87 – Developments in Survey Design and Implementation
Complex Survey Sample Design in IRS' Multi-Objective Taxpayer Compliance Burden Studies
John Guyton
IRS
Wei Liu
IRS
Michael Sebastiani
IRS
The Internal Revenue Service periodically conducts complex surveys to measure the prefiling and filing burden of individual taxpayers in response to the requirements of the U.S. federal tax system. The sample design for the survey needs to balance three major objectives. The first is to ensure a sufficient number of respondents within and across strata to meet the needs of the modeling of compliance burden. The second is that it must be efficient so that the estimates are reliable. The third is to facilitate the comparisons between the current year study and the previous study. An iterative procedure for a stratified random sample design is proposed to search for the optimal sample allocation. The proposed procedure utilizes the optimality in the Neyman allocation method, and incorporates the minimum sample size requirements for modeling and different nonresponse rates across strata. Our adjustment on the Neyman allocation causes loss of efficiency for descriptive analysis, but such loss of efficiency is minimized so that the estimates still meet the precision requirements. Furthermore, such loss is well compensated by the gains in modeling and analytical capabilities.