- I am looking for some basic mechanical parts to build structures(prototypes)?
- Is there a danger to a human that is linked to ground wire of home electrical system?
- How do jets/airplane cold start?
- Stop free-roaming dogs from entering my property
- How can I effectively patch up holes in insect screen?
- How to add a Headrest to this chair?
- How to get rid of print from fabric clothing?
- How can I straighten a twisted necktie?
- What is the best way to clean up the spider webs?
- Prevent rubber bands from ageing?
- Efficient life hack to peel a jicama
- Inflation, Future, And Value of Money - deciding to buy a house
- What does it mean for a technology to have a $|\rho|<1$?
- How to use unread-command-events variable?
- Could a gas giant with layer similar to Earth atmosphere exist?
- What change to laws of nature could disable modern technology, but allow nature as we know it? Or is it impossible?
- How would battle strategies change if airplanes had much more limited ranges?
- Is Quora a disruptor for StackExchange?
- Where should i find a co-founder and teammates for my startup?
- Why a girl is forced to get married with in an year after her Mothers death

# Size of PCA decorrelation matrix?

I have a $P\times K$ matrix $\mathbf X$ with $K$ random vectors as columns (with the respective means subtracted from each entry). My goal is to decorrelate the columns of $\mathbf X$ via PCA to obtain the transformed matrix $\mathbf Y$ of the same size as $\mathbf X$.

I proceed as follows: I form the $P \times P$ covariance matrix $\mathbf C=\frac{1}{K}E\big[\mathbf X \mathbf X^\top\big]$. Let the eigendecomposition of the covariance matrix be $\mathbf \Sigma=\mathbf U\mathbf \Lambda \mathbf U^T$ where $\mathbf U$ contains the eigenvectors and $\mathbf \Lambda = \text{diag}\{\lambda_i,\cdots,\lambda_{P}\}$ is the eigenvalue matrix of $\mathbf

\Sigma$. The eigenvalues correspond to the variances. To decorrelate the columns of $\mathbf X$, we multiply this matrix on the left by $\mathbf

\Lambda^{-1/2} \mathbf U^T$:

$$\mathbf Y = \mathbf \Lambda^{-1/2} \mathbf E^T \mathbf X,$$

so that the transformed data $\mathbf Y$ will have an identity covariance matrix.

In the