|
Activity Number:
|
273
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, August 5, 2008 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Business and Economics Statistics Section
|
| Abstract - #301224 |
|
Title:
|
Multiple Imputation Approaches for Right-Censored Wages in the German IAB Employment Register
|
|
Author(s):
|
Thomas Buettner*+ and Susanne Rässler
|
|
Companies:
|
Institute for Employment Research and Otto-Friedrich University Bamberg
|
|
Address:
|
Regensburger Str. 104, Nuremberg, International, 90480, Germany
|
|
Keywords:
|
multiple imputation ; missing data ; censored wage data ; simulation study
|
|
Abstract:
|
Right-censored wages are very common with administrative data from social security systems like the IAB employment register, which is based on the data of the German unemployment insurance. In order to be able to analyze wages with this register, the German Institute for Employment Research (IAB) is using multiple imputation approaches to impute the missing wage information by draws of a random variable from a truncated distribution based on Markov chain Monte Carlo techniques. In addition, we suggest a new multiple imputation method based on GLS estimation which does not presume homoscedasticity of the residuals. In a simulation study, we use uncensored wage information from an income survey (German Structure of Earnings Survey, GSES) to compare different imputation approaches in order to confirm the necessity as well as the validity of the new approach.
|
