|
Abstract:
|
In the near future, the economic directorate of the U.S. Census Bureau will introduce the Annual Integrated Economic Survey (AIES), an economy wide survey that replaces a suite of six independently designed ongoing surveys. The AIES sample design requirements are informed by the user community’s longstanding data needs (e.g., national and sub-national tabulations), as well as by extensive respondent research on collection. This paper provides an end-to-end high-level overview of the AIES probability sampling design, including determination of the sampling unit, computation of unit-level inclusion probabilities for the implement probability proportional to size sampling, stratification, allocation, and sample selection and validation. Throughout, we selectively highlight specific challenges of developing a multi-purpose business survey whose collection covers a wide range of economic sectors. The paper concludes with a brief discussion on post-sampling activities designed to improve the quality of the tabulated domain estimates, including calibrationweighting and proposed imputation methodology.
|
