Assessing Partial Influence in Generalized Linear Models
- 1 March 1988
- journal article
- research article
- Published by JSTOR in Biometrics
- Vol. 44 (1) , 71-77
- https://doi.org/10.2307/2531896
Abstract
A general technique for assessing partial influence in generalized linear models is presented. The method consists of a graphical diagnostic display to identify observations that are either influential on a subset of parameters of substantially contributing to a particular model departure. Application of the method is illustrated with an example in logistic regression.This publication has 2 references indexed in Scilit:
- Influential Observations, High Leverage Points, and Outliers in Linear RegressionStatistical Science, 1986
- Goodness of Link Tests for Generalized Linear ModelsJournal of the Royal Statistical Society Series C: Applied Statistics, 1980