Advanced

The small sample properties of the reset test as applied to systems of equations

Shukur, G and Edgerton, David LU (2002) In Journal of Statistical Computation and Simulation 72(12). p.909-924
Abstract
The RESET test for functional misspecification is generalised to cover systems of equations, and the properties of 7 versions are studied using Monte Carlo methods. The Rao F -test clearly exhibits the best performance as regards correct size, whilst the commonly used LRT (uncorrected for degrees-of-freedom), and LM and Wald tests (both corrected and uncorrected) behave badly even in single equations. The Rao test exhibits correct size even in ten equation systems, which is better than previous research concerning autocorrelation tests. The power of the test is low, however, when the number of equations grows and the correlation between the omitted variables and the RESET proxies is small.
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
small, tests of functional misspecification, systems of equations, sample properties, Monte Carlo methods
in
Journal of Statistical Computation and Simulation
volume
72
issue
12
pages
909 - 924
publisher
Taylor & Francis
external identifiers
  • wos:000179147700002
  • scopus:0036896546
ISSN
1563-5163
DOI
10.1080/00949650214678
language
English
LU publication?
yes
id
b7e4ad6f-c364-459e-ba11-0ca1ab95f0f6 (old id 324187)
date added to LUP
2007-11-13 15:21:55
date last changed
2017-02-26 04:14:01
@article{b7e4ad6f-c364-459e-ba11-0ca1ab95f0f6,
  abstract     = {The RESET test for functional misspecification is generalised to cover systems of equations, and the properties of 7 versions are studied using Monte Carlo methods. The Rao F -test clearly exhibits the best performance as regards correct size, whilst the commonly used LRT (uncorrected for degrees-of-freedom), and LM and Wald tests (both corrected and uncorrected) behave badly even in single equations. The Rao test exhibits correct size even in ten equation systems, which is better than previous research concerning autocorrelation tests. The power of the test is low, however, when the number of equations grows and the correlation between the omitted variables and the RESET proxies is small.},
  author       = {Shukur, G and Edgerton, David},
  issn         = {1563-5163},
  keyword      = {small,tests of functional misspecification,systems of equations,sample properties,Monte Carlo methods},
  language     = {eng},
  number       = {12},
  pages        = {909--924},
  publisher    = {Taylor & Francis},
  series       = {Journal of Statistical Computation and Simulation},
  title        = {The small sample properties of the reset test as applied to systems of equations},
  url          = {http://dx.doi.org/10.1080/00949650214678},
  volume       = {72},
  year         = {2002},
}