Principal Component Analysis

    The objective of the Principal Component Analysis is to reduce the dimensionality of the data set. It involves a mathematical procedure that transforms a number of possibly correlated variables into a smaller number of uncorellated variables that are called principal components.


A principal component decomposition

    It is important to note that if the reduced dimensionnality exceeds three, it is very difficult to understand the data in a 2D/3D graphical representation.

    ArrayMiner offers a PCA view of your data in both 2D and 3D representations. It is accessed with the "PCA axes" check box located in the control strip at the bottom of the button panel in the 2D or 3D mode in the Main Window. When performing a clustering, you can use the "Show PCA axes" button of the information window to display the PCA window.

     In the optional ClassMarker, a PCA view of the samples is available in the 3D view in a Result Tab.