A Tutorial of Partial Least Squares Analysis

Partial least squares (PLS) is a statistical method to predict one set of variables (responses) from another set of variables (predictors). It can handle high dimensional data and thus is an alternative tool to perform genomic prediction. In this tutorial, I will introduce the method and describe the differences between this method and principal component analysis. I will demonstrate its application to genomic prediction using both simulated data and data collected in a real life experiment.