Skip to Main Content
Frequently Asked Questions
Submit an ETD
Global Search Box
Need Help?
Keyword Search
Participating Institutions
Advanced Search
School Logo
Files
File List
osu1211331801.pdf (657.3 KB)
ETD Abstract Container
Abstract Header
Essays on Dynamic Nonlinear Time Series Models and on Gender Inequality
Author Info
Basu, Deepankar
Permalink:
http://rave.ohiolink.edu/etdc/view?acc_num=osu1211331801
Abstract Details
Year and Degree
2008, Doctor of Philosophy, Ohio State University, Economics.
Abstract
My dissertation research has two distinct foci: one, studying problems of estimation and inference in dynamic nonlinear econometric models (first three chapters); and two, studying issues related to the problem of gender inequality in developing countries (last two chapters). The first chapter develops a framework to study dynamic discrete ordered choice behavior in situations where past choices directly influence current choices. I study such choice situations - in a time series setting - with a novel specification of a dynamic multinomial ordered choice model, where the latent variable is allowed to depend on lags of the choice variable. The second chapter highlights a potential problem in a binary choice duration model, where duration dependence is used as a regressor to capture persistence. I show that if such a model is extended to a situation where T is large, a problem of internal consistency will arise. This is because the dependent variable converges in probability to unity and the information matrix becomes singular. The third chapter develops a random threshold autoregressive (RTAR) model which generalizes the standard threshold autoregressive (TAR) models by allowing the threshold parameter in a two regime TAR model to be a random variable. I demonstrate that the RTAR model has a strictly stationarity solution which is also near epoch dependent. The fourth chapter develops and tests a simple model for the generation of gender inequality at the aggregate level in the absence of direct discrimination against girls. The results of the model is driven by son preference leading to male-preferring stopping rules on fertility decisions; this results in girls being born, on average, into larger families and as elder children within families. Both these generate disadvantageous position for girls at the aggregate level. In the backdrop of the debate on missing women (Oster, 2005), the fifth chapter of my dissertation empirically tests for two competing explanations of the increasing sex ratio at birth (SRB) in India: prevalence of hepatitis B and human intervention in the form of sex selective abortion or female infanticide. I find that human intervention rather than hepatitis B explains the increasing SRB in India.
Committee
Robert De Jong (Advisor)
Lung-Fei Lee (Committee Member)
Trevon Logan (Committee Member)
Pages
215 p.
Subject Headings
Economics
Keywords
nonlinear time series
;
gender inequality
;
missing women
Recommended Citations
Refworks
EndNote
RIS
Mendeley
Citations
Basu, D. (2008).
Essays on Dynamic Nonlinear Time Series Models and on Gender Inequality
[Doctoral dissertation, Ohio State University]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=osu1211331801
APA Style (7th edition)
Basu, Deepankar.
Essays on Dynamic Nonlinear Time Series Models and on Gender Inequality.
2008. Ohio State University, Doctoral dissertation.
OhioLINK Electronic Theses and Dissertations Center
, http://rave.ohiolink.edu/etdc/view?acc_num=osu1211331801.
MLA Style (8th edition)
Basu, Deepankar. "Essays on Dynamic Nonlinear Time Series Models and on Gender Inequality." Doctoral dissertation, Ohio State University, 2008. http://rave.ohiolink.edu/etdc/view?acc_num=osu1211331801
Chicago Manual of Style (17th edition)
Abstract Footer
Document number:
osu1211331801
Download Count:
725
Copyright Info
© 2008, all rights reserved.
This open access ETD is published by The Ohio State University and OhioLINK.