Creating and Interpreting Scree Plots for Multivariate Normal Data Using R Code Example

Here is the revised code with the requested changes:

library(MASS)
library(purrr)

data <- read.csv("data.csv", header = FALSE)
set.seed(1);
eigen_fun <- function() {
  sigma1 <- as.matrix((data[,3:22]))
  sigma2 <- as.matrix((data[,23:42]))
  sample1 <- mvrnorm(n = 250, mu = as_vector(data[,1]), Sigma = sigma1)
  sample2 <- mvrnorm(n = 250, mu = as_vector(data[,2]), Sigma = sigma2)
  sampCombined <- rbind(sample1, sample2);
  covCombined <- cov(sampCombined);
  covCombinedPCA <- prcomp(sampCombined);
  eigenvalues <- covCombinedPCA$sdev^2;
}
mat <- replicate(50, eigen_fun())
colMeans(mat)

library(ggplot2)
library(tidyr)
library(dplyr)

as.data.frame(mat) %>% 
  mutate(id = row_number()) %>% 
  pivot_longer(starts_with("V")) %>% 
  ggplot(aes(x = id, y = value, colour = name, group = name)) +
  geom_hline(aes(yintercept = ave(value, name)), linetype = 3) +
  geom_path(show.legend = FALSE) +
  geom_point(show.legend = FALSE) +
  theme_classic() + 
  ggtitle("Scree plot") + 
  xlab("Principal component") + 
  ylab("Eigen Value") + 
  theme(plot.title = element_text(hjust = 0.5))

The changes made were:

Added ggtitle to set the title of the plot
Added xlab to set the label for the x-axis
Added ylab to set the label for the y-axis
Added theme(plot.title = element_text(hjust = 0.5)) to center the title

Note that I also added a space between the ggtitle, xlab, and ylab functions, as per the standard convention in R.

Last modified on 2023-05-22