AN EXTRAVARIATION MODEL FOR IMPROVING CONFIDENCE-INTERVALS OF POPULATION-SIZE ESTIMATES FROM REMOVAL DATA

We propose a new model for estimating the size of a population from su ccessive catches taken during a removal experiment. The data from thes e experiments often have excessive variation, known as overdispersion, as compared with that predicted by the multinomial model. The new mod el allows catchability to vary randomly among samplings, which account s for overdispersion. When the catchability is assumed to have a beta distribution, the likelihood function, which is refered to as beta-mul tinomial, is derived, and hence the maximum likelihood estimates can b e evaluated. Simulations show that in the presence of extravariation i n the data, the confidence intervals have been substantially underesti mated in previous models (Leslie-DeLury, Moran) and that the new model provides more reliable confidence intervals. The performance of these methods was also demonstrated using two real data sets: one with over dispersion, from smallmouth bass (Micropterus dolomieu), and the other without overdispersion, from rat (Rattus rattus).