Dealing with censored earnings in register data
Dealing with censored earnings in register data
Earnings are often top-coded (right-censored) in administrative registers. The censoring threshold in the case of Germany is the limit value for social security contributions, leading to a substantial fraction of censoring: For example, about 12 % of male workers in West Germany are affected, rising to above 30 % for highly educated prime-aged workers. This missing right tail of the earnings distribution constitutes a major problem for researchers studying earnings inequality and top incomes. We overcome this challenge by taking a distributional approach and semi-parametrically modelling the right tail as being Pareto-like. Non-censored earnings survey data matched to administrative records, derived from the SOEP-RV project, let us operate in a laboratory-like setting in which the targets are known. Our approach outperforms alternative imputation methods based on Tobit regressions.
SOEP-RV, extreme value index, heavy-tailed distribution, imputation, right-censored earnings, top-coding
Beckmannshagen, Mattis
d0868955-a686-47f9-aecc-bd788d3163bd
König, Johannes
ccd256ac-c174-4f00-ad7b-94d954d27342
Retter, Isabella
4a990621-4f93-45a2-a524-7d8f5a1b249f
Schluter, Christian
ae043254-4cc4-48aa-abad-56a36554de2b
Schröder, Carsten
6c7c08bb-6763-47fd-88bc-29551d469c1c
Tchokni, Yogam
ade01664-70dd-4e81-83b5-2561825c6515
Beckmannshagen, Mattis
d0868955-a686-47f9-aecc-bd788d3163bd
König, Johannes
ccd256ac-c174-4f00-ad7b-94d954d27342
Retter, Isabella
4a990621-4f93-45a2-a524-7d8f5a1b249f
Schluter, Christian
ae043254-4cc4-48aa-abad-56a36554de2b
Schröder, Carsten
6c7c08bb-6763-47fd-88bc-29551d469c1c
Tchokni, Yogam
ade01664-70dd-4e81-83b5-2561825c6515
Beckmannshagen, Mattis, König, Johannes, Retter, Isabella, Schluter, Christian, Schröder, Carsten and Tchokni, Yogam
(2025)
Dealing with censored earnings in register data.
Jahrbücher für Nationalökonomie und Statistik.
(doi:10.1515/jbnst-2024-0037).
Abstract
Earnings are often top-coded (right-censored) in administrative registers. The censoring threshold in the case of Germany is the limit value for social security contributions, leading to a substantial fraction of censoring: For example, about 12 % of male workers in West Germany are affected, rising to above 30 % for highly educated prime-aged workers. This missing right tail of the earnings distribution constitutes a major problem for researchers studying earnings inequality and top incomes. We overcome this challenge by taking a distributional approach and semi-parametrically modelling the right tail as being Pareto-like. Non-censored earnings survey data matched to administrative records, derived from the SOEP-RV project, let us operate in a laboratory-like setting in which the targets are known. Our approach outperforms alternative imputation methods based on Tobit regressions.
Text
10.1515_jbnst-2024-0037
- Version of Record
More information
Accepted/In Press date: 7 April 2025
e-pub ahead of print date: 23 May 2025
Keywords:
SOEP-RV, extreme value index, heavy-tailed distribution, imputation, right-censored earnings, top-coding
Identifiers
Local EPrints ID: 502424
URI: http://eprints.soton.ac.uk/id/eprint/502424
ISSN: 0021-4027
PURE UUID: 212bf06c-9ad4-4552-85b3-1581f8e48567
Catalogue record
Date deposited: 25 Jun 2025 16:51
Last modified: 19 Sep 2025 16:53
Export record
Altmetrics
Contributors
Author:
Mattis Beckmannshagen
Author:
Johannes König
Author:
Isabella Retter
Author:
Carsten Schröder
Author:
Yogam Tchokni
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics