#Loading 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(lme4)
## Loading required package: Matrix
library(knitr)
library(Matrix)
library(tidyr)
##
## Attaching package: 'tidyr'
## The following objects are masked from 'package:Matrix':
##
## expand, pack, unpack
library(tinytex)
library(reshape2)
##
## Attaching package: 'reshape2'
## The following object is masked from 'package:tidyr':
##
## smiths
#Naming datasets
agonistic <- read.csv("Independent Project Data Set.csv")
agonisticsize <- read.csv("Independent Project Size Data Set.csv")
matched <- read.csv("Matched Behaviour.csv")
crossed <- read.csv("Crossed Behaviour.csv")
totalbehaviour <- read.csv("Total Behaviour.csv")
sizedifference <- read.csv("Size Difference.csv")
#SIZE DISTRIBUTION
##Histogram Showing Size Distribution of Male and Female Crayfish
ggplot(data = agonisticsize, aes(x = size, fill = sex)) +
geom_histogram(bins=7) +
facet_wrap(~ sex) +
scale_fill_manual(values = c("bisque2", "bisque4")) + ggtitle("Size Distribution") +
xlab("Size (mm)") + ylab("Crayfish Count") +
theme_minimal()+
theme(strip.text = element_blank())+
theme(plot.title = element_text(hjust = 0.5),
axis.line = element_line(color = "black", size = 1))
## Warning: The `size` argument of `element_line()` is deprecated as of ggplot2 3.4.0.
## ℹ Please use the `linewidth` argument instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
#BEHAVIOUR DISTRIBUTION
##Histogram Showing Behaviour Distribution of Crayfish in Sex Matched Trials
df <- data.frame(
behavior = c(-2, -1, 1, 2, 3, 4, 5),
Female = matched$female,
Male = matched$male
)
df_long <- melt(df, id.vars = "behavior", variable.name = "Sex", value.name = "Count")
ggplot(df_long, aes(x = factor(behavior), y = Count, fill = Sex)) +
geom_bar(stat = "identity", position = "dodge") +
labs(title = "MATCHED: Behaviour Distribution", x = "Behavior", y = "Average Count", fill = "Sex") +
scale_fill_manual(values = c("Female" = "bisque2", "Male" = "bisque4")) +
facet_wrap(~ Sex, labeller = labeller(Sex = c(Male = "Male Behavior", Female = "Female Behavior"))) +
theme_minimal() +
theme(plot.title = element_text(hjust = 0.5))
##Histogram Showing Behaviour Distribution of Crayfish in Sex Crossed Trials
df <- data.frame(
behavior = c(-2, -1, 1, 2, 3, 4, 5),
Female = crossed$female,
Male = crossed$male
)
df_long <- melt(df, id.vars = "behavior", variable.name = "Sex", value.name = "Count")
ggplot(df_long, aes(x = factor(behavior), y = Count, fill = Sex)) +
geom_bar(stat = "identity", position = "dodge") +
labs(title = "CROSSED: Behaviour Distribution", x = "Behavior", y = "Average Count", fill = "Sex") +
scale_fill_manual(values = c("Female" = "bisque2", "Male" = "bisque4")) +
facet_wrap(~ Sex, labeller = labeller(Sex = c(Male = "Male Behavior", Female = "Female Behavior"))) +
theme_minimal() +
theme(plot.title = element_text(hjust = 0.5))
#SCATTERPLOTS
agonistic_crossed <- subset(agonistic, match == "n")
agonistic_matched <- subset(agonistic, match == "y")
##Scatterplot of Crayfish Sex and Size in Relation to Intensity (CROSSED INTERACTIONS)
plot(agonistic_crossed$size, agonistic_crossed$intensity,
col = ifelse(agonistic_crossed$sex == "female", "bisque2", "bisque4"),
pch = ifelse(agonistic_crossed$sex == "female", 20, 20),
main = "CROSSED: Aggression in Relation to Sex and Size",
xlab = "Size (mm)",
ylab = "Intensity Score")
legend("topleft",
pch = c(20, 20),
c("Female Response", "Male Response"),
col = c("bisque2", "bisque4"))
abline(lm(intensity ~ size, data = subset(agonistic_crossed, sex == "female")), col = "bisque2")
abline(lm(intensity ~ size, data = subset(agonistic_crossed, sex == "male")), col = "bisque4")
##Scatterplot of Crayfish Sex and Size in Relation to Intensity (MATCHED INTERACTIONS)
plot(agonistic_matched$size, agonistic_matched$intensity,
col = ifelse(agonistic_matched$sex == "female", "bisque2", "bisque4"),
pch = ifelse(agonistic_matched$sex == "female", 20, 20),
main = "MATCHED: Aggression in Relation to Sex and Size",
xlab = "Size (mm)",
ylab = "Intensity Score")
legend("topleft",
pch = c(20, 20),
c("Female Response", "Male Response"),
col = c("bisque2", "bisque4"))
abline(lm(intensity ~ size, data = subset(agonistic_matched, sex == "female")), col = "bisque2")
abline(lm(intensity ~ size, data = subset(agonistic_matched, sex == "male")), col = "bisque4")
agonistic_crossed1 <- subset(sizedifference, match == "n")
agonistic_matched1 <- subset(sizedifference, match == "y")
##Scatterplot of Crayfish Sex and Size Difference in Relation to Intensity (CROSSED INTERACTIONS)
plot(agonistic_crossed1$size.difference, agonistic_crossed1$intensity,
col = ifelse(agonistic_crossed1$sex == "female", "bisque2", "bisque4"),
pch = ifelse(agonistic_crossed1$sex == "female", 20, 20),
main = "CROSSED: Aggression in Relation to Sex and Size Difference",
xlab = "Size Difference (mm)",
ylab = "Intensity Score")
legend("topleft",
pch = c(20, 20),
c("Female Response", "Male Response"),
col = c("bisque2", "bisque4"))
abline(lm(intensity ~ size.difference, data = subset(agonistic_crossed1, sex == "female")), col = "bisque2")
abline(lm(intensity ~ size.difference, data = subset(agonistic_crossed1, sex == "male")), col = "bisque4")
##Scatterplot of Crayfish Sex and Size Difference in Relation to Intensity (MATCHED INTERACTIONS)
plot(agonistic_matched1$size.difference, agonistic_matched1$intensity,
col = ifelse(agonistic_matched1$sex == "female", "bisque2", "bisque4"),
pch = ifelse(agonistic_matched1$sex == "female", 20, 20),
main = "MATCHED: Aggression in Relation to Sex and Size Difference",
xlab = "Size Difference (mm)",
ylab = "Intensity Score")
legend("topleft",
pch = c(20, 20),
c("Female Response", "Male Response"),
col = c("bisque2", "bisque4"))
abline(lm(intensity ~ size.difference, data = subset(agonistic_matched1, sex == "female")), col = "bisque2")
abline(lm(intensity ~ size.difference, data = subset(agonistic_matched1, sex == "male")), col = "bisque4")
#STATISTICAL TESTING
##Generalized Linear Model for ALL Trials
glm_sexmatchinteraction <- glm(intensity ~ sex + size + size.difference+ match + sex*match, data = agonistic)
summary(glm_sexmatchinteraction)
##
## Call:
## glm(formula = intensity ~ sex + size + size.difference + match +
## sex * match, data = agonistic)
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -47.6891 23.5800 -2.022 0.04466 *
## sexmale 37.2699 5.3425 6.976 6.09e-11 ***
## size 1.3614 0.8739 1.558 0.12108
## size.difference -0.1516 0.5875 -0.258 0.79666
## matchy 15.1261 5.4579 2.771 0.00619 **
## sexmale:matchy -21.1823 8.0107 -2.644 0.00894 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for gaussian family taken to be 610.9262)
##
## Null deviance: 157490 on 179 degrees of freedom
## Residual deviance: 106301 on 174 degrees of freedom
## AIC: 1673.4
##
## Number of Fisher Scoring iterations: 2
plot(glm_sexmatchinteraction)
##Generalized Linear Model for Matched Trials
glm_matched <- glm(intensity ~ size + size.difference + sex, data = subset(agonistic, match == "y"), family = gaussian)
summary(glm_matched)
##
## Call:
## glm(formula = intensity ~ size + size.difference + sex, family = gaussian,
## data = subset(agonistic, match == "y"))
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -44.708 34.944 -1.279 0.2046
## size 1.840 1.368 1.345 0.1826
## size.difference 1.517 0.915 1.658 0.1014
## sexmale 14.853 6.731 2.207 0.0304 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for gaussian family taken to be 657.0145)
##
## Null deviance: 69374 on 79 degrees of freedom
## Residual deviance: 49933 on 76 degrees of freedom
## AIC: 751.94
##
## Number of Fisher Scoring iterations: 2
plot(glm_matched)
##Generalized Linear Model for Crossed Trials
glm_crossed <- glm(intensity ~ size + size.difference + sex, data = subset(agonistic, match == "n"), family = gaussian)
summary(glm_crossed)
##
## Call:
## glm(formula = intensity ~ size + size.difference + sex, family = gaussian,
## data = subset(agonistic, match == "n"))
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -41.7232 27.2752 -1.530 0.129
## size 0.9871 1.0157 0.972 0.334
## size.difference -1.5196 0.6856 -2.216 0.029 *
## sexmale 45.2943 4.9170 9.212 7.35e-15 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for gaussian family taken to be 463.1927)
##
## Null deviance: 87202 on 99 degrees of freedom
## Residual deviance: 44467 on 96 degrees of freedom
## AIC: 903.52
##
## Number of Fisher Scoring iterations: 2
plot(glm_crossed)
##Correlation Testing
##Correlation Testing for Size Difference and Intensity
agonistic2 <- agonistic %>% group_by(day, interaction) %>% filter(size.difference>0)
cor.test(agonistic2$size.difference, agonistic2$intensity, method = "pearson")
##
## Pearson's product-moment correlation
##
## data: agonistic2$size.difference and agonistic2$intensity
## t = 0.30826, df = 88, p-value = 0.7586
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.1754419 0.2383127
## sample estimates:
## cor
## 0.03284243
##Correlation Testing for Size and Intensity
cor.test(agonistic2$size, agonistic2$intensity, method = "pearson")
##
## Pearson's product-moment correlation
##
## data: agonistic2$size and agonistic2$intensity
## t = 1.5835, df = 88, p-value = 0.1169
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.04209349 0.36109282
## sample estimates:
## cor
## 0.1664486
##Correlation Testing for Sex and Intensity
agonistic$sex_numeric <- ifelse(agonistic$sex == "female", 0, 1)
correlation <- cor.test(agonistic$sex_numeric, agonistic$intensity, method = "spearman")
## Warning in cor.test.default(agonistic$sex_numeric, agonistic$intensity, :
## Cannot compute exact p-value with ties
print(correlation)
##
## Spearman's rank correlation rho
##
## data: agonistic$sex_numeric and agonistic$intensity
## S = 351008, p-value < 2.2e-16
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
## rho
## 0.63887
##Correlation Testing for Female Behaviour (Matched)
correlationfemalematch <- cor.test(matched$behaviour, matched$female, method = "spearman")
print(correlationfemalematch)
##
## Spearman's rank correlation rho
##
## data: matched$behaviour and matched$female
## S = 104, p-value = 0.02381
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
## rho
## -0.8571429
##Correlation Testing for Male Behaviour (Matched)
correlationmalematch <- cor.test(matched$behaviour, matched$male, method = "spearman")
print(correlationmalematch)
##
## Spearman's rank correlation rho
##
## data: matched$behaviour and matched$male
## S = 84, p-value = 0.2667
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
## rho
## -0.5
##Correlation Testing for Female Behaviour (Crossed)
correlationfemalecross <- cor.test(crossed$behaviour, crossed$female, method = "spearman")
## Warning in cor.test.default(crossed$behaviour, crossed$female, method =
## "spearman"): Cannot compute exact p-value with ties
print(correlationfemalecross)
##
## Spearman's rank correlation rho
##
## data: crossed$behaviour and crossed$female
## S = 103.43, p-value = 0.0162
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
## rho
## -0.8468812
##Correlation Testing for Male Behaviour (Crossed)
correlationmalecross <- cor.test(crossed$behaviour, crossed$male, method = "spearman")
## Warning in cor.test.default(crossed$behaviour, crossed$male, method =
## "spearman"): Cannot compute exact p-value with ties
print(correlationmalecross)
##
## Spearman's rank correlation rho
##
## data: crossed$behaviour and crossed$male
## S = 38.846, p-value = 0.504
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
## rho
## 0.3063187