Activity 5

MANOVA in R – How To Implement and Interpret One-Way MANOVA

MANOVA in R: Implementation

head(iris)

Dependent variables

library(ggplot2)
library(gridExtra)

box_sl <- ggplot(iris, aes(x = Species, y = Sepal.Length, fill = Species)) +
  geom_boxplot() +
  theme(legend.position = "top")
box_sw <- ggplot(iris, aes(x = Species, y = Sepal.Width, fill = Species)) +
  geom_boxplot() +
  theme(legend.position = "top")
box_pl <- ggplot(iris, aes(x = Species, y = Petal.Length, fill = Species)) +
  geom_boxplot() +
  theme(legend.position = "top")
box_pw <- ggplot(iris, aes(x = Species, y = Petal.Width, fill = Species)) +
  geom_boxplot() +
  theme(legend.position = "top")

grid.arrange(box_sl, box_sw, box_pl, box_pw, ncol = 2, nrow = 2)

One-way MANOVA in R

dependent_vars <- cbind(iris$Sepal.Length, iris$Sepal.Width, iris$Petal.Length, iris$Petal.Width)
independent_var <- iris$Species

manova_model <- manova(dependent_vars ~ independent_var, data = iris)
summary(manova_model)

Partial Eta Squared

library(effectsize)

eta_squared(manova_model)

Interpret MANOVA in R With a Post-Hoc Test

Linear Discriminant Analysis (LDA)

library(MASS)

iris_lda <- lda(independent_var ~ dependent_vars, CV = F)
iris_lda

lda_df <- data.frame(
  species = iris[, "Species"],
  lda = predict(iris_lda)$x
)
lda_df

ggplot(lda_df) +
  geom_point(aes(x = lda.LD1, y = lda.LD2, color = species), size = 4) +
  theme_classic()