Exact testing in multivariate regression

Stewart, Kenneth G.

doi:10.1080/07474939708800390

Cited by 41 publications

(44 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Asymptotic Wald, Lagrange multiplier and likelihood ratio tests are available and commonly employed in econometric applications of the MLR model; see Berndt and Savin (1977), Evans and Savin (1982), Breusch (1979), Renault (1993, 1995) and Stewart (1995Stewart ( , 1997. It has been shown, however, that in finite samples, these asymptotic criteria are seriously biased towards overrejection when the number of equations relative to the sample size is large (even moderately).…”

Section: Introductionmentioning

confidence: 99%

“…Further evidence for the case of multivariate tests in capital asset pricing models (CAPM) is also available; see Stambaugh (1982), Jobson and Korkie (1982), Amsler and Schmidt (1985) and MacKinlay (1987). These and other references are discussed by Stewart (1997).…”

Section: Introductionmentioning

confidence: 99%

“…Examples of UL hypotheses include: (i) the case where identical transformations of the regression coefficients (within or across equations) are set to given values, and (ii) the hypothesis that a single parameter equals zero. For some recent exact results on tests of UL hypotheses, see Stewart (1997). Note however not all linear hypotheses can be put in UL form.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Simulation based finite and large sample tests in multivariate regressions

Dufour

Khalaf

2002

Journal of Econometrics

View full text Add to dashboard Cite

CIRANOLe CIRANO est un organisme sans but lucratif constitué en vertu de la Loi des compagnies du Québec. Le financement de son infrastructure et de ses activités de recherche provient des cotisations de ses organisationsmembres, d'une subvention d'infrastructure du ministère de la Recherche, de la Science et de la Technologie, de même que des subventions et mandats obtenus par ses équipes de recherche. CIRANO is a private non-profit organization incorporated under the Résumé / AbstractDans le contexte des modèles de régression multivariés (MLR), il est bien connu que les tests asymptotiques usuels tendent à rejeter trop souvent les hypothèse considérées. Dans cet article, nous proposons une méthode générale qui permet de construire des tests exacts pour des hypothèses possiblement non linéaires sur les coefficients de tels modèles. Pour le cas des hypothèse uniformes linéaires, nous présentons des résultats sur la distribution exacte de plusieurs statistiques de test usuelles. Ces dernières incluent le critère du quotient de vraisemblance (Wilks), de même que les critères de la trace et de la racine maximale. L'hypothèse de normalité des erreurs n'est pas requise pour la plupart des résultats présentés. Ceux-ci ont deux types de conséquences pour l'inférence statistique. Premièrement, l'invariance par rapport aux paramètres de nuisance signifie que l'on peut appliquer la technique des tests de Monte Carlo afin de construire des tests exacts pour les hypothèses uniformes linéaires. Deuxième-ment, nous montrons comment exploiter cette propriété afin d'obtenir des bornes sans paramètres de nuisance sur la distribution des statistiques de quotient de vraisemblance pour des hypothèses générales. Même si les bornes ne sont pas faciles à calculer par des moyens analytiques, on peut les simuler aisément et ainsi effectuer des tests de Monte Carlo à bornes. Nous présentons une expérience de simulation qui montre que ces bornes sont suffisamment serrées pour fournir des résultats concluants avec une forte probabilité. Nos résultats démontrent la valeur de ces bornes comme instrument à utiliser conjointement avec des méthodes d'inférence simulée plus traditionnelles (telles que le bootstrap paramétrique) que l'on peut appliquer lorsque le test à borne n'est pas concluant.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Simulation based finite and large sample tests in multivariate regressions

Dufour

Khalaf

2002

Journal of Econometrics

View full text Add to dashboard Cite

show abstract

“…Beyond this specific hypothesis class, it is well known that the LR statistic is not pivotal, even if the null hypothesis is linear. For further discussion of uniform linear hypotheses in MLR models, the reader may consult Berndt and Savin (1977), Stewart (1997) and Dufour and Khalaf (1998b). Let us now turn to the SURE model.…”

Section: Test Proceduresmentioning

confidence: 99%

“…These are relevant because the MLR model can be viewed as a special case of the SURE model where the regressor matrices for the different equations are identical. For reviews and further references on exact and asymptotic inference in MLR models, the reader may consult Rao (1973, Chapter 8), Anderson (1984, chapters 8 and 13), Kariya (1985), Stewart (1997) and Dufour and Khalaf (1998b). In particular, besides showing the inadequacy of various size-correction procedures (including Bartlett corrections) through simulation, we derived in Dufour and Khalaf (1998b) exact bounds on the null distribution of LR test statistics for possibly non-linear hypotheses on regression coefficients in MLR models.…”

Section: Introductionmentioning

confidence: 99%

Finite-Sample Simulation-Based Tests in Seemingly Unrelated Regressions

Dufour

Khalaf

2003

Computer-Aided Econometrics

View full text Add to dashboard Cite

In this paper, we propose finite and large sample likelihood based test procedures for possibly nonlinear hypotheses on the coefficients of SURE systems. Two complementary approaches are described. First, we propose an exact Monte Carlo bounds test based on the standard likelihood ratio criterion. Second, we consider alternative Monte Carlo tests which can be run whenever the bounds are not conclusive. These include, in particular, quasi-likelihood ratio criteria based on nonmaximum-likelihood estimators. Illustrative Monte Carlo experiments show that: (i) the bounds are sufficiently tight to yield conclusive results in a large proportion of cases, and (ii) the randomized procedures correct all the usual size distortions in such contexts. The procedures proposed are finally applied to test restrictions on a factor demand model.

show abstract

Bootstrap Hypothesis Testing

MacKinnon

2009

Handbook of Computational Econometrics

122

View full text Add to dashboard Cite

This paper surveys bootstrap and Monte Carlo methods for testing hypotheses in econometrics. Several different ways of computing bootstrap P values are discussed, including the double bootstrap and the fast double bootstrap. It is emphasized that there are many different procedures for generating bootstrap samples for regression models and other types of model. As an illustration, a simulation experiment examines the performance of several methods of bootstrapping the supF test for structural change with an unknown break point.

show abstract

Exact testing in multivariate regression

Cited by 41 publications

References 57 publications

Simulation based finite and large sample tests in multivariate regressions

Simulation based finite and large sample tests in multivariate regressions

Finite-Sample Simulation-Based Tests in Seemingly Unrelated Regressions

Bootstrap Hypothesis Testing

Contact Info

Product

Resources

About