A comparative study of models for correlated binary data with applications to health services research

  • Gemechis Dilba Department of Statistics, Faculty of Science, Addis Ababa University, PO Box 1176 Addis Ababa, Ethiopia
  • Marc Aerts Centre for Statistics, Limburgs Universitair Centrum Universitaire Campus–building D, 3590 Diepenbeek, Belgium
Keywords: Beta-binomial, bootstrap, correlated binary data, model selection, overdispersion

Abstract

Various methods of modeling correlated binary data are compared as applied to data from health services research. The methods include the standard logistic regression, a simple adjustment of the standard errors of logistic regression by a single inflator, the weighted logistic regression, the generalized estimating equation, the beta-binomial model, and two proposed bootstrap methods. First, these approaches are compared for a fixed set of predictors by individual tests of significance. Next, several subsets of predictors are compared through the AIC criterion, whenever applicable.

Key words/phrases: Beta-binomial, bootstrap, correlated binary data, model selection, overdispersion

SINET: Ethiopian Journal of Science Vol. 27 (2) 2004: 97–104
Published
2005-10-18
Section
Articles

Journal Identifiers


eISSN: 2520-7997
print ISSN: 0379-2897