Fuzzy set analyses of genetic determinants of health and disability status.

Analyses of complex genotype-phenotype relations require new statistical procedures because of the potentially high dimensionability of those relations which are expressed with both measurement error and stochasticity in the correlation function. We propose modifying a multivariate procedure called grade of membership (GoM) analysis to deal with the special problems of such analyses. In doing so, we make clear some special features of the GoM model for multivariate analysis of high dimensional, discrete data. This is illustrated for apolipoprotein E (APOE) assessments made on 1805 people in the 1999 National Long Term Care Survey. A number of interesting relations with APOE polymorphism were found where disability profiles were more predictive than specific diagnoses because they implicitly contained information on chronicity and severity of disease processes.