R Statistics Cookbook

How to do it...

In this example, we will generate data from a multivariate Gaussian distribution (with three variables) with an arbitrary covariance matrix. We will assume that these are History, Math and Biology scores, so we will code the matrices accordingly. In a real example, we would load this data from a file, and the column names would obviously be already defined. We will have 50 (observations-students) in each class. The reason we have chosen to work with this simulated dataset is to carry our MANOVA tests in a controlled environment where we know the true parameters:

1. First, we load the MASS library and generate a 3x3 covariance matrix object, as follows:

library(MASS)f = matrix(c(2,1,1,1,2,1,1,1,2),3,3)

2. We generate three datasets ...