I am reading about PCA and found an exercise that says Show that when a N-dim set of data points X

rmd1228887e

rmd1228887e

Answered question

2022-07-06

I am reading about PCA and found an exercise that says
Show that when a N-dim set of data points X is projected onto the eigenvectors V = [ e 1 e 2 . . . e n ] of its covariance matrix C = X X T , the covariance matrix of the projected data C p = Y Y T is diagonal and hence that, in the space of the eigenvector decomposition, the distribution of X is uncorrelated.
What I have so far is
Y = V T X
Therefore
C p = Y Y T = V T X ( V T X ) T = V T X X T V
but there I got stuck. Any advise on how to proceed, moreover, what does "The covariance matrix of the projected data is diagonal" mean?

Answer & Explanation

Hayley Mccarthy

Hayley Mccarthy

Beginner2022-07-07Added 19 answers

A diagonal matrix is one with zero everywhere and the diagonal entries can be zero or non zero.
Assuming the eigenvectors are normalized in magnitude e i = 1
  V = [ e 1 e 2 e n ]  and  C e i = λ i e i   C V = V [ λ 1 0 0 0 λ 2 0 0 0 λ n ]   C p = V T ( X X T ) V = V T C V   C p = V T V [ λ 1 0 0 0 λ 2 0 0 0 λ n ]   V T V = I  as eigenvecotrs of a symmetric matrix are orthogonal   C p = [ λ 1 0 0 0 λ 2 0 0 0 λ n ] A diagonal matrix with variance in each eigenvector direction

Do you have a similar question?

Recalculate according to your conditions!

Ask your question.
Get an expert answer.

Let our experts help you. Answer in as fast as 15 minutes.

Didn't find what you were looking for?