The applications of capture-recapture models to epidemiological data

Capture-recapture methodology, originally developed for estimating demograp hic parameters of animal populations, has been applied to human populations . This tutorial reviews various closed capture-recapture models which are a pplicable to ascertainment data for estimating the size of a target populat ion based on several incomplete lists of individuals. Most epidemiological approaches merging different lists and eliminating duplicate cases are like ly to be biased downwards. That is, the final merged list misses those who are in the population but were not ascertained in any of the lists. If ther e are no matching errors, then the duplicate information collected from a c apture-recapture experiment can be used to estimate the number of missed un der proper assumptions. Three approaches and their associated estimation pr ocedures are introduced: ecological models; log-linear models, and the samp le coverage approach. Each approach has its unique way of incorporating two types of source dependencies: local (list) dependence and dependence due t o heterogeneity. An interactive program, CARE (for capture-recapture) devel oped by the authors is demonstrated using four real data sets. One set of d ata deals with infection by the acute hepatitis A virus in an outbreak in T aiwan; the other three sets are ascertainment data on diabetes, spina bifid a. and infants' congenital anomaly discussed in the literature. These data sets provide examples to show the usefulness of the capture-recapture metho d in correcting for under-ascertainment. The limitations of the methodology and some cautionary remarks are also discussed. Copyright (C) 2001 John Wi ley & Sons, Ltd.