Likelihood-based approach to estimating twin concordance for dichotomous traits

Genetic epidemiologists are well aware that the casewise and pairwise twin concordances are two different measures. In determining appropriate estimat ors for each of these measures, the method of ascertainment must be conside red. Here, we derive expressions for the concordance estimators and their a symptotic variances appropriate to different twin ascertainment schemes usi ng a likelihood framework, and apply these formulas to existing data We emp hasize the distinction between concordance measures (i.e., the parameters o f interest) and the concordance estimators based on the number of pairs obs erved. Under random or complete ascertainment the casewise estimator is asy mptotically unbiased for the casewise concordance, and the pairwise estimat or is asymptotically unbiased for the pairwise concordance. Under incomplet e ascertainment, the casewise estimator is biased for the casewise concorda nce, the pairwise estimator is biased for the pairwise concordance, but the probandwise estimator is asymptotically unbiased for the casewise concorda nce. One can extend the Likelihood equations presented here to allow the co ncordance parameter of interest to depend on zygosity and, if measured, oth er factors such as cohabitation status and similarity for genetic markers, while concurrently allowing the disease prevalence to depend on measured co variates. Genet. Epidemiol. 16:290-304, 1999. (C) 1999 Wiley-Liss, Inc.