Leverages, Outliers and the Performance of Robust Regression Estimators
David Adedia, Atinuke Adebanji, Eric Okyere, James Kwaku Agyen
Journal of Advances in Mathematics and Computer Science · pp. 1–14 · Published 12 Mar 2016
10.9734/BJMCS/2016/24281Abstract
This study compared the performance of some robust regression methods and the Ordinary Least Squares Estimator (OLSE). The estimators were compared using varied levels of leverages and vertical outliers in the predictors and the dependent variables. An anthropometric dataset on total body fat with height, Body Mass Index (BMI), Triceps Skin-fold(TS), and arm fat as percent composition of the body (parmfat), as the predictors. The effects of outliers and leverages on the estimators, were investigated at (5% leverages and 10% vertical outliers, 5% leverages with 15% vertical outliers). The criteria for the comparison: coefficients, Root Mean Square Error (RMSE), Relative Efficiencies (RE), coefficients of determination (R-squared) and power of the test. The findings from this study revealed that, OLSE was affected by both outliers and leverages whilst Huber Maximum likelihood Estimator (HME) was affected by leverages. The Least Trimmed Squares Estimator (LTSE) was slightly affected by high perturbations of outliers and leverages. The study also showed that Modified Maximum likelihood Estimator (MME) and S Estimator (SE) were robust to all levels of outliers and leverage perturbations. Therefore leverages and outliers in datasets do affect the post hoc power analysis of the methods which cannot resist them.
References (11)
- 1 Robust Regression and Outlier Detection [DOI]
- 2 Least Median of Squares Regression [DOI]
- 3 Robust Regression: Asymptotics, Conjectures and Monte Carlo [DOI]
- 4 Robust Statistics: Theory and Methods
- 5 High Breakdown-Point and High Efficiency Robust Estimates for Regression [DOI]
- 6 Robust Regression by Means of S-Estimators [DOI]
- 7 Robust Regression in Stata [DOI]
- 8 A Fast Algorithm for S-Regression Estimates [DOI]
- 9 Comparison of Robust Regression Methods in Linear Regression
- 10 Model of Robust Regression with Parametric and Nonparametric Methods
- 11 Ordinary Least Squares and Robust Estimators in Linear Regression: Impacts of Outliers, Error and Response Contaminations [DOI]
Cited by 2
L. Gobena, M. van Dijke · 2017
David Adedia, A. Adebanji, S. K. Appiah · 2016
Related research
- New Critical Values for the Winsorized t-Test — shares topic coverage
- Scalable Functions Used for Empirical Forecasting — shares topic coverage
- On the Efficiency of Modified Regression-type Estimators Using Robust Regression Slopes and Non-conventional Measures of Dispersion — shares topic coverage
- Ordinary Least Squares and Robust Estimators in Linear Regression: Impacts of Outliers, Error and Response Contaminations — shares topic coverage
- Modified Maximum Likelihood Estimation for Generalized Exponential Distribution — shares topic coverage
Article metrics
Real usage data collected on this platform.
0
Page views
0
PDF downloads
0
Outbound clicks
2
Citations
Views by country
Approximate, from request IP at view time — not citizenship or institution. Countries with fewer than 5 views are grouped as "Other".
No views recorded yet.
Traffic sources
Referring site, by host.
No traffic recorded yet.
Views and downloads exclude known bots/crawlers. Citations combines this platform's own DOI-resolved index with each external source's own reported total — see Cited by above for individually listed citing works. Last refreshed 0 seconds ago.