Careful use of pseudoR-squared measures in epidemiological studies

摘要: Many epidemiological research problems deal with large numbers of exposed subjects whom only a small number actually suffers the adverse event interest. Such rare events data can be analysed by employing an approximate Poisson model. The objective this study is to challenge interpretability corresponding pseudo R-squared measure. It will lack sensible interpretation whenever outcome generated counting within covariate patterns formed cross-tabulating categorical covariates. failure caused immanent arbitrariness in definition patterns, that is, independent Bernoulli events, B(1,pi), are arbitrarily combined into binomially distributed ones, B(n,pi), which then approximated