Log-linear-model analysis of the association between disease and genotype.

In this paper, log-linear-model analysis is employed to provide further insight into the disease-genotype association problem, as discussed by Norwood and Hinkelmann (1978, Biometrics 34, 593-602). It is shown how this approach can take account of the structure of the data when testing hypotheses about the type of association, by specifying the form of recurrence risks and allowing estimation of such recurrence risks by maximum likelihood. The notation of conditional recurrence risk is introduced and its usefulness is illustrated.