A Capture-Recapture Design Robust to Unequal Probability of Capture

摘要: At the basis of many capture-recapture sampling models is assumption that all animals are equally likely to be caught in each sample (The Equal Catchability Assumption). This often violated wildlife populations (Seber 1973:81) and 2 general types alternatives exist (Pollock 1981): (1) Heterogeneity: The probability capture any a property animal may vary over population. That is, probabilities according age, sex, social status, other factors. (2) Trap response: depends on animal's prior history capture. become "trap shy" or happy" depending upon type trapping method used. Either 1 both these acting particular traditional model used by biologists for closed (populations additions deletions) short-term studies Schnabel Model (Schnabel 1938) requires Assumption. In recent years there has been substantial research allow heterogeneity and/or trap response probabilities. Otis et al. (1978) published an important monograph allows their routine use biologists. becoming open long-term Jolly-Seber 1973). Assumption complexity population preclude response. During preparation review methods 1981), I realized statisticians have drawn sharp distinction between perhaps rather artificial. Here describe design robust It analysis uses methodology from models. There brief examination its robustness properties using simulation example given detail illustrate