This item is only available for download by members of the University of Illinois community. Students, faculty, and staff at the U of I may log in with your NetID and password to view the item. If you are trying to access an Illinois-restricted dissertation or thesis, you can request a copy through your library's Inter-Library Loan office or purchase a copy directly from ProQuest.
Permalink
https://hdl.handle.net/2142/85677
Description
Title
Essays in Nonparametric Econometrics
Author(s)
Morillo, Daniel Santiago
Issue Date
2000
Doctoral Committee Chair(s)
Koenker, Roger W.
Department of Study
Economics
Discipline
Economics
Degree Granting Institution
University of Illinois at Urbana-Champaign
Degree Name
Ph.D.
Degree Level
Dissertation
Keyword(s)
Statistics
Language
eng
Abstract
The work presented here is a collection of three self-contained chapters that explore various aspects of the computation and application of nonparametric methods in Econometrics. All three chapters are linked by the use of Quantile Regression ideas and techniques. The first chapter uses stochastic approximation techniques to develop an algorithm for recursive estimation of a general linear quantile regression model. The asymptotics of the proposed estimator are developed and it is shown that the asymptotic performance of the estimator is equivalent to that of the estimator obtained via standard linear programming methods. A Monte Carlo experiment shows that the proposed estimator is competitive with the standard linear-programming estimator for moderately large sample sizes. The second chapter presents an improvement on existing recursive regression methods for pricing American-type options. The central idea is to reduce bias and variance of existing estimators by combining two option value estimators both of them biased but in opposite direction. A Monte Carlo experiment demonstrates that the proposed method does indeed perform better than existing methods in simple log-normal case. A detailed empirical example uses Quantile regression to capture the dynamics of observed asset price data and to simulate the price paths used to computed option value estimates. Results give evidence that the modeling flexibility provided by Quantile Regression methods can result in pricing performance gains over the standard binomial method. Finally, the last chapter proposes a method for the analysis of income mobility that applies the permanent inequality measures of mobility to simulated data that can be constructed from estimates of the short-term dynamics of income. The method is thus able to track changes in mobility itself while remaining within the general welfare-based framework. Nonparametric quantile regression is used to obtain the transition quantile curves of the income process and then to simulate future income paths. The procedure is applied to income data from the U.S. and Germany. Results show evidence of a significant increase in mobility in the U.S. starting in the early 90's and also provide evidence of a positive relationship between government size and income mobility.
Use this login method if you
don't
have an
@illinois.edu
email address.
(Oops, I do have one)
IDEALS migrated to a new platform on June 23, 2022. If you created
your account prior to this date, you will have to reset your password
using the forgot-password link below.
