In regression analysis, the presence of outliers in the dataset can strongly distort the classical least-squares estimator and lead to unreliable results. To deal with this, several robust-to-outliers methods have been proposed in the statistical literature. In Stata, some of these methods are available through the rreg and qreg commands. Unfortunately, these methods resist only some specific types of outliers and turn out to be ineffective under alternative scenarios. In this article, we present more effective robust estimators that we implemented in Stata. We also present a graphical tool that recognizes the type of detected outliers.
MaronnaR. A., and YohaiV. J.2000. Robust regression with both continuous and categorical predictors. Journal of Statistical Planning and Inference89: 197–214.
7.
RousseeuwP. J.1984. Least median of squares regression. Journal of the American Statistical Association79: 871–880.
8.
RousseeuwP. J., and LeroyA. M.2003. Robust Regression and Outlier Detection.New York: Wiley.
9.
RousseeuwP. J., and van DriessenK.1999. A fast algorithm for the minimum covariance determinant estimator. Technometrics41: 212–223.
10.
RousseeuwP. J., and van ZomerenB. C.1990. Unmasking multivariate outliers and leverage points. Journal of the American Statistical Association85: 633–639.
11.
RousseeuwP. J., and YohaiV. J.1984. Robust regression by means of S-estimators. In Robust and Nonlinear Time Series Analysis, ed. FrankeJ., HärdleW., and MartinR. D., 256–276. New York: Springer.
12.
Salibian-BarreraM., and YohaiV. J.2006. A fast algorithm for S-regression estimates. Journal of Computational and Graphical Statistics15: 414–427.
13.
YohaiV. J.1987. High breakdown-point and high efficiency robust estimates for regression. Annals of Statistics15: 642–656.
