快速流行病学评价法抽样的应用评价

An Evalaation of The Sampling Method in Rapid Epi- demiologic Assessments

本文利用一个基于全人群的大肠癌危险因素病例对照研究资料,来评价快速流行病学评价法抽样方法的实用价值;并与对同一总体的整群及完全单纯随机抽样方法作了比较。结果表明整群、快速流行病学评价法和单纯随机抽样的样本暴露率在α=0.05水平上对总体的错估率分别为21.9%、9.4%和0;32项因素的样本率与相应总体率之间的平均误差分别为:0.043、0.028和0.021,且快速流行病学评价法抽样误差与单纯随机抽样的误差无显著差异(P>0.05)。

Data from a population-based case-control study of risk factors for colorectal cancer were used to evaluate the values of the REA sampling method by being compared with cluster and complete simople randomization.It is shown that the false estimate rates for the population exposure rates by cluster, REA and simple randomixed samples were 21.9%,9.4% and 0% with 0.05 signific ant level;and the average error for the 32 factors in the analysis were 0.043,0.028 and 0.021,re- spectively,And there was no significant difference between the average errors of the REA and simpls randomixed samples(P >0.05).