|
Activity Number:
|
106
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Monday, August 3, 2009 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Government Statistics
|
| Abstract - #304457 |
|
Title:
|
Using Sample Data to Reduce Nonsampling Error in State-Level Estimates Produced from Tax Records
|
|
Author(s):
|
Jana Scali*+ and Kimberly Henry and Parthasarathi Lahiri
|
|
Companies:
|
IRS and IRS and University of Maryland
|
|
Address:
|
500 N. Capitol St, NW, Statistics of Income, Washington, DC, 20001,
|
|
Keywords:
|
Survey sampling ; Administrative Records ; Indirect Estimators
|
|
Abstract:
|
For developing public policies and research purposes, income-related statistics are frequently needed for different small geographic regions. Previous research using the Statistics of Income (SOI) Division's Individual sample suggests that some IRS data, though free from the usual sampling error encountered in small area estimation, can be subject to nonsampling error. However, the SOI sample estimates, based on a large national sample of cleaned tax data, are subject to sampling variability for small domains. We use empirical and hierarchical Bayes methods to improve estimators of small-area totals and apply our estimators to data from SOI's 2004 and 2005 samples to evaluate the impact of an increased sample size.
|
- The address information is for the authors that have a + after their name.
- Authors who are presenting talks have a * after their name.
Back to the full JSM 2009 program |
