ANALYSIS OF LARGE HEALTH SURVEYS - ACCOUNTING FOR THE SAMPLING DESIGN

Large scale health surveys offer an opportunity to study associations between risk factors and outcomes in a population-based setting. Their complicated multistage sampling designs with differential probabiliti es of sampling individuals can make their analysis unstraightforward. Classical 'design-based' methods that yield approximately unbiased est imators of associations and standard errors can be highly inefficient. Model-based methods require assumptions which, if wrong, can lead to biased estimators of associations and standard errors. This paper exam ines the implications of utilizing the sample clustering and sample we ights in the analysis of survey data. The approach is to estimate the inefficiency of using these aspects of the sampling design in a design -based analysis when actually it was unnecessary to do so. If the inef ficiency is small, then that aspect of the design is used in a design- based fashion. Otherwise, additional modelling assumptions are incorpo rated into the analysis. By focusing attention on risk factor-outcome associations in large health surveys, specific recommendations for pra ctitioners are given. The issues are demonstrated with real survey dat a including two controversial analyses previously published in medical references.