Proceedings of the Survey Methods Section ANALYSIS OF CATEGORICAL DATA FROM COMPLEX SAMPLE SURVEYS USING INVERSE SAMPLING

Analysis of complex survey categorical data using classical statistical methods without taking into account the complex nature of the data may lead to asymptotically invalid statistical inferences. Several methods have been developed that account for the survey design, but these methods require additional information such as survey weights, design effects or cluster identification for microdata. An alternate approach is to undo the complex data structures using repeated inverse sampling so that standard methods can be applied to the generated inverse-sampling data files. We propose a combined estimating equation approach to analyze such data files in the context of categorical survey data. For simplicity, we focus on goodness-of-fit test statistics under cluster sampling