A Bias Bound for Least Squares Linear Regression

by Naihua Duan, Ker-Chau Li


Full Document

FormatFile SizeNotes
PDF file 0.4 MB

Use Adobe Acrobat Reader version 10 or higher for the best experience.


Purchase Print Copy

 FormatList Price Price
Add to Cart Paperback14 pages $35.00 $28.00 20% Web Discount

Regression analysis is one of the most useful tools in statistical analysis. Usually, regression analysis requires specifying the link function for the model. The popular link functions used widely include the linear link function, the logistic link function, and the probit link function. However, in many applications, the functional form and the link function might not be known precisely. Therefore, the usual regression analysis based on a specific link function might not perform well. In this paper, the authors focus on the least squares linear regression which assumes the linear link function. When the linear link function does not hold, the results based on the least squares regression might be biased. The authors derive bounds for the bias and apply the theory to a special case as an illustration.

This report is part of the RAND Corporation Note series. The note was a product of the RAND Corporation from 1979 to 1993 that reported other outputs of sponsored research for general distribution.

Permission is given to duplicate this electronic document for personal use only, as long as it is unaltered and complete. Copies may not be duplicated for commercial purposes. Unauthorized posting of RAND PDFs to a non-RAND Web site is prohibited. RAND PDFs are protected under copyright law. For information on reprint and linking permissions, please visit the RAND Permissions page.

The RAND Corporation is a nonprofit institution that helps improve policy and decisionmaking through research and analysis. RAND's publications do not necessarily reflect the opinions of its research clients and sponsors.