JSM 2012 Home

JSM 2012 Online Program

The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.

Online Program Home

Abstract Details

Activity Number: 440
Type: Invited
Date/Time: Wednesday, August 1, 2012 : 8:30 AM to 10:20 AM
Sponsor: Section on Survey Research Methods
Abstract - #303872
Title: Multiple Imputation for Correcting Rounding Errors from Heaped Income Data
Author(s): Hans Kiesl*+ and Joerg Drechsler
Companies: Regensburg University of Applied Sciences and German Institute for Employment Research (IAB)
Address: Fakultaet Informatik/Mathematik, Regensburg, International, 93025, Germany
Keywords: Multiple Imputation ; Heaping ; Income data ; Rounding
Abstract:

Questions on income in surveys are prone to two sources of errors. First, income is considered sensitive information and item nonresponse rates on income questions in general tend to be higher than nonresponse rates for other non-sensitive questions. Second, respondents tend to round their income. Depending on the respondent and on the value of income, the magnitude of rounding can range from rounding to the closest 5 dollar value to rounding to the closest 5000 dollar value. This kind of measurement error (often called "heaping") may lead to bias in non-linear statistics like the median income or the poverty rate. In this paper we propose a two stage imputation strategy that estimates the posterior probability for rounding given the observed values on the first stage and multiply re-imputes the income values given the rounding probabilities on the second stage. Missing values are also imputed at this stage. We provide a simulation study illustrating that the proposed multiple imputation model can help overcome the possible negative effects of heaping. We also present results based on data from the German panel survey "Labor Market and Social Security".


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 2012 program




2012 JSM Online Program Home

For information, contact jsm@amstat.org or phone (888) 231-3473.

If you have questions about the Continuing Education program, please contact the Education Department.