Michigan State University
Minimum distance estimation on regression models with dependent errors and goodness of fit test of errors
Abstract
dc:descriptionThis dissertation consists of three chapters. The rst chapter introduces the models under consideration and motivates problems of interest. A brief literature review is also provided in this chapter. The second chapter investigates minimum distance estimators of the parameters in the linear regression model with dependent errors: autoregressive errors and panel data errors. Asymptotic distributional properties of these estimators are discussed. A simulation study that compares the performance of some of these minimum distance estimators with Gaussianmaximum likelihood, the generalized least squares, and the ordinary least squares estimators is also included. This simulation shows the superiority of the minimum distance estimator over the other estimators.The third chapter compares two asymptotic distribution free methods for tting an error distribution in the one sample location-scale model: Khmaladze transformation and empirical likelihood methods. The comparison is made from the perspective of empirical level and power obtained from simulations. When testing for normal and logistic null distributions, we try various alternative distributions and nd that Khmaladze transformation method has better power in most cases.
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Kim, Jiwoong
- Contributors dc:contributor
-
- Koul, Hira L.
- Hayes, Daniel
- Lim, Chae Young
- Huebner, Marianne
Subjects
dc:subject × 3Rights
dc:rights- Statement dc:rights
-
- In Copyright
- Language dc:language
- English
Identifiers
dc:identifier.*- Identifier
-
etd:4075
isbn:9781369022384
isbn:1369022387
oclc:961360113
umi:10146940
local:Kim_grad.msu_0128D_14797 - OAI record oai:identifier
- https://d.lib.msu.edu/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai%3Ad.lib.msu.edu%3Aetd_4075