SOI Tax Stats - 2005 Special Studies in Federal Tax Statistics


This report contains selected papers given at the 2005 annual meetings of the American Statistical Association and other professional conferences.

The views expressed here are those of the authors and are not necessarily the official positions of the Internal Revenue Service.

These reports are available in Adobe PDF format. A free Adobe Acrobat® reader is available for download, if needed.

Some articles include Microsoft Excel tables. A free Excel viewer is available for download, if needed.

Citations are included in the papers. For more information about a paper, please send us an email message.

All PapersPDF
Adobe Acrobat PDF, October 2006.




Jump to a section:

New Research from the IRS

Back to top


An Analysis of Business Organizational Structure and Activity from Tax DataPDF
Tom Petska, Michael Parisi, Kelly Luttrell, Lucy Davitian, and Matt Scoffic, Statistics of Income, IRS

This paper is divided into four sections. The first section briefly provides background information on the tax treatment of business income. The second section briefly summarizes major tax law changes that affected the taxation of business income in the period 1980–2002. The third section presents and analyzes data from annual SOI cross-sectional business studies, and the final section notes some conclusions and plans for future research.

Current Research in the Nonprofit SectorPDF
Paul Arnsberger, Melissa Ludlum, and Margaret Riley, Statistics of Income, IRS

The nonprofit sector supports and advances a variety of religious, social, and economic endeavors. Tax-exempt nonprofit organizations dedicate billions of dollars annually to operating or supporting various initiatives in education, environmental protection and preservation, the arts and humanities, social welfare, health, and other critical areas.

Geographic Variation in Schedule H Filing Rates: Why Should Location Influence the Decision To Report Nanny Taxes?PDF
Kim M. Bloomquist, Statistics of Income, IRS, and Zhiyong An, Department of Economics, University of California, Berkeley Institute

The Schedule H is the Internal Revenue Service (IRS) form used to report Social Security and Medicare taxes on wages of $1,400 or more paid to household employees. The IRS defines a household employee as someone whose work details are controlled by the employer.

Corporate Tax Issues: Book-Tax Differences and Measuring Tax Avoidance

Back to top


Prelude to Schedule M-3: Schedule M-1 Corporate Book-Tax Difference Data, 1990–2003PDF
Charles Boynton and Portia DeFilippes, Office of Tax Analysis, U.S. Treasury Department, and Ellen Legel, Statistics of Income, IRS

For most large corporations, the new Schedule M-3 book-tax reconciliation replaces the 4-decade old Schedule M-1, effective December 2004. The goal of this paper is: (1) to present Schedule M-1 data and other selected tax return data for the immediately preceding 14-year period, 1990–2003; and (2) to address tax policy data interpretation issues related to U.S. intercompany dividends (ICD) improperly included on corporate tax returns by some large taxpayers.

Related Tables (Excel): In paper:1XLS, 2XLS, 3XLS, 4XLS. In addition to paper: 5XLS, 6XLS, 7XLS, 8XLS, 9XLS, 10XLS, 11XLS, 12XLS, 13XLS, 14XLS, 15XLS, 16XLS, 17XLS, 18XLS, 19XLS, 20XLS, 21XLS, 22XLS, 23XLS, 24XLS, 25XLS, 26XLS, 27XLS, 28XLS, 29XLS, 30XLS, 31XLS, 32XLS, 33XLS, 34XLS

Behavioral Responses to Corporate Taxation

Back to top


An Essay on the Effects of Taxation on the Corporate Financial PolicyPDF
George Contos, Statistics of Income, IRS

The taxation of corporate profits in the United States has been one of the most widely discussed issues in the area of public finance. Corporate revenues are currently subject to double taxation. Profits are taxed first at the corporate level and then, when distributed as dividends or when capital gains are realized, taxed a second time at the individual level. The share of tax revenues from corporate profits has been decreasing steadily over the past four decades.

Issues in Quantifying Measurement Error

Back to top


Measuring Nonsampling Error in the Statistics of Income Individual Tax Return StudyPDF
Jana Scali, Valerie Testa, Maureen Kahr, and Michael Strudler, Statistics of Income, IRS

The purpose of this paper is to estimate a component of nonsampling error in the SOI Individual Study. The data from the quality review process is used for this purpose.

Corporation Supercritical Cases: How Do Imputed Returns on the Corporate File Compare to the Actual Returns?PDF
Lucy Davitian, Statistics of Income, IRS

Statistics of Income (SOI) corporation "supercritical" cases are certain large corporations that SOI samples at the 100-percent rate. These supercritical cases account for 58 percent of the total assets of the corporation study while comprising only .03 percent of the total corporation returns; thus, their absence from the Corporation Study would affect the final statistics.

The Impact of the Followup Process on the 2002 Foreign Tax Credit Study DataPDF
Rob Singmaster and Lissa Redmiles, Statistics of Income, IRS

The followup process is an important step in the data cleansing process of the Foreign Tax Credit study conducted by the Statistics of Income Division of the IRS. The study itself collects data from corporate tax forms and their attached Form 1118's.

Interesting Methodological Topics Related to Internal Revenue Service Tax Statistics

Back to top


A Cluster Analysis Approach To Describing Tax DataPDF
Brian G. Raub and William W. Chen, Statistics of Income, IRS

This paper describes a population of Form 1118 filers using cluster analysis, with the goal of identifying alternative ways of organizing and analyzing tax data. A second goal is to identify new insights about this population of filers.

A Comparison of Income Concepts: IRS Statistics of Income, Census Current Population Survey, and BLS Consumer Expenditure SurveyPDF
Eric L. Henry and Charles D. Day, Statistics of Income, IRS

Several Federal Government agencies produce statistics on individual and household income. Because of the differing purposes to which their data will be put, agencies use different definitions for income (income concepts), as well as different reporting units, sample designs, collection modes, and processing rules.

The 1999 Individual Income Tax Return Edited PanelPDF
Michael E. Weber and Victoria L. Bryant, Statistics of Income, IRS

The primary product of the Statistics of Income Division's Individual Statistics Branch is an annual cross-sectional sample of individual income tax returns. Some form of this annual cross section, also known as the Individual Complete Report File, has been produced every year since 1916.

Trends in 401(k) and IRA Contribution Activity, 1999–2002—Results from a Panel of Matched Tax Returns and Information DocumentsPDF
Peter Sailer and Victoria L. Bryant, Statistics of Income, IRS and Sara Holden, Investment Company Institute

By combining individual tax returns (Form 1040) and information returns (such as Forms W-2 and 5498) in one panel database, the Statistics of Income (SOI) Division has made it possible to study trends in contributions by individual taxpayers over time to Individual Retirement Arrangements (IRA’s), as well as the participation in other types of retirement plans.

Estate and Personal Wealth Sample Design

Back to top


Origins of the Estate and Personal Wealth Sample DesignPDF
Paul B. McMahon, Jr., Statistics of Income, IRS

One implication of the decentralized nature of the statistical system in the United States of America, composed of over 70 Federal Government organizations, is that the data used by lawmakers and researchers to develop and evaluate Government policies come from a variety of sources.

IRS Area-To-Area Migration Data

Back to top


Internal Revenue Service Area-To-Area Migration Data: Strengths, Limitations, and Current TrendsPDF
Emily Gross, Statistics of Income, IRS

The development of new disclosure protection techniques is useful only insofar as those techniques are adopted by statistical agencies. For technical experts in disclosure limitation to be successful, they are likely to need to interact with the appropriate statistical offices. This paper discusses just such a successful interaction in the United States.


2006 /  2005   /   2004   /   2003PDF