INFLUENCE DIAGNOSTICS IN PROPER DISPERSION MODELS
- 1 September 1996
- journal article
- Published by Wiley in Australian Journal of Statistics
- Vol. 38 (3) , 307-316
Abstract
Summary: This paper discusses the application of influence diagnostic methods in univariate proper dispersion models. This class includes, in particular, continuous generalized linear models as well as other subclasses of continuous regression models. We emphasize the study of the local influence on the likelihood displacement and predictions from the models. Some of the diagnostics are illustrated by an example on directional data.Keywords
This publication has 16 references indexed in Scilit:
- Statistical Analysis of Circular Data1993
- Regression Models for an Angular Response1992
- Estimation, large-sample parametric tests and diagnostics for non-exponential family nonlinear modelsCommunications in Statistics - Simulation and Computation, 1992
- Some parametric models on the simplexJournal of Multivariate Analysis, 1991
- Fitting Non-Exponential Family Nonlinear Models in GLIM by Using the Offset-Facility1989
- Iteratively Reweighted Least Squares for Maximum Likelihood Estimation, and Some Robust and Resistant AlternativesJournal of the Royal Statistical Society Series B: Statistical Methodology, 1984
- Maximum likelihood estimation and large-sample inference for generalized linear and nonlinear regression modelsBiometrika, 1983
- Two graphical displays for outlying and influential observations in regressionBiometrika, 1981
- Theoretical Statistics1979
- Efficient Simulation of the von Mises DistributionJournal of the Royal Statistical Society Series C: Applied Statistics, 1979