I want to generate a covariance matrix in R. However, after trying different methods, no one has been successful for obtaining a matrix with the properties I want. rWishart
could be a good method, where I can choose the number of degrees of freedom and a scale matrix.
This is a small example of what I am trying:
nvars = 100
K = rWishart(n=1, df=nvars, Sigma=diag(nvars))[,,1]
However, I am not sure how can I have an easy to handle way, based on 1 or 2 parameters, to manage the values of the covariances (higher or lower), as I haven't used this distribution before.
Does anyone know how could I do this?
Thanks in advance for any help!