蒙特卡罗模拟在批质量保证抽样(LQAS)样本量估计中的应用

Monte Carlo simulation for sample size estimation of lot quality assurance sampling(LQAS)

本文在回顾批质量保证抽样(LQAS)样本量计算的统计学原理基础上,用超几何分布计算在一定条件下LQAS一次抽样的样本量;应用Excel和SAS软件展示二项分布蒙特卡罗模拟的原理和实现;采用SAS超几何分布随机数函数完成LQAS样本量估计的蒙特卡罗模拟。超几何分布计算的与蒙特卡罗方法模拟的LQAS一次抽样样本量与现有LQAS样本量表的结果一致。蒙特卡罗模拟估计LQAS样本量具有深刻的统计学思想,其计算简单,易于理解;LQAS可广泛应用于公共卫生领域的快速评价。

In this article, we review statistical principles of sample size estimation for lot quality assurance sampling(LQAS);compute sample sizes for LQAS under a certain conditions using a hypergeometric distribution;elaborate principles and processes of Monte Carlo simulation for binominal distributions using Microsoft Excel and SAS;and perform Monte Carlo simulation for LQAS sample size estimation using the random function of hypergeometric distribution in SAS. Sample sizes computed using hypergeometric distributions or Monte Carlo simulations for onetime LQAS sampling were the same as sample sizes from LQAS tables. Monte Carlo simulation for LQAS sample size estimation has a profound statistical basis;calculations are simple and understandable. LQAS could be more widely applied for rapid public health assessments.