds)
anova(smp1)## Warning in anova.lm(smp1): ANOVA F-tests on an essentially perfect fit are
## unreliable## Analysis of Variance Table
##
## Response: Simpsons Index
## Df Sum Sq Mean Sq F value Pr(>F)
## Miner 2 0.040588 0.020294
## Residuals 0 0.000000anova(smp)## Warning in anova.lm(smp): ANOVA F-tests on an essentially perfect fit are
## unreliable## Analysis of Variance Table
##
## Response: birds$`Simpsons Index`
## Df Sum Sq Mean Sq F value Pr(>F)
## as.factor(birds$Miner) 2 0.040588 0.020294
## Residuals 0 0.000000# no p-value = p = 1.0
mod2 <- lm(birds$`Total Birds` ~ birds$Miner + birds$`Simpsons Index`, data = birds)
anova(mod2)## Warning in anova.lm(mod2): ANOVA F-tests on an essentially perfect fit are
## unreliable## Analysis of Variance Table
##
## Response: birds$`Total Birds`
## Df Sum Sq Mean Sq F value Pr(>F)
## birds$Miner 2 7340.7 3670.3
## Residuals 0 0.0summary(mod2)##
## Call:
## lm(formula = birds$`Total Birds` ~ birds$Miner + birds$`Simpsons Index`,
## data = birds)
##
## Residuals:
## ALL 3 residuals are 0: no residual degrees of freedom!
##
## Coefficients: (1 not defined because of singularities)
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2 NA NA NA
## birds$MinerLOW 110 NA NA NA
## birds$MinerMEDIUM 11 NA NA NA
## birds$`Simpsons Index` NA NA NA NA
##
## Residual standard error: NaN on 0 degrees of freedom
## Multiple R-squared: 1, Adjusted R-squared: NaN
## F-statistic: NaN on 2 and 0 DF, p-value: NAAbundance of each small species at each site
library(readxl)
abprop <- read_excel("bird.xlsx", sheet = "abprop")## New names:
## * `` -> ...5
## * `` -> ...6
## * `` -> ...7prop1 <- read_excel("bird.xlsx", sheet = "Sheet5")
boxplot(prop1$Abundance ~ prop1$Location)
boxplot(prop1$Abundance ~ prop1$Species, las = 2, xlab = "")
ANOVA
prop.aov <- aov(prop1$Abundance ~ prop1$Location + prop1$Species)
anova(prop.aov)## Analysis of Variance Table
##
## Response: prop1$Abundance
## Df Sum Sq Mean Sq F value Pr(>F)
## prop1$Location 2 0.00000 0.000000 0.0000 1.000000
## prop1$Species 7 0.91225 0.130321 5.8633 0.002489 **
## Residuals 14 0.31117 0.022227
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1library(emmeans)
compr <- emmeans(prop.aov, "Species")
pairs(compr)## contrast estimate SE df
## Australian Reed Warbler - Fairy Martin -0.049607 0.122 14
## Australian Reed Warbler - Noisy Miner -0.607626 0.122 14
## Australian Reed Warbler - Spotted Pardalote -0.008708 0.122 14
## Australian Reed Warbler - Superb Fairywren -0.026585 0.122 14
## Australian Reed Warbler - Welcome Swallow -0.220463 0.122 14
## Australian Reed Warbler - White-browed Scrubwren -0.062471 0.122 14
## Australian Reed Warbler - Willie-wagtail -0.008180 0.122 14
## Fairy Martin - Noisy Miner -0.558018 0.122 14
## Fairy Martin - Spotted Pardalote 0.040900 0.122 14
## Fairy Martin - Superb Fairywren 0.023023 0.122 14
## Fairy Martin - Welcome Swallow -0.170856 0.122 14
## Fairy Martin - White-browed Scrubwren -0.012864 0.122 14
## Fairy Martin - Willie-wagtail 0.041427 0.122 14
## Noisy Miner - Spotted Pardalote 0.598918 0.122 14
## Noisy Miner - Superb Fairywren 0.581041 0.122 14
## Noisy Miner - Welcome Swallow 0.387163 0.122 14
## Noisy Miner - White-browed Scrubwren 0.545155 0.122 14
## Noisy Miner - Willie-wagtail 0.599446 0.122 14
## Spotted Pardalote - Superb Fairywren -0.017877 0.122 14
## Spotted Pardalote - Welcome Swallow -0.211755 0.122 14
## Spotted Pardalote - White-browed Scrubwren -0.053763 0.122 14
## Spotted Pardalote - Willie-wagtail 0.000528 0.122 14
## Superb Fairywren - Welcome Swallow -0.193878 0.122 14
## Superb Fairywren - White-browed Scrubwren -0.035886 0.122 14
## Superb Fairywren - Willie-wagtail 0.018405 0.122 14
## Welcome Swallow - White-browed Scrubwren 0.157992 0.122 14
## Welcome Swallow - Willie-wagtail 0.212283 0.122 14
## White-browed Scrubwren - Willie-wagtail 0.054291 0.122 14
## t.ratio p.value
## -0.408 0.9999
## -4.992 0.0036
## -0.072 1.0000
## -0.218 1.0000
## -1.811 0.6234
## -0.513 0.9994
## -0.067 1.0000
## -4.584 0.0075
## 0.336 1.0000
## 0.189 1.0000
## -1.404 0.8416
## -0.106 1.0000
## 0.340 1.0000
## 4.920 0.0041
## 4.773 0.0054
## 3.181 0.0915
## 4.478 0.0091
## 4.924 0.0041
## -0.147 1.0000
## -1.740 0.6650
## -0.442 0.9998
## 0.004 1.0000
## -1.593 0.7474
## -0.295 1.0000
## 0.151 1.0000
## 1.298 0.8854
## 1.744 0.6625
## 0.446 0.9997
##
## Results are averaged over the levels of: Location
## P value adjustment: tukey method for comparing a family of 8 estimatesplot(compr)
#Miner Abundance as 3 levels Low, medium and high.
miner <- as.factor(prop1$`Miner Abundance`)
prop1.aov <- aov(prop1$Abundance ~ prop1$`Miner Abundance` + prop1$Location)
anova(prop1.aov)## Analysis of Variance Table
##
## Response: prop1$Abundance
## Df Sum Sq Mean Sq F value Pr(>F)
## prop1$`Miner Abundance` 1 0.034814 0.034814 2.8097 0.1101
## prop1$Location 1 0.015818 0.015818 1.2766 0.2726
## Residuals 19 0.235423 0.012391Miner Abundance as a proportion compared to abundance of other species present at that site
minerab <- read_excel("bird.xlsx", sheet = "Sheet5")
miner.aov <- aov(minerab$Abundance ~ minerab$Species + minerab$Location + minerab$`Miner Abundance`)
anova(miner.aov)## Analysis of Variance Table
##
## Response: minerab$Abundance
## Df Sum Sq Mean Sq F value Pr(>F)
## minerab$Species 7 0.169963 0.0242805 3.3026 0.03359 *
## minerab$Location 2 0.027868 0.0139342 1.8953 0.19262
## Residuals 12 0.088223 0.0073519
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1Abundance is impacted by species composition (p value = 0.0335). Location is not significant.
Check assumptions.
# check assumptions
plot(miner.aov)## Warning: not plotting observations with leverage one:
## 7
## Warning: not plotting observations with leverage one:
## 7
smallsp <- lm(minerab$Abundance ~ minerab$`Miner Abundance` + minerab$Species + minerab$Location)
anova(smallsp)## Analysis of Variance Table
##
## Response: minerab$Abundance
## Df Sum Sq Mean Sq F value Pr(>F)
## minerab$`Miner Abundance` 1 0.034814 0.034814 4.7353 0.05024 .
## minerab$Species 7 0.157897 0.022557 3.0681 0.04257 *
## minerab$Location 1 0.005121 0.005121 0.6966 0.42024
## Residuals 12 0.088223 0.007352
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1