This website uses cookies to track visitor behaviour anonymously - this helps us to improve the website.
Read our Privacy Policy for more information.    Accept | Do Not Track
Home » Knowledge » Techniques » Principal Component Analysis

Principal Component Analysis

Principal Component Analysis (PCA) is a multivariate statistical model that transforms or reduces a set of data (for example, spectra) into a smaller set of linearly independent functions (principal components) which are organised in decreasing order of their variance across the sample set. This allows for useful information to be isolated from a noise background, and for trends and similarities to be highlighted in the data set. PCA is also used as the first stage of principal component regression (PCR). The NIPALS algorithm (Nonlinear Iterative PArtial Least Squares) is an efficient way of calculating the principal components.