Nonlinear models with repeated measures for analyzing disease progress in plant epidemiology

Nonlinear models are commonly used in plant disease epidemiology to model temporal changes in the proportion of diseased plants (disease index). Most of the times they are fit using linearizing transformations or nonlinear least squares. These approaches assume that the disease index has a normal distribution, that they are independent and that they have constant variance. None of these assumptions can be justified in disease indices. In this paper we apply different strategies to model the progress of papaya ring spot virus in papaya. Using the logistic model we compare different strategies using the SAS® System. Marginal (population average) and subjectspecific interpretations of the models are discussed.