I'm pretty new to R and PCA analyses, and my datasets are normally too small for any meaningful statistics, but I need to conduct a PCA in R for a paper I'm writing. I'm using the pcaMethods package (method=ppca) because my dataset has a lot of non-random missing data and chatGPT told me this was the best package to use for that. I'm having trouble understanding how to evaluate the effectiveness of my PCA, however. I've found documentation of how to evaluate the amount of variance that's described by each component using a screeplot, but that doesn't seem to be compatible with pcaMethods. Any advice on how to visualize the effectiveness of the PCA I would appreciate (again, I'm a novice at both R and stats).
But also, I have produced a biplot from my PCA and I'm confused why there are secondary x and y-axes that are in a different scale than my primary x and y-axis. I've included a picture below to illustrate. I've looked in a paper published under my advisor several years ago and the PCA performed there looks like a standard scatter plot with one x and one y axis. Any idea why mine is generating these secondary axes and can I get rid of them?
pca_result <- pca(data_matrix, method = "ppca", nPcs = 3)
biplot(pca_result, choices = c(1, 2), main = "Biplot of PC1 and PC2")