Abstract
Case influence statistics are a useful diagnostic tool for identifying high leverage cases in a sample. A case's influence on a solved regression model depends on that case's residual and its location inn the distribution of the predictor variables. Cases with large residuals and located in extreme ranges of the predictor variables' distributions will be most influential. Case influence is illustrated with an SAS analysis of a simple data set.

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Copyright (c) 1991 John T. Pohlman (Author)
Downloads
Download data is not yet available.