|
Activity Number:
|
39
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Sunday, August 2, 2009 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Survey Research Methods
|
| Abstract - #305588 |
|
Title:
|
The Effect of Late-Filed Returns on Population Estimates: A Comparative Analysis
|
|
Author(s):
|
Brian Raub*+ and Cynthia Belmonte and Paul Arnsberger and Melissa Ludlum
|
|
Companies:
|
IRS and IRS and IRS and IRS
|
|
Address:
|
P.O. Box 2608, Statistics of Income, Washington, DC, 20013-2608,
|
|
Keywords:
|
Population estimates ; Bernoulli sample ; Non-response bias ; post-stratification
|
|
Abstract:
|
This paper will examine the effect of late-filed returns on population estimates for three Statistics of Income (SOI) programs. Estimates for populations of interest for each study are produced by drawing stratified, random Bernoulli samples of tax and information returns as they are filed, over periods that span a predetermined number of years. While this methodology results in the inclusion of the majority of targeted returns, a small number of returns for each program are filed beyond the data collection period. These late-filed returns may introduce non-response bias into the population estimates, which might be mitigated by post-stratification or weighting adjustments. This paper will examine the effects of truncated sampling periods on population estimates, using the three SOI projects as case studies, and will provide a comparative analysis.
|
