nonparametric instrumental variable methods , duration analysis , policy evaluation , constrained estimation , class size , test score
Abstract:
In my PhD thesis, I develop nonparametric instrumental variable methods for two different settings. First, in a duration setup, I develop an approach to deal with dynamic and static selection, two important problems in econometric research. The method can deal with censoring and is based on a comparison of cohorts. I also construct a framework to analyse the static endogeneity of a model. In addition to these identification results, I also provide the necessary estimation procedures and derive their asymptotic properties. Second, I show that a class of constrained penalised minimum distance estimators can be viewed as projections. In a simulation, I study their properties under monotonicity constraint. I construct a test for monotonicity and use it to analyse the effect of class size on test scores in a Minnesota dataset. The effect is revealed to be non-monotone. I suggest an economic approach to explain this result.
Translation of the title:
Aufsätze in Instrumentalvariablen-Regressionsanalyse
(German)
Dieser Eintrag ist Teil der Universitätsbibliographie.
Das Dokument wird vom Publikationsserver der Universitätsbibliothek Mannheim bereitgestellt.
![[img]](https://madoc.bib.uni-mannheim.de/style/images/fileicons/application_pdf.png)
Search Authors in