ESTIMATION IN DUAL FRAME SURVEYS WITH COMPLEX DESIGNS

In a dual frame survey, samples are drawn independently from two overl apping frames that are assumed to cover the population of interest. Th is article considers the case when at least one of the samples is sele cted by a complex design involving, e.g., multistage sampling. A ''pse udo''-maximum likelihood estimator of a population total or a mean for such dual frame surveys is proposed. An advantage of the proposed est imator is that the same weights are used for all the variables, unlike the estimators of Hartley and Fuller and Burmeister. Asymptotic prope rties of the estimator are studied, including its efficiency. An alter native ''single frame'' estimator, based on the design induced by the two separate designs, is also studied. Results of a limited simulation study indicate that our estimator is essentially as efficient as thos e of Hartley and Fuller and Burmeister and can lead to significant eff iciency gains over the single frame estimator.