Comparing design-based methods to improve zip code-level estimates from tax administration data

Article type: Research Article

Authors: Henry, Kimberly^* | Haines, Tracy | Bryant, Victoria

Affiliations: Statistics of Income, 77K St NE, Washington, DC 20002, USA

Correspondence: [*] Corresponding author: Kimberly Henry, Statistics of Income, 77K St NE, Washington, DC 20002, USA. E-mail: Kimberly.A.Henry@irs.gov.

Abstract: Tax policy research relies heavily on the availability of accurate and timely income-related statistics on the filing population of the United States. With computing advancements, more researchers are seeking quality income information for smaller subsets of the filing population. While the Statistics of Income (SOI) Division of the Internal Revenue Service’s Individual sample has a long history of providing quality data at the national level, estimates for small domains are subject to sampling variability. We incorporate auxiliary population frame data with poststratification and ratio adjustments into the SOI sample data to improve zip code-level estimates. We use data from SOI’s Tax Year 2012 sample and population frame to compare results across the alternative methods.

Keywords: Survey sampling, Administrative Tax Records, small area estimation

DOI: 10.3233/SJI-170413

Journal: Statistical Journal of the IAOS, vol. 34, no. 1, pp. 77-89, 2018