Most multivariable models in clinical and epidemiology research consider predictor variables as linear terms or as dummy variables after categorization of continuous variables. Clinically it may be desirable to classify patients into different prognosis groups, but categorization of continuous variables assumes homogeneity of the trait under consideration within each specified category. This may however be unrealistic especially when few categories are used. Categorization may result in overparameterized models and there is usually loss of efficiency. Important relevant predictor variables are sometimes missed in prognostic or diagnostic models because the true functional form of a predictor variable may be non-linear. Categorizing confounding variables may result in residual confounding. Fractional polynomials have been proposed in epidemiological studies to investigate functional forms of continuous predictor variables and confounders.
HIV studies at SACEMA have led to theoretical work on two important questions: “Can the early and aggressive use of antiretroviral therapy lead to reductions in HIV incidence?” and “Can we improve the estimation of this incidence from cross-sectional surveys?”. The latter question has focused specifically on how to optimise the use of the BED Read More