Essays in econometric theory

Research output: ThesisDoctoral ThesisScientific

9 Downloads (Pure)

Abstract

This dissertation contains three essays in the field of econometric theory. The first essay focuses on single-index binary choice regression model. A new class of semiparametric estimators based on indirect inference is proposed to estimate the regression coefficients. It is demonstrated that the proposed estimation methodology is feasible under weak distributional assumptions and robust to misclassification of responses. The second essay examines the estimation of threshold regression models with dependent data. In particular, the integrated difference kernel estimator is used as a plug-in estimator which facilitates estimation of a wide array of parametric, semiparametric and nonparametric threshold regression models. The third essay studies the identification and estimation of non separable panel data models with index structure and correlated random effects. The parameter vectors of interest are shown to be identified up to scale and could be estimated by a generalized method of moments estimator with moment conditions based on average derivative and outer product of the difference of derivatives of the regression function.
Original languageEnglish
QualificationDoctor of Philosophy
Awarding Institution
  • Tilburg University
Supervisors/Advisors
  • Melenberg, Bertrand, Promotor
  • Cizek, Pavel, Promotor
Award date20 May 2019
Place of PublicationTilburg
Publisher
Print ISBNs978 90 5668 587 4
Publication statusPublished - 2019

Fingerprint

Econometrics
Regression model
Derivatives
Threshold regression
Coefficients
Random effects
Kernel estimator
Moment conditions
Generalized method of moments estimator
Methodology
Misclassification
Integrated
Estimator
Semiparametric estimators
Indirect inference
Binary choice

Cite this

Sadikoglu, S. (2019). Essays in econometric theory. Tilburg: CentER, Center for Economic Research.
Sadikoglu, Serhan. / Essays in econometric theory. Tilburg : CentER, Center for Economic Research, 2019. 162 p.
@phdthesis{99d83644f9dc49e3a4e15ca8a8d3f784,
title = "Essays in econometric theory",
abstract = "This dissertation contains three essays in the field of econometric theory. The first essay focuses on single-index binary choice regression model. A new class of semiparametric estimators based on indirect inference is proposed to estimate the regression coefficients. It is demonstrated that the proposed estimation methodology is feasible under weak distributional assumptions and robust to misclassification of responses. The second essay examines the estimation of threshold regression models with dependent data. In particular, the integrated difference kernel estimator is used as a plug-in estimator which facilitates estimation of a wide array of parametric, semiparametric and nonparametric threshold regression models. The third essay studies the identification and estimation of non separable panel data models with index structure and correlated random effects. The parameter vectors of interest are shown to be identified up to scale and could be estimated by a generalized method of moments estimator with moment conditions based on average derivative and outer product of the difference of derivatives of the regression function.",
author = "Serhan Sadikoglu",
note = "CentER Dissertation Series Volume: 586",
year = "2019",
language = "English",
isbn = "978 90 5668 587 4",
volume = "586",
series = "CentER Dissertation Series",
publisher = "CentER, Center for Economic Research",
school = "Tilburg University",

}

Sadikoglu, S 2019, 'Essays in econometric theory', Doctor of Philosophy, Tilburg University, Tilburg.

Essays in econometric theory. / Sadikoglu, Serhan.

Tilburg : CentER, Center for Economic Research, 2019. 162 p.

Research output: ThesisDoctoral ThesisScientific

TY - THES

T1 - Essays in econometric theory

AU - Sadikoglu, Serhan

N1 - CentER Dissertation Series Volume: 586

PY - 2019

Y1 - 2019

N2 - This dissertation contains three essays in the field of econometric theory. The first essay focuses on single-index binary choice regression model. A new class of semiparametric estimators based on indirect inference is proposed to estimate the regression coefficients. It is demonstrated that the proposed estimation methodology is feasible under weak distributional assumptions and robust to misclassification of responses. The second essay examines the estimation of threshold regression models with dependent data. In particular, the integrated difference kernel estimator is used as a plug-in estimator which facilitates estimation of a wide array of parametric, semiparametric and nonparametric threshold regression models. The third essay studies the identification and estimation of non separable panel data models with index structure and correlated random effects. The parameter vectors of interest are shown to be identified up to scale and could be estimated by a generalized method of moments estimator with moment conditions based on average derivative and outer product of the difference of derivatives of the regression function.

AB - This dissertation contains three essays in the field of econometric theory. The first essay focuses on single-index binary choice regression model. A new class of semiparametric estimators based on indirect inference is proposed to estimate the regression coefficients. It is demonstrated that the proposed estimation methodology is feasible under weak distributional assumptions and robust to misclassification of responses. The second essay examines the estimation of threshold regression models with dependent data. In particular, the integrated difference kernel estimator is used as a plug-in estimator which facilitates estimation of a wide array of parametric, semiparametric and nonparametric threshold regression models. The third essay studies the identification and estimation of non separable panel data models with index structure and correlated random effects. The parameter vectors of interest are shown to be identified up to scale and could be estimated by a generalized method of moments estimator with moment conditions based on average derivative and outer product of the difference of derivatives of the regression function.

M3 - Doctoral Thesis

SN - 978 90 5668 587 4

VL - 586

T3 - CentER Dissertation Series

PB - CentER, Center for Economic Research

CY - Tilburg

ER -

Sadikoglu S. Essays in econometric theory. Tilburg: CentER, Center for Economic Research, 2019. 162 p. (CentER Dissertation Series).