검정력 기반의 복합표본설계를 위한 표본수 결정

Abstract

The determination of sample size is one of the most important aspects in planning a survey. Several precision criteria such as (relative) standard error of error of an estimate are often adopted for deciding the sample size to satisfy the descriptive purpose of the survey in the literature. In this study, we consider power calculation and sample size determination issue when designing a survey the main objective of which is for the analytical purpose. We first carry out a simulation study to show how complex design features can distort the performance of the power when testing a hypothesis on the mean and proportion using the IID-based theory. Furthermore, we propose a method of the sample size determination via a design effect formula for complex sample survey to adjust for the IID-based theory in order to meet a detectable difference requirement of the hypothesis testing.