Bitte verwenden Sie diesen Link, um diese Publikation zu zitieren, oder auf sie als Internetquelle zu verweisen: https://hdl.handle.net/10419/171854 
Erscheinungsjahr: 
2015
Quellenangabe: 
[Journal:] Econometrics [ISSN:] 2225-1146 [Volume:] 3 [Issue:] 4 [Publisher:] MDPI [Place:] Basel [Year:] 2015 [Pages:] 719-732
Verlag: 
MDPI, Basel
Zusammenfassung: 
This paper proposes a methodology to incorporate bivariate models in numerical computations of counterfactual distributions. The proposal is to extend the works of Machado and Mata (2005) and Melly (2005) using the grid method to generate pairs of random variables. This contribution allows incorporating the effect of intra-household decision making in counterfactual decompositions of changes in income distribution. An application using data from five latin american countries shows that this approach substantially improves the goodness of fit to the empirical distribution. However, the exercise of decomposition is less conclusive about the performance of the method, which essentially depends on the sample size and the accuracy of the regression model.
Schlagwörter: 
counterfactual distributions
quantile regression
numeric integration
grid method
labor market
income distribution
JEL: 
C13
C14
C15
C31
Persistent Identifier der Erstveröffentlichung: 
Creative-Commons-Lizenz: 
cc-by Logo
Dokumentart: 
Article

Datei(en):
Datei
Größe
471.88 kB





Publikationen in EconStor sind urheberrechtlich geschützt.