Eigenvalues and Eigenvectors of a non-square data set

Question

I have just calculated my covariance matrix and in a question I am asked to calculate the first two eigenvalues/eigenvectors of the covariance matrix, but the matrix isn't square. So, I am just unclear what values to use to calculate these values. Here is a picture of the data to make things easier to understand:

yep I figured it out there :) was just using the whole data set like an idiot instead of using ev<-eigven(cov(Data)) ! — XeroPhobous, Mar 12 '17 at 15:16

score 1 · Answer 1 · answered Mar 12 '17 at 14:54

1

Even if the data is non-square the covariance matrix will still be square. For example, using the builtin anscombe data frame:

dim(anscombe)
## [1] 11  8

dim(cov(anscombe))
## [1] 8 8

answered Mar 12 '17 at 14:54

G. Grothendieck

254,981
17
203
341

Eigenvalues and Eigenvectors of a non-square data set

1 Answers1