The Annals of Statistics
- Ann. Statist.
- Volume 47, Number 2 (2019), 884-908.
Partial least squares prediction in high-dimensional regression
We study the asymptotic behavior of predictions from partial least squares (PLS) regression as the sample size and number of predictors diverge in various alignments. We show that there is a range of regression scenarios where PLS predictions have the usual root-$n$ convergence rate, even when the sample size is substantially smaller than the number of predictors, and an even wider range where the rate is slower but may still produce practically useful results. We show also that PLS predictions achieve their best asymptotic behavior in abundant regressions where many predictors contribute information about the response. Their asymptotic behavior tends to be undesirable in sparse regressions where few predictors contribute information about the response.
Ann. Statist., Volume 47, Number 2 (2019), 884-908.
Received: January 2017
Revised: December 2017
First available in Project Euclid: 11 January 2019
Permanent link to this document
Digital Object Identifier
Mathematical Reviews number (MathSciNet)
Zentralblatt MATH identifier
Cook, R. Dennis; Forzani, Liliana. Partial least squares prediction in high-dimensional regression. Ann. Statist. 47 (2019), no. 2, 884--908. doi:10.1214/18-AOS1681. https://projecteuclid.org/euclid.aos/1547197242
- Supplement to “Partial least squares prediction in high-dimensional regression”. Proofs for all lemmas, propositions and theorems are provided in the online supplement to this article.