In Chapter 1, I propose a novel, nonparametric estimator of truncated conditional expectation functions. It is based on local linear methods and an orthogonal moment equation. I allow for the truncation quantile level to be estimated from the data.
Chapter 2 is joint work with Christoph Rothe. It concerns estimation and inference in fuzzy regression discontinuity designs with a manipulated running variable. In the manipulation framework of Gerard, Rokkanen, and Rothe (2020), we derive alternative, non-sharp bounds on the treatment effect of interest that can be conveniently used for conducting inference.
Chapter 3 is joint work with Claudia Noack and Christoph Rothe. We propose a novel class of covariate-adjusted regression discontinuity estimators that can have a smaller variance than the estimators used in the literature. Our procedure accommodates a wide range of covariate adjustments under mild conditions, and it is easily applicable based on existing estimation and inference routines.
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)
Suche Autoren in