EVALUATION OF A DENSITY ESTIMATOR BASED ON A TRAPPING WEB AND DISTANCE SAMPLING THEORY
EVALUATION OF A DENSITY ESTIMATOR BASED ON A TRAPPING WEB AND DISTANCE SAMPLING THEORY
复制标题
DOI：
10.2307/1939171
复制
发表时间：
1985-01-01
期刊：
影响因子：
4.8
通讯作者：
ANDERSON, DR
中科院分区：
文献类型：
--
作者：
WILSON, KR;ANDERSON, DR
使用蒙特卡罗方法评估了一种使用捕获网和距离采样理论的新密度估计技术。复杂的计算机算法根据 4 种不同的活动范围利用分布模拟小型哺乳动物的运动。使用 4 种空间模式、两种种群密度和三种现实的平均捕获概率来模拟小型哺乳动物种群的诱捕；总共评估了 8151 次重复。对于 0.16 和 0.24 的平均捕获概率 (.hivin.p)，密度估计器的相对偏差百分比范围为 -4 至 29%；当 (.hivin.p) = 0.09 时，密度估计器的相对偏差百分比为 -17 至 30%。密度 (D) 为 100 人/公顷时，平均变异系数为 7.8-9.8%；D = 25 人/公顷时，平均变异系数为 15.1-19.1%。在 95% 名义水平的假设下，密度估计器实现的置信区间覆盖范围为 32-94%。开发了一种改进的捕获网方差估计器，可以提高置信区间覆盖范围。诱捕网方法似乎非常有希望帮助管理者或研究人员获得小型哺乳动物种群的可靠密度估计。这一估计背后的统计理论已经非常成熟，并且基于相对较少的假设。
A new density estimation technique using a trapping web and distance sampling theory was evaluated using Monte Carlo methods. A sophisticated computer algorithm simulated movement of small mammals according to 4 different home range utilization distributions. Trapping of small mammal populations was simulated with 4 spatial patterns, two population densities, and three realistic average capture probabilities; in total, 8151 replications were evaluated. Percent relative bias of the estimator of density ranged from -4 to 29% for average capture probabilities (.hivin.p) of 0.16 and 0.24, and from -17 to 30% at (.hivin.p) = 0.09. Average coefficients of variation were 7.8-9.8% at a density (D) of 100 individuals/ha and 15.1-19.1% at D = 25 individuals/ha. Acheived confidence interval coverage for the density estimator ranged from 32-94%, under the assumption of a 95% nominal level. An improved variance estimator for the trapping web was developed that should improve the confidence interval coverage. The trapping web approach appears very promising in aiding the manager or researcher to obtain reliable density estimates for small mammal populations. The statistical theory underlying this estimation is well developed and is based on relatively few assumptions.