English

A note on the variance in principal component regression

Methodology 2023-06-30 v3 Statistics Theory Statistics Theory

Abstract

Principal component regression results in lack of fit when important dimensions are omitted, which cannot be assessed from the eigenvalues. I show that the PC-regression estimator can also suffer from increased variance relative to ordinary least squares in such cases.

Keywords

Cite

@article{arxiv.2301.01543,
  title  = {A note on the variance in principal component regression},
  author = {Bert van der Veen},
  journal= {arXiv preprint arXiv:2301.01543},
  year   = {2023}
}

Comments

6 pages, 0 figures

R2 v1 2026-06-28T08:02:19.362Z