Selecting Procedures for Optimal Subset of Regression Variables.
Abstract
Recently a number of methods have been developed for selecting the best or at least a good subset of variables in regression analysis. For various reasons, we may be interested in including only a subset, say, of size r < p, the number of independent variables. Various authors have considered this problem and a variety of techniques are presently being used to construct such subsets. In this paper, we are interested in deriving an optimal decision procedure based on residual mean squares to select a subset excluding all inferior independent variables. This kind of optimality criterion is related to the approach of Gupta and Huang (1977). (Author)
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 01, 1982
- Accession Number
- ADA113971
Entities
People
- Deng Yuang Huang
- Shanti Gupta
Organizations
- Purdue University