The Effect of Different Imputation Methods on Analytical Statistics of Simple Linear Regression

by Jann-Huei Jinn .

Abstract: We have considered the simple linear regression model where the errors are normally and independently distributed with E( )=0 and Var( )= . Let , and denote the estimates of , , and where "c" indicates that these are estimates from a completed data set. We present the results of a theoretical investigation of the effect that commonly used imputation methods have on the properties of confidence for and . Specifically, we will try to identify "good" imputation procedures and conditions where specific imputation procedures work well.

Key Words: Simple Linear Regression, Imputation

Authors:
Jann-Huei Jinn, jinnj@gvsu.edu

Editor: Ravi Khattree, Khattree@oakland.edu

READING THE ARTICLE: You can read the article in portable document (.pdf) format (244625 bytes.)

NOTE: The content of this article is the intellectual property of the authors, who retains all rights to future publication.

This page has been accessed 2920 times since July 24, 2006.


Return to the InterStat Home Page.