Milking Data through Biased Regression Techniques,
Abstract
The recent interest in biased estimation procedures in multiple linear regression arises from the large variances of the least squares estimators (unbiased) of the regression coefficients when multicollinearities are present. The biased estimation procedures greatly reduce this variance at the cost of some bias. It is the purpose of this paper to look at this bias with reference to the nature of the specific problem being investigated. (Author)
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 01, 1977
- Accession Number
- ADA053632
Entities
People
- J. T. Webster
- R. F. Gunst
Organizations
- Southern Methodist University