Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/309236 
Year of Publication: 
2021
Citation: 
[Journal:] Comparative Population Studies (CPoS) [ISSN:] 1869-8999 [Volume:] 46 [Year:] 2021 [Pages:] 453-486
Publisher: 
Bundesinstitut für Bevölkerungsforschung (BiB), Wiesbaden
Abstract: 
The estimation of impact functions - that is the time-varying causal effect of a dichotomous treatment (e.g., marriage, divorce, parenthood) on outcomes (e.g., earnings, well-being, health) - has become a standard procedure in demographic applications. The basic methodology of estimating impact functions with panel data and fixed-effects regressions is now widely known. However, many researchers may not be fully aware of the methodological subtleties of the approach, which may lead to biased estimates of the impact function. In this paper, we highlight potential pitfalls and provide guidance on how to avoid these in practice. We demonstrate these issues with exemplary analyses, using data from the German Family Panel (pairfam) study and estimating the effect of motherhood on life satisfaction.
Subjects: 
Fixed effects regression
Impact functions
Motherhood
Negative weighting bias
pairfam
Panel data analysis
Persistent Identifier of the first edition: 
Creative Commons License: 
cc-by-sa Logo
Document Type: 
Article

Files in This Item:
File
Size





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.