Complutense University Library

Selecting and checking a binomial response generalized linear model using phi-divergences

Pardo Llorente, Julio Ángel and Pardo Llorente, María del Carmen (2009) Selecting and checking a binomial response generalized linear model using phi-divergences. Journal of Statistical Planning and Inference , 139 (9). pp. 3038-3049. ISSN 0378-3758

[img] PDF
Restricted to Repository staff only until 2020.

521kB

Official URL: http://www.sciencedirect.com/science/article/pii/S0378375809000378

View download statistics for this eprint

==>>> Export to other formats

Abstract

This work introduces specific tools based on phi-divergences to select and check generalized linear models with binary data. A backward selection criterion that helps to reduce the number of explanatory variables is considered. Diagnostic methods based on divergence measures such as a new measure to detect leverage points and two indicators to detect influential points are introduced. As an illustration, the diagnostics are applied to human psychology data.

Item Type:Article
Uncontrolled Keywords:Generalized linear model; Binary data; -Divergence; Backward procedure; Diagnostics
Subjects:Sciences > Mathematics > Mathematical statistics
ID Code:17316
Deposited On:05 Dec 2012 09:36
Last Modified:07 Feb 2014 09:45

Repository Staff Only: item control page