ASSESSING THE DISTRIBUTION OF PARAMETERS IN MODELS OF LIGAND-RECEPTORINTERACTION - TO LOG OR NOT TO LOG

It is quite common to see experimental data analysed according to a va riety of models of ligand-receptor interaction. Often, parameters deri ved from such models are compared statistically. The most commonly emp loyed statistical analyses contain explicit assumptions about the unde rlying distributions of the model parameters being compared, yet the v alidity of these assumptions is not often ascertained. In this article , Arthur Christopoulos describes a general approach to Monte Carlo sim ulation of data, and outlines how the analysis of such simulated data may be used to address the question of the distribution of model param eters. The results of such an exercise carl guide the researcher to th e appropriate choice of statistical test or data transform.