Principal Component Analysis and Factor Extraction › Key Parameters

The key parameters for Principal Component Analysis are:

• X: The input data matrix of shape $(n, p)$, where $n$ is the number of observations and $p$ is the number of variables.
• n_components: The number of principal components to retain. This determines the dimensionality of the reduced data.
• Standardization: Whether to scale variables to unit variance before analysis. This is critical when variables have different units or vastly different variances.
• Centering: PCA requires data to be centered (mean zero). This is handled automatically by most libraries but is a necessary preprocessing step in manual implementation.