ESTIMATING MEANS AND PERCENTAGES IN A COMPLEX SAMPLING SURVEY - APPLICATION TO A FRENCH NATIONAL SURVEY ON SEXUAL-BEHAVIOR (ACSF)

Two-phase stratification sampling with unequal selection probabilities is a relatively cost-efficient strategy to address problems on a nati onwide basis and to perform comparative analyses of specific subgroups . This was the case with the ACSF survey. Specific procedures to estim ate the variances of unbiased estimators in complex sampling designs a re not included in standard statistical packages and no specialized so ftware is available for two-phase sampling. A detailed synthesis of ge neral basic rules for inference about a target population from a proba bility sample is first presented. We follow with a standard procedure to estimate means and percentages with their confidence intervals acco rding to the design. Finally, numerical results are discussed.