# General Linear Models and multiple comparisons
# Use the penguins data

# RESEARCH QUESTION 1: Does body mass differ between species?

# Why use General Linear Model?!

penguins

model1 <- lm(body_mass ~ species, data = penguins)
summary(model1)

# Is the effect of species statistically significant?
# Which species has the highest mean body mass?
# What does the p-value tells you?
# What does the Ajusted R-squared value tells you?
  
# Multiple Comparisons

library(emmeans)
emmeans(model1, pairwise ~ species)

# Plot Using ggplot

library(ggplot2)

ggplot(penguins, aes(x = species, y = body_mass, fill = species)) +
  geom_boxplot() +
  labs(x = "Species", y = "Body mass (g)") +
  theme_classic()

# Based on species and sex
ggplot(penguins, aes(x = species, y = body_mass, fill = sex)) +
  geom_boxplot() +
  labs(x = "Species", y = "Body mass (g)") +
  theme_classic()

# Remove rows where sex is NA
library(dplyr)

penguins_clean <- penguins %>% 
  filter(!is.na(sex))

ggplot(penguins_clean, aes(x = species, y = body_mass, fill = sex)) +
  geom_boxplot() +
  labs(x = "Species", y = "Body mass (g)") +
  theme_classic()

# Does the interaction between species and sex influence body mass?
model2 <- lm(body_mass ~ species * sex, data = penguins_clean)
summary(model2)
emmeans(model2, pairwise ~ sex | species)

# Does flipper length vary across island?
# Does flipper length vary across species and island?