Accessibility Skip to Top Navigation Skip to Main Content Home  |  Change Text Size  |  Contact IRS  |  About IRS  |  Site Map  |  Español  |  Help  
magnifying glass
Advanced Search   Search Tips

SOI Tax Stats - Papers - 2002 American Statistical Association Conference

 

Return to Tax Stats home page

This section contains papers written by members of the Statistics of Income Division of IRS, and others, and presented at the 2002 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.

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

All papers are available as PDF files. A free Adobe Acrobat reader is available for download, if needed.

Title and Authors "Analysis of the 1998 Gift Tax Panel Study."
Martha Britton Eller and Tamara L. Rib; Statistics of Income, IRS.
Abstract

The Statistics of Income Division (SOI) of the Internal Revenue Service (IRS), initiated the 1998 Gift Tax Panel Study in order to examine gift tax revenue, and lifetime giving patterns of wealthy Americans. At the close of the study, SOI will have obtained and extracted data from post-1976 returns filed by donors included in the study that will facilitate research of lifetime giving and trust creation patterns and maintenance, among others.
Title and Authors "Assessing Disclosure Protection for a SOI Public Use File."
Marianne Winglee, Richard Valliant, Jay Clark, and Yunhee Lim (of Westat) and Michael Weber and Michael Strudler (of Statistics of Income, IRS).
Abstract This paper describes an evaluation of the disclosure protection methods for the Individual Tax Model Public Use File (PUF) released by the Statistics of Income (SOI) Program. Included is an introduction and motivation for this study, preparation of the PUF, options for sub-sampling high-income returns, and options for disclosure protection by micro-aggregation (grouping microdata in aggregates of three). In addition, the method and data used to measure disclosure risk and information loss as well as results and recommendations for further research are also discussed.
Title and Authors "Developing an Econometric Model for Measuring Tax Noncompliance Using Operational Audit Data."
Brian Erard (of B. Erard and Associates) and Chih-Chin Ho (of the IRS). 
Abstract Two reasons why the extent of noncompliance on returns subject to operational audits will tend to differ from the extent of noncompliance on non-examined returns are: 1) the two groups are likely to have important differences in their recorded return characteristics, 2) when deciding whether to proceed with an audit, IRS classifiers may employ information beyond what has been recorded from the return.  To control for these differences, both in recorded and unrecorded return characteristics, an econometric specification for the likelihood that a return will be audited is estimated jointly with a specification for noncompliance. 
 
Title and Authors "Electronic Dissemination of Internal Revenue Service Locality Data."  
Emily Gross and Beth Kilss; Statistics of Income, IRS.
Abstract This paper includes an overview of the IRS's Statistics of Income Program, a description of the types of locality income data the IRS offers, the electronic formats available, the years covered by the data, and the sources and limitations of the data. It also includes practical applications of the data as well as some interesting ongoing studies by some of SOI's customers. Innovations for the future are also highlighted.
Title and Authors "Evaluating the Effect of Sample Size Changes on Scoring System Performance Using Bootstraps and Random Samples."  
William Wong (of Statistics of Income, IRS) and Chih-Chin Ho (of the Internal Revenue Service).
Abstract Currently, the U. S. Internal Revenue Service (IRS) calculates a scoring formula for each return and uses it as one criterion to determine which returns to audit. Periodically, IRS updates this formula from a stratified random audit sample. The question was raised as to what size sample should be selected for the next audit sample. To answer that question, the authors examine the effect of increasing or decreasing the sample by 20 percent has on the scoring formula.
Title and Authors "How the Quality of Responses the IRS Provides to Taxpayer Inquiries is Measured."  
Kevin Cecco and Rachael Hoopengardner; Statistics of Income, IRS.
Abstract The IRS has been measuring the quality of the service it provides to taxpayer inquiries for at least fifteen different types of telephone customer service product lines since the late 1980's. This paper will describe the historical development and standardization of the quality measuring process, as well as the future of quality measurement within the IRS.
Title and Authors "Proxies in Administrative Records Surveys."  
Paul B. McMahon; Statistics of Income, IRS.
Abstract This paper will discuss the need for using proxies in administrative record surveys and will briefly describe the IRS's processing and the needs
of its' sponsors.  It will also examine the impact of the proxies on the three largest and longest running annual surveys in the Statistics of Income series, the Corporation Income Tax Returns, Individual Income Tax Returns, and Partnership Returns of Income.
Title and Authors "Salaries and Wages and Deferred Income, 1989-1999."  
Peter Sailer, Ellen Yau, Kurt Gurka, and Michael Weber; Statistics of Income, IRS.
Abstract This paper discusses trends in salaries and wages, as well as income deferred for retirement purposes, as reported for men and women in the United States between 1989 and 1999.
Title and Authors "Some New Tables of the Largest Root of a Matrix in Multivariate Analysis: A Computer Approach from 2 to 6."  
William W. Chen; Statistics of Income, IRS.
Abstract This paper discusses the distribution of the largest characteristic roots in multivariate analysis, when there are roots that range from 2 to 6. It also discusses, in detail, the algorithm used to create tables for this paper. In addition, it compares the K.C.S. Pillai method with its own and also discusses the advantage of its own approach.
Title and Authors "Using Auxiliary Information to Adjust for Non-Response in Weighting a Linked Sample of Administrative Records."  
Barry W. Johnson and Paul B. McMahon; Statistics of Income, IRS.
Abstract Federal estate tax returns are a rich source of information on the assets and liabilities associated with decedents, as well as data on beneficiaries of estates. When linked with income tax data for the decedents and their beneficiaries, the resulting data base provides a unique opportunity to study a variety of important economic issues relating to the transfer of wealth and the accumulation of capital.  In this paper, steps taken to weight the linked files are detailed.

2008 / 2007 / 2006 / 2005 / 2004 / 2003 / 2001 / 2000 / 1999 / 1998 / 1997 / 1993 / 1992

Return to Tax Stats home page

 


Page Last Reviewed or Updated: December 09, 2008