Detection of influential observations in ridge regression and modified ridge regression

Article type: Research Article

Authors: Türkan, Semra^{; *} | Toktamış, Öniz

Affiliations: Department of Statistic, Faculty of Science, Hacettepe University, Beytepe, Ankara, Turkey

Correspondence: [*] Corresponding author. Tel.: +90 3122992016; Fax: +90 3122977913; E-mail: sturkan@hacettepe.edu.tr.

Abstract: The detection of influential observations is important because of their unduly large influence on the regression analysis results. Numerous diagnostics on identifying these observations are developed in the regression analysis. Pena's statistic is one of the proposed diagnostics. In this study, Pena's approach is formulated to ridge regression (RR) and modified ridge regression (MRR). The real data and artificial data are used to see performance of proposed diagnostic for the RR and MRR on detecting influential observations.

Keywords: Case deletion, ridge regression, Pena's statistic, modified ridge regression, influential observation

DOI: 10.3233/MAS-2011-0215

Journal: Model Assisted Statistics and Applications, vol. 7, no. 2, pp. 91-97, 2012