TY - ABST
AU - Cook, R. D.
AU - Helland, I. S.
AU - Su, Z.
TI - Envelopes and partial least squares regression
JO - Journal of the Royal Statistical Society: Series B (Statistical Methodology)
PY - 2013-11-01T00:00:00///
VL - 75
IS - 5
SP - 851
EP - 877
N2 - Summary
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.
UR - http://www.ingentaconnect.com/content/bpl/rssb/2013/00000075/00000005/art00003
M3 - doi:10.1111/rssb.12018
UR - http://dx.doi.org/10.1111/rssb.12018