IDENTIFIKASI TITIK HIGH LEVERAGE PADA MODEL REGRESI LOGISTIK DENGAN METODE ROBUST LOGISTIC DIAGNOSTIC

Abstract

This article discusses the robust logistic diagnostic method for the identification of high leverage points in logistic regression model which is a review of article from Syaiba and Habshah [Journal of Applied Sciences, 10 (2010), 3042-3050]. On first stage, robust estimator used to identify suspect high leverage points by computing the robust Mahalanobis distance based on minimum covariance determinant and minimum volume ellipsoid. On the second stage, the group deleted based on the distance from the mean for logistic regression model is computed. Then the effectiveness of this method is investigated through the simulation of data using software R version 3.1.2.