This section contains papers written by members of the Statistics of Income Division of IRS, and others, and presented at the 2004 Joint Statistical Meetings of the American Statistical Association.
The views expressed in these papers are those of the authors and are not necessarily the official positions of the Internal Revenue Service.
All papers are available as PDF files. A free Adobe Acrobat reader is available for download, if needed.
Citations are included in the papers. For more information about a paper, please send us an email message.
Assessing Industry Codes on the IRS Business Master File
Paul B. McMahon, Statistics of Income, IRS
An early process in the development of any business survey is the construction of a sampling frame, and a list of establishments is usually the preferred frame. The most favored sources for such a frame are records systems with lots of auxiliary information, which permit stratification, probability proportional to size sampling, calibration estimation, and other options. The Internal Revenue Service's Business Master File System is one such source.
Customer Satisfaction Initiatives within the Statistics of Income Division of the Internal Revenue Service
Kevin Cecco, Statistics of Income, IRS
This paper focuses on providing an historical perspective of conducting SOI customer surveys, summarizing results from several customer surveys, and offering future plans for expanding customer satisfaction initiatives within SOI.
Data Interpretation across Sources: A Study of Form 990–PF Information Collected from Multiple Databases
Melissa Ludlum, Statistics of Income, IRS
The paper examines administrative data provided to IRS by tax-exempt private foundations. It compares statistics derived from these data and identifies the sources of various discrepancies. Additionally, it examines data compiled at both aggregate and micro levels to determine the effects of IRS data entry and correction procedures.
Editor Judgment Effect: Modeling a Key Component of Nonsampling Error in Administrative Data
Kimberly Henry, Yahia Ahmed, and Ellen Legel, Statistics of Income, IRS. January 2005.
This paper is a first attempt to model a key component of nonsampling error in administrative data, particularly tax data. It examines the simplest corporate tax returns to quantify the effect of SOI editor judgment error on data quality.
Further Analysis of the Distribution of Income and Taxes, 1979–2003
Michael Strudler and Tom Petska, Statistics of Income, IRS, and Ryan Petska, Quantitative Economics and Statistics, Ernst and Young LLP. November 2004. Tables revised October, 2005.
This paper is the sixth in a series examining trends in the distribution of individual incomes and tax burdens based on a consistent and comprehensive measure of income derived from individual income tax returns. It continues the analysis of individual income and tax distributions, adding for 3 years (1979, 1989, and 1999) Social Security and Medicare taxes to this analysis and using panel data.
Related Tables (Excel ver. 4) Revised October 2005.
Some New Tables for Upper Probability Points of the Largest Root of a Determinantal Equation
with Seven and Eight Roots
William W. Chen, Statistics of Income, IRS. January 2005.
We revisit the Fisher-Girshick-Hsu-Roy distribution (1939), which has interested statisticians for more than six decades.
The Effect of Content Errors on Bias and Nonsampling Variance in Estimates Derived From Samples
of Administrative Records
Barry W. Johnson and Darien B. Jacobson, Statistics of Income, IRS. January 2005.
This paper examines quality review data from Federal estate tax returns selected into the Calendar Year 2002 SOI Estate Tax Study to determine the effects of non-sampling error on estimates derived from the final data file.
The Evolution of IRS Telephone Quality Measures
Laura Rosage, Statistics of Income, IRS. January 2005.
The Internal Revenue Service (IRS), tasked with collecting taxes from this country's citizens, deals with more Americans than any other public institution.
The Statistics of Income 1979–2002 Continuous Work History Sample Individual Income Tax Return Panel
Michael Weber, Statistics of Income, IRS. January 2005.
Since 1979, the annual SOI Individual Income Tax Return Cross-Sectional Sample has had at least one Continuous Work History Sample (CWHS) Social Security Number (SSN) ending embedded in the sampling framework.
Use of Individual Retirement Arrangements to Save for Retirement—Results From a Matched File of Tax Returns and Information Documents for Tax Year 2001
Peter Sailer, Statistics of Income, IRS, and Sarah Holden, Investment Company Institute. January 2005.
With $2.6 trillion in assets at year-end 2001, Individual Retirement Arrangements (IRAs) had grown to represent nearly one-quarter of the $11.2 trillion in the U.S. retirement market.