Fisher Lecture: Dimension Reduction in Regression
arXiv:0708.3774 · doi:10.1214/088342306000000682
Abstract
Beginning with a discussion of R. A. Fisher's early written remarks that relate to dimension reduction, this article revisits principal components as a reductive method in regression, develops several model-based extensions and ends with descriptions of general approaches to model-based and model-free dimension reduction in regression. It is argued that the role for principal components and related methodology may be broader than previously seen and that the common practice of conditioning on observed values of the predictors may unnecessarily limit the choice of regression methodology.
This paper commented in: [arXiv:0708.3776], [arXiv:0708.3777], [arXiv:0708.3779]. Rejoinder in [arXiv:0708.3781]. Published at http://dx.doi.org/10.1214/088342306000000682 in the Statistical Science (http://www.imstat.org/sts/) by the Institute of Mathematical Statistics (http://www.imstat.org)
Cited by in corpus (6)
- Principal Fitted Components for Dimension Reduction in Regression
- Dimension reduction for nonelliptically distributed predictors
- On surrogate dimension reduction for measurement error regression: An invariance law
- Discussion of: Treelets--An adaptive multi-scale basis for sparse unordered data
- Theoretical properties of Cook's PFC dimension reduction algorithm for linear regression
- Comment: Fisher Lecture: Dimension Reduction in Regression