Bitte verwenden Sie diesen Link, um diese Publikation zu zitieren, oder auf sie als Internetquelle zu verweisen: https://hdl.handle.net/10419/119435 
Autor:innen: 
Erscheinungsjahr: 
2015
Schriftenreihe/Nr.: 
SFB 649 Discussion Paper No. 2015-016
Verlag: 
Humboldt University of Berlin, Collaborative Research Center 649 - Economic Risk, Berlin
Zusammenfassung: 
This paper proposes a test for missing at random (MAR). The MAR assumption is shown to be testable given instrumental variables which are independent of response given potential outcomes. A nonparametric testing procedure based on integrated squared distance is proposed. The statistic's asymptotic distribu- tion under the MAR hypothesis is derived. We demonstrate that our results can be easily extended to a test of missing completely at random (MCAR) and miss- ing completely at random conditional on covariates X (MCAR(X)). A Monte Carlo study examines finite sample performance of our test statistic. An empirical illustration concerns pocket prescription drug spending with missing values; we reject MCAR but fail to reject MAR.
Schlagwörter: 
incomplete data
missing-data mechanism
selection model
nonparametric hypothesis testing
consistent testing
instrumental variable
series estimation
JEL: 
C12
C14
Dokumentart: 
Working Paper

Datei(en):
Datei
Größe
504.8 kB





Publikationen in EconStor sind urheberrechtlich geschützt.