Estimation in dual frame surveys with complex designs

摘要: Abstract In a dual frame survey, samples are drawn independently from two overlapping frames that assumed to cover the population of interest. This article considers case when at least one is selected by complex design involving, e.g., multistage sampling. A “pseudo”—maximum likelihood estimator total or mean for such surveys proposed. An advantage proposed same weights used all variables, unlike estimators Hartley and Fuller Burmeister. Asymptotic properties studied, including its efficiency. alternative “single frame” estimator, based on induced separate designs, also studied. Results limited simulation study indicate our essentially as efficient those Burmeister can lead significant efficiency gains over single estimator.