- Should client ideas about the UI turn into User Stories?
- How to use separated methods?
- Are “technical user stories” allowed in Scrum?
- Cyclomatic Complexity Question
- Rear derailleur speed number interchangability
- mismatched chain and chainring
- Can a character without caster levels learn a metamagic feat?
- Does Flaw (Endurance) reduce health?
- Cached login for Mobile Accounts not working in High Sierra
- Auto-updating charts with Numbers and Keynote
- Buying US iTunes card from UK
- Infrared remote control sometimes stops working
- How to focus the list of songs in iTunes after typing the search query?
- iPad Air & iPhone 5 w IOS8 suddenly won't text (iMessage BAD) send is gray or Red?
- Apache not working on my Mac with Sierra
- I have 2 1 TB partitions on an external drive, and one is a Time Machine backup. How can I resize them to be 1.25 TB and 0.75 TB?
- External Storage solutions for 2017 MacBook Pro Easy to Use on Public Transport
- How to insert Collate into Wordpress search query?
- Force Plugin Updates: “Update Failed: Plugin update failed.” after update one plugin
- Adding category to customized permalink for specific category

# 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