Analysis and Comparison of Six Robust Regression Techniques

---

Navruz G., Özdemir A. F.

Journal of Selçuk University Natural and Applied Science, vol.3, no.ISDS Symposium (2014), pp.46-56, 2014 (Peer-Reviewed Journal)

• Publication Type: Article / Article
• Volume: 3 Issue: ISDS Symposium (2014)
• Publication Date: 2014
• Journal Name: Journal of Selçuk University Natural and Applied Science
• Page Numbers: pp.46-56
• Dokuz Eylül University Affiliated: Yes

Abstract

The ordinary least squares regression can be misleading when there are outliers, heteroscedasticity and non-normality. Problems with ordinary least squares are briefly explained and six robust regression techniques, Theil-Sen, least median of squares, least trimmed squares, least absolute value, least trimmed absolute value and M-regression, that are not affected by these common problems are investigated and compared in terms of actual significance level and relative efficiency over ordinary least squares. Results are discussed and some recommendations are given.