Influence diagnostics in mixed effects logistic regression models

DIAZ MP; LEIVA V; TAPIA A; GIAMPAOLI V

TEST

SPRINGER

Lugar: Berlin; Año: 2018

1133-0686

Correlated binary r esponses are commonly described by mixed eff ects l ogisticregression models. This article derives a diagnostic methodology based on the Qdisplacement function to investigate local influence of the responses in the maximumlikelihood estimates of the parameters and in the predictive performance of the mixedeffects logistic regression model. An appropriate perturbation strategy of the probability of success is established, as a form of assessing the perturbation in the response.The diagnostic methodology is evaluated with Monte Carlo simulations. Illustrationswith two real-world data sets (balanced and unbalanced) are conducted to show thepotential of the proposed methodology.