Partial Least Squares (PLS) is a flexible statistical technique that applies to data of any shape. It models relationships between inputs and outputs even when the inputs are correlated and noisy, there are multiple outputs, and there are more inputs than observations.
The book and e-book Discovering Partial Least Squares with JMP®, by Ian Cox and Marie Gaudard uses JMP to explore PLS and position it within the context of statistical modeling and multivariate analysis.