Back to Search Start Over

Linear Programming Techniques in Regression Analysis

Authors :
E. A. Kiountouzis
Source :
Applied Statistics. 22:69
Publication Year :
1973
Publisher :
JSTOR, 1973.

Abstract

SUMMARY In this paper simulation techniques are used to evaluate the use of linear programming in regression analysis. The experiments demonstrate that, in certain cases, minimizing the sum of the absolute values of the deviations (L1 norm) is preferable to the Least Squares criterion. No significant bias was found in the L1 norm estimates.

Subjects

Subjects :
Statistics and Probability
Iteratively reweighted least squares
Proper linear model
Linear regression
Statistics
Explained sum of squares
Least absolute deviations
Statistics, Probability and Uncertainty
Total least squares
Simple linear regression
Nonlinear regression
Mathematics

Details

ISSN :
00359254
Volume :
22
Database :
OpenAIRE
Journal :
Applied Statistics
Accession number :
edsair.doi...........7cfea108136a5566a3921424cb60fd81

Tools

Authors Abstract Subjects Details