Dokument: Essays in Panel Data Econometrics
| Titel: | Essays in Panel Data Econometrics | |||||||
| URL für Lesezeichen: | https://docserv.uni-duesseldorf.de/servlets/DocumentServlet?id=57800 | |||||||
| URN (NBN): | urn:nbn:de:hbz:061-20211021-152733-9 | |||||||
| Kollektion: | Dissertationen | |||||||
| Sprache: | Englisch | |||||||
| Dokumententyp: | Wissenschaftliche Abschlussarbeiten » Dissertation | |||||||
| Medientyp: | Text | |||||||
| Autor: | Czarnowske, Daniel [Autor] | |||||||
| Dateien: |
| |||||||
| Beitragende: | Prof. Dr. Heiß, Florian [Gutachter] Prof. Dr. Stiebale, Joel [Gutachter] | |||||||
| Dewey Dezimal-Klassifikation: | 300 Sozialwissenschaften, Soziologie » 330 Wirtschaft | |||||||
| Beschreibung: | A major advantage of panel data is that they allow researchers to control for unobserved heterogeneity in their empirical analyses. Roughly speaking, researchers often choose between two models: unobserved effects models, which assume that the idiosyncratic error term can be decomposed into unobserved heterogeneity and a residual idiosyncratic error term, and varying coefficients models, which additionally allow slope parameter heterogeneity. The availability of comprehensive and especially long panel data, i. e. large 𝑇-panels, offers new opportunities to draw inference from both types of models but also poses new challenges.
In my thesis, I analyze existing inference methods and develop new inference methods for large 𝑇-panels. In Chapter 2 and 4, I examine how unbalancedness affects the asymptotic properties of two estimators for unobserved effects models. More precisely, I analyze the bias-corrected estimators of Fernández-Val and Weidner (2016), for fixed effects binary choice models, and the interactive fixed effects estimator of Bai (2009). The asymptotic properties for both estimators were derived for balanced panels. In Chapter 3, I extend the generic inference method of Chernozhukov, Fernández-Val, and Weidner (2020) for distribution regression models with unobserved effects. More specifically, I broaden its applicability to panel data applications with weakly exogenous regressors. In Chapter 5, I propose a novel estimation procedure based on the classifier-Lasso of Su, Shi, and Phillips (2016) to identify latent firm heterogeneity, i. e. slope parameter heterogeneity, in production functions. | |||||||
| Lizenz: |  Urheberrechtsschutz | |||||||
| Fachbereich / Einrichtung: | Wirtschaftswissenschaftliche Fakultät » Statistik und Ökonometrie | |||||||
| Dokument erstellt am: | 21.10.2021 | |||||||
| Dateien geändert am: | 21.10.2021 | |||||||
| Promotionsantrag am: | 07.06.2021 | |||||||
| Datum der Promotion: | 05.10.2021 |
