Learn More
Stratification is one of the most widely used techniques in finite population sampling. Strata are disjoint subdivisions of a population, the union of which exhaust the universe, each of which contains a portion of the sample. Two of its essential statistical purposes are to: (1) allow for efficient estimation, especially in the case of stratification by(More)
The authors dedicate this paper to Richard Royall in this year of his retirement, for the profound influence of his thought on survey sampling. In the present work we explicate the application of maximum likelihood inference in the analysis of surveys which are the result of (possibly informative) stratified sampling. In Section 1 we review basic ideas,(More)
Disclaimer: Opinions expressed in this paper are those of the authors and do not constitute policy of the U.S. government or of the agencies listed above. 1. Introduction Government policy makers, economic analysts, and the general public rely heavily on data gathered from federal establishment surveys for information on the U.S. economy. All data(More)
Let A be a population sub-domain of interest and assume that the elements of A cannot be identified on the sampling frame and the number of elements in A is not known. Further assume that a sample of fixed size (say n) is selected from the entire frame and the resulting sub-domain sample size (say n A) is random. The problem addressed is the construction of(More)
The work of this paper is prompted by the particular case of the Current Employment Statistics (CES) Survey conducted monthly by the U.S. Bureau of Labor Statistics. Besides estimates at the national level, the survey yields estimates of employment for numerous domains defined by intersection of industry and geography, providing important information about(More)
In cutoff sampling, inference-— for example, interval estimates with associated alpha-levels —-is problematic. Design-based samplers do not find an adequate random design on which to base variance estimates. Model-based samplers worry that gaps in information can lead to biases. We nonetheless describe some schemes for inference in cutoff sampling. 1.(More)
Nonparametric regression is the model-based sampler's method of choice when there is serious doubt about the suitability of a linear or other simple parametric model for the survey data at hand. It supersedes the need for use of design weights and standard design-based weights. Recognition of this is especially helpful in confronting problems in sampling(More)