Analyzing and identifying unusual observations in modified liu estimator using global influence technique

Abstract

Influence concepts have an important place in linear regression models and case deletion is a useful method for assessing the influence of single case. The influence measures in the presence of multicollinearity were discussed under the linear regression models when the errors structure is uncorrelated and homoscedastic. When modified Liu estimator (MLE) is used to mitigate the effects of multicollinearity, the influence of observations can be drastically modified. In this research paper it is aimed to analyze global influence techniques to detect influential observations in MLE. To illustrate the methodologies derived in this research paper a multicollinearity real data set was used to identify influential observations using global influence techniques derived in this research paper.