Universidad Complutense de Madrid
E-Prints Complutense

Cressie and Read power-divergences as influence measures for logistic regression models



Downloads per month over past year

Muñoz García, Joaquín and Muñoz Pichardo, Juan Manuel and Pardo Llorente, Leandro (2006) Cressie and Read power-divergences as influence measures for logistic regression models. Computational statistics and data analysis, 50 (11). pp. 3199-3221. ISSN 0167-9473

[img] PDF
Restringido a Repository staff only


Official URL: http://www.sciencedirect.com/science/article/pii/S0167947305001350



A sample version of the power-divergence measures of Cressie and Read is proposed for the influence analysis in the logistic regression model. Influence measures are obtained by quantifying the deviation between the sample distribution of an estimate obtained with all the observations and the sample distribution of the same estimate obtained without any observation. In particular, this approach is applied to three estimates of the model: the MLE of regression coefficients vector, the probabilities vector and the linear predictor of a future case. Some examples are considered to clarify the usefulness of the introduced diagnostics.

Item Type:Article
Uncontrolled Keywords:generalized linear-models; of-fit tests; loglinear models; power-divergence measure; logistic regression; influence analysis; residuals; leverage
Subjects:Sciences > Mathematics > Applied statistics
ID Code:17631
Deposited On:14 Jan 2013 09:12
Last Modified:09 Aug 2018 11:51

Origin of downloads

Repository Staff Only: item control page