Deakin University
Browse

A simulation study on robust alternatives of least squares regression

journal contribution
posted on 2007-11-15, 00:00 authored by Mohammadreza MohebbiMohammadreza Mohebbi, K Nourijelyani, H Zeraati
We applied four methods of linear regression; the least squares, Huber M, least absolute deviations and nonparametric to several distributional assumptions. The same sets of simulated data were used and MSE, MAD and biases of these methods were compared. The least absolute deviations, Huber M and nonparametric regression shown to be more appropriate alternatives to the least squares in heavy tailed distributions while the nonparametric and LAD regression were better choices for skewed data. However, no best method could be suggested in all situations and using more than one method of exploratory data analysis is recommended in practice. © 2007 Asian Network for Scientific Information.

History

Journal

Journal of Applied Sciences

Volume

7

Pagination

3469-3476

ISSN

1812-5654

eISSN

1812-5662

Publication classification

CN.1 Other journal article

Issue

22

Publisher

Science Alert

Usage metrics

    Research Publications

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC