Introductory Overview Lecture on Methods of Estimation for Complex Surveys, Part I

• Activity Number: 263
• Type: Invited
• Date/Time: Tuesday, August 5, 2014 : 8:30 AM to 10:20 AM
• Sponsor: ASA
• Author(s): Jay Breidt
• Companies: Colorado State University
• Keywords: design-based estimation ; nonresponse ; analytic inference ; calibration ; weighting ; influential units

Abstract

Survey data often arise from the efforts of institutions (like government agencies) to describe characteristics of a heterogeneous population in a cost-effective way. Typically, institutions use complex surveys with stratification, clustering, and unequal probabilities, and use various weighting adjustments to account for nonresponse and to calibrate to external data sources. This introductory overview lecture is presented in two parts. This first part will describe the basics of design and estimation for complex surveys. Part I will emphasize model-assisted estimation methods, exploring their uses for both descriptive inferences about real finite population parameters and analytic inferences about hypothesized superpopulation parameters. Generalized regression estimation and related calibration methods will be discussed, along with recent nonparametric and semiparametric extensions.