Small domain estimation in the presence of measurement and sampling errors /

Bibliographic Details
Main Authors:	Eltinge, John L. (Author), Harter, Rachel M. (Author)
Corporate Authors:	National Institutes of Health (U.S.) (sponsoring body.), A.C. Nielsen Company (sponsoring body.)
Format:	Book
Language:	English
Published:	College Station, Texas : Department of Statistics, Texas A & M University, 1991.
Series:	Technical report (Texas A & M University. Department of Statistics) ; no. 161.
Subjects:	Errors-in-variables models. Small area statistics. Error analysis (Mathematics) Sampling (Statistics) System identification. Mathematical statistics. Statistics > Inference from stochastic processes > Prediction. Bias reduction

Description
Abstract:	This paper discusses the role of measurement error in small domain estimation. The general framework of Fuller and Harter (1987) is used. Measurement errors in observed survey characteristics and auxiliary variables have two general effects on small domain estimation. First, dependence of measurement error distributions on true values requires adjustment of both mean estimates and shrinkage coefficients. Second, it is important to consider differences in the distributions of measurement errors for sample and nonsample units, respectively. These ideas are illustrated with data from some market research work.
Item Description:	Funding information taken from leaf 15.
Physical Description:	18 leaves, 8 unnumbered leaves : illustrations ; 28 cm
Bibliography:	Includes bibliographical references (leaf 15-18).