Envelopes and partial least squares regression
R. D. Cook, I. S. Helland, Z. Su
Journal of the Royal Statistical Society: Series B (Statistical Methodology) · 2013 · Volume 75 · Issue 5
Abstract
We build connections between envelopes, a recently proposed context for efficient estimation in multivariate statistics, and multivariate partial least squares (PLS) regression. In particular, we establish an envelope as the nucleus of both univariate and multivariate PLS, which opens the door to pursuing the same goals as PLS but using different envelope estimators. It is argued that a likelihood-based envelope estimator is less sensitive to the number of PLS components that are selected and that it outperforms PLS in prediction and estimation.
Keywords
Dimension reduction, Envelope models, Envelopes, Maximum likelihood estimation, Partial least squares, SIMPLS algorithm
Enable JavaScript for citation tools and additional paper interactions.