Files in this item

FilesDescriptionFormat

application/pdf

application/pdf9411756.pdf (3Mb)Restricted to U of Illinois
(no description provided)PDF

Description

Title:Hypothesis testing when a nuisance parameter is identified only under the alternative hypothesis
Author(s):Ra, Sungsup
Doctoral Committee Chair(s):Bera, Anil K.
Department / Program:Economics
Discipline:Economics
Degree Granting Institution:University of Illinois at Urbana-Champaign
Degree:Ph.D.
Genre:Dissertation
Subject(s):Economics, General
Economics, Theory
Abstract:When a nuisance parameter is unidentified under the null hypothesis, standard testing procedures cannot be applied due to the singularity of the information matrix. Probably best known examples are the problems of unknown change points and the mixtures of distributions in econometrics and statistics. Davies (1977, 1987) proposes a general solution to this type of problems.
In this dissertation, we study three applications: tests for parameter constancy, white noise against the autoregressive moving average (ARMA(1,1)) alternative, and autoregressive conditional heteroskedasticity in mean (ARCH-M) model. Davies' procedure and the conventional Lagrange multiplier (LM) test are applied, and find that Davies' test outperforms the LM test. However, despite of its generality, Davies' approach has several deficiencies to be implemented for more general cases and it is quite expensive computationally.
For testing for parameter constancy, a joint LM test for autocorrelation and heteroskedasticity is suggested as a simple alternative test to Davies' procedure. For testing white noise against ARMA(1,1), we implement a more exact and simplified version of Davies approach. Monte Carlo results indicate that both the joint LM test and the simplified version of Davies have good finite sample power properties.
Issue Date:1993
Type:Text
Language:English
URI:http://hdl.handle.net/2142/20246
Rights Information:Copyright 1993 Ra, Sungsup
Date Available in IDEALS:2011-05-07
Identifier in Online Catalog:AAI9411756
OCLC Identifier:(UMI)AAI9411756


This item appears in the following Collection(s)

Item Statistics

  • Total Downloads: 0
  • Downloads this Month: 0
  • Downloads Today: 0