This file is part of IDEAS, which uses RePEc data


[ Papers | Articles | Software | Books | Chapters | Authors | Institutions | JEL Classification | NEP reports | Search | New papers by email | Author registration | Rankings | Volunteers | FAQ | Blog | Help! ]

Simulation-Based Finite-Sample Tests for Heteroskedasticity and ARCH Effects

Author info | Abstract | Publisher info | Download info | Related research | Statistics
Author Info
Jean-Thomas Bernard
Jean-Marie Dufour ()
Ian Genest
Lynda Khalaf

Additional information is available for the following registered author(s):

Abstract

A wide range of tests for heteroskedasticity have been proposed in the econometric and statistics literatures. Although a few exact homoskedasticity tests are available, the commonly employed procedures are quite generally based on asymptotic approximations which may not provide good size control in finite samples. There has been a number of recent studies that seek to improve the reliability of common heteroskedasticity tests using Edgeworth, Bartlett, jackknife and bootstrap methods. Yet the latter remain approximate. In this paper, we describe a solution to the problem of controlling the size of homoskedasticity tests in linear regression contexts. We study procedures based on the standard test statistics [e.g., the Goldfeld-Quandt, Glejser, Bartlett, Cochran, Hartley, Breusch-Pagan-Godfrey, White and Szroeter criteria] as well as tests for autoregressive conditional heteroskedasticity (ARCH-type models). We also suggest several extensions of the existing procedures (sup-type or combined test statistics) to allow for unknown breakpoints in the error variance. We exploit the technique of Monte Carlo tests to obtain provably exact p-values, for both the standard and the new tests suggested. We show that the MC test procedure conveniently solves the intractable null distribution problem, in particular those raised by the sup-type and combined test statistics as well as (when relevant) unidentified nuisance parameter problems under the null hypothesis. The method proposed works in exactly the same way with both Gaussian and non-Gaussian disturbance distributions [such as heavy-tailed or stable distributions]. The performance of the procedures is examined by simulation. The Monte Carlo experiments conducted focus on: (1) ARCH, GARCH and ARCH-in-mean alternatives; (2) the case where the variance increases monotonically with: (i) one exogenous variable, and (ii) the mean of the dependent variable; (3) grouped heteroskedasticity; (4) breaks in variance at unknown points. We find that the proposed tests achieve perfect size control and have good power.

Un grand éventail de tests d'hétéroskédasticité a été proposé en économétrie et en statistique. Bien qu'il existe quelques tests d'homoskédasticité exacts, les procédures couramment utilisées sont généralement fondées sur des approximations asymptotiques qui ne procurent pas un bon contrôle du niveau dans les échantillons finis. Plusieurs études récentes ont tenté d'améliorer la fiabilité des tests d'hétéroskédasticité usuels, sur base de méthodes de type Edgeworth, Bartlett, jackknife et bootstrap. Cependant, ces méthodes demeurent approximatives. Dans cet article, nous décrivons une solution au problème de contrôle du niveau des tests d'homoskédasticité dans les modèles de régression linéaire. Nous étudions des procédures basées sur les critères de test standards [e.g., les critères de Goldfeld-Quandt, Glejser, Bartlett, Cochran, Hartley, Breusch-Pagan-Godfrey, White et Szroeter], de même que des tests pour l'hétéroskédasticité autorégressive conditionnelle (les modèles de type ARCH). Nous suggérons plusieurs extensions des procédures usuelles (les statistiques de type-sup ou combinées) pour tenir compte de points de ruptures inconnus dans la variance des erreurs. Nous appliquons la technique des tests de Monte Carlo (MC) de façon à obtenir des seuils de signification marginaux (les valeurs-p) exacts, pour les test usuels et les nouveaux tests que nous proposons. Nous démontrons que la procédure de MC permet de résoudre les problèmes des distributions compliquées sous l'hypothèse nulle, en particulier ceux associés aux statistiques de type-sup, aux statistiques combinées et aux paramètres de nuisance non-identifiés sous l'hypothèse nulle. La méthode proposée fonctionne exactement de la même manière en présence de lois Gaussiennes et non-Gaussiennes [comme par exemple les lois aux queues épaisses ou les lois stables]. Nous évaluons la performance des procédures proposées par simulation. Les expériences de Monte Carlo que nous effectuons portent sur: (1) les alternatives de type ARCH, GARCH and ARCH-en-moyenne; (2) le cas où la variance augmente de manière monotone en fonction: (i) d'une variable exogène, et (ii) de la moyenne de la variable dépendante; (3) l'hétéroskédasticité groupée; (4) les ruptures en variance à des points inconnus. Nos résultats montrent que les tests proposés permettent de contrôler parfaitement le niveau et ont une bonne puissance.

Download Info
To download:

If you experience problems downloading a file, check if you have the proper application to view it first. Information about this may be contained in the File-Format links below. In case of further problems read the IDEAS help page. Note that these files are not on the IDEAS site. Please be patient as the files may be large.

File URL: http://www.cirano.qc.ca/pdf/publication/2001s-25.pdf
File Format: application/pdf
File Function:
Download Restriction: no

Publisher Info
Paper provided by CIRANO in its series CIRANO Working Papers with number 2001s-25.

Download reference. The following formats are available: HTML (with abstract), plain text (with abstract), BibTeX, RIS (EndNote, RefMan, ProCite), ReDIF
Length:
Date of creation: 01 Apr 2001
Date of revision:
Handle: RePEc:cir:cirwor:2001s-25

Contact details of provider:
Postal: 2020 rue University, 25e �tage, Montr�al, Qu�c, H3A 2A5
Phone: (514) 985-4000
Fax: (514) 985-4039
Email:
Web page: http://www.cirano.qc.ca/
More information through EDIRC

For technical questions regarding this item, or to correct its listing, contact: (Webmaster).

Related research
Keywords: Heteroskedasticity; homoskedasticity; linear regression; Monte Carlo test; exact test; finite-sample test; specification test; ARCH; GARCH; ARCH in mean; stable distribution; structural stability; hétéroskédasticité; homoskédasticité; régression linéaire; test de Monte Carlo; test exact; test valide en échantillon fini; test de spécification; ARCH; GARCH; ARCH-en-moyenne; distribution stable; stabilité structurelle;

Other versions of this item:

Find related papers by JEL classification:
C12 - Mathematical and Quantitative Methods - - Econometric and Statistical Methods: General - - - Hypothesis Testing
C15 - Mathematical and Quantitative Methods - - Econometric and Statistical Methods: General - - - Statistical Simulation Methods
C2 - Mathematical and Quantitative Methods - - Single Equation Models; Single Variables
C52 - Mathematical and Quantitative Methods - - Econometric Modeling - - - Model Evaluation and Testing
C22 - Mathematical and Quantitative Methods - - Single Equation Models; Single Variables - - - Time-Series Models; Dynamic Quantile Regressions

References listed on IDEAS
Please report citation or reference errors to , or , if you are the registered author of the cited work, log in to your RePEc Author Service profile, click on "citations" and make appropriate adjustments.:

  1. Jean-Marie Dufour & Jan F. Kiviet, 1998. "Exact Inference Methods for First-Order Autoregressive Distributed Lag Models," Econometrica, Econometric Society, vol. 66(1), pages 79-104, January.
    Other versions:
Full references

Cited by:
(explanations, Please report citation or reference errors to , or , if you are the registered author of the cited work, log in to your RePEc Author Service profile, click on "citations" and make appropriate adjustments.)

  1. DUFOUR, Jean-Marie & KHALAF, Lynda & BEAULIEU, Marie-Claude, 2003. "Finite-Sample Diagnostics for Multivariate Regressions with Applications to Linear Asset Pricing Models," Cahiers de recherche 06-2003, Centre interuniversitaire de recherche en économie quantitative, CIREQ. [Downloadable!]
    Other versions:
  2. Dufour, Jean-Marie & Beaulieu, Marie-Claude & Khalaf, Lynda, 2003. "Testing mean-variance efficiency in CAPM with possibly non-gaussian errors: an exact simulation-based approach," Discussion Paper Series 1: Economic Studies 2003,01, Deutsche Bundesbank, Research Centre. [Downloadable!]
    Other versions:
  3. Francq, Christian & Zakoian, Jean-Michel, 2008. "Testing the nullity of GARCH coefficients : correction of the standard tests and relative efficiency comparisons," MPRA Paper 16672, University Library of Munich, Germany. [Downloadable!]
    Other versions:
  4. Marie-Claude Beaulieu & Jean-Marie Dufour & Lynda Khalaf, 2005. "Exact Multivariate Tests of Asset Pricing Models with Stable Asymmetric Distributions," CIRANO Working Papers 2005s-03, CIRANO. [Downloadable!]
    Other versions:
  5. James G. MacKinnon, 2006. "Bootstrap Methods in Econometrics," Working Papers 1028, Queen's University, Department of Economics. [Downloadable!]
    Other versions:
  6. Lynda Khalaf & Maral Kichian, 2006. "Structural Change in Covariance and Exchange Rate Pass-Through: The Case of Canada," Working Papers 06-2, Bank of Canada. [Downloadable!]
  7. James G. MacKinnon, 2006. "Applications of the Fast Double Bootstrap," Working Papers 1023, Queen's University, Department of Economics. [Downloadable!]
  8. DUFOUR, Jean-Marie & KHALAF, Lynda & BEAULIEU, Marie-Claude, 2003. "Exact Skewness-Kurtosis Tests for Multivariate Normality and Goodness-of-Fit in Multivariate Regressions with Application to Asset Pricing Models," Cahiers de recherche 07-2003, Centre interuniversitaire de recherche en économie quantitative, CIREQ. [Downloadable!]
    Other versions:
  9. Christian Francq & Jean-Michel Zakoïan, 2006. "Inference in GARCH when some coefficients are equal to zero," Computing in Economics and Finance 2006 64, Society for Computational Economics. [Downloadable!]
  10. Eduardo Fé-Rodríguez & Chris D. Orme, 2009. "On the Sensitivity of Kernel-based Tests of Conditional Moment Restrictions," The School of Economics Discussion Paper Series 0912, Economics, The University of Manchester. [Downloadable!]
  11. Lynda Khalaf & Maral Kichian, 2003. "Testing the Stability of the Canadian Phillips Curve Using Exact Methods," Working Papers 03-7, Bank of Canada. [Downloadable!]
  12. Emma Iglesias & Jean Marie Dufour, 2004. "Finite Sample and Optimal Inference in Possibly Nonstationary ARCH Models with Gaussian and Heavy-Tailed Errors," Econometric Society 2004 North American Summer Meetings 161, Econometric Society. [Downloadable!]
Statistics
Access and download statistics

Did you know? All full texts are decentralized with the publishers, none reside on this server, thus making it possible to offer this service for free to all parties.

This page was last updated on 2009-11-20.


This information is provided to you by IDEAS at the Department of Economics, College of Liberal Arts and Sciences, University of Connecticut using RePEc data on a server sponsored by the Society for Economic Dynamics.