2002
DOI: 10.1016/s0304-4076(02)00108-2
|View full text |Cite
|
Sign up to set email alerts
|

Simulation based finite and large sample tests in multivariate regressions

Abstract: 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 mo… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
5

Citation Types

1
72
0
2

Year Published

2003
2003
2016
2016

Publication Types

Select...
4
2
2

Relationship

6
2

Authors

Journals

citations
Cited by 64 publications
(75 citation statements)
references
References 68 publications
1
72
0
2
Order By: Relevance
“…In this paper, we extend the results presented in Dufour and Khalaf (1998b) to the case of SURE systems, under both gaussian and non-gaussian disturbance distributions. Indeed the model considered here is an extension of the standard gaussian SURE model that allows for both gaussian and non-gaussian disturbance distribution, as long the latter is specified up an unknown linear transformation (or contemporaneous covariance matrix).…”
Section: Introductionmentioning
confidence: 57%
See 2 more Smart Citations
“…In this paper, we extend the results presented in Dufour and Khalaf (1998b) to the case of SURE systems, under both gaussian and non-gaussian disturbance distributions. Indeed the model considered here is an extension of the standard gaussian SURE model that allows for both gaussian and non-gaussian disturbance distribution, as long the latter is specified up an unknown linear transformation (or contemporaneous covariance matrix).…”
Section: Introductionmentioning
confidence: 57%
“…It has been shown however that, in finite samples, the asymptotic criteria are seriously biased towards overrejection, with the problem getting worse as the number of equations grows relative to the sample size; see, for example, Laitinen (1978), Meisner (1979), Bera, Byron and Jarque (1981), Theil and Fiebig (1985), and Dufour and Khalaf (1998b). Attempts to improve standard asymptotic tests include, in particular: (i) Bartlett-type corrections, and (ii) bootstrap and simulation-based methods.…”
Section: Introductionmentioning
confidence: 99%
See 1 more Smart Citation
“…From a methodological perspective, RR restrictions raise statistical challenges. Even with linear multivariate models, discrepancies between standard asymptotic and finite-sample distributions can be severe, due for example to high dimensionality; see Dufour and Khalaf (2002) and the references therein. Rank restrictions pose further identification non-regularities which can lead to the failure of standard asymptotics.…”
Section: Introductionmentioning
confidence: 99%
“…L'emploi de résultats de convergence dans les échantillons finis reste toutefois sujet à caution. 1 Afin d'obtenir des procédures dont la validité est démontrable à distance finie, nous avons récemment proposé d'appliquer la technique des tests de Monte Carlo dans différents problèmes économé-triques ; voir Dufour et Khalaf (2002b, 2002c, Dufour et al (2004), Dufour, Khalaf et Beaulieu (2002, 2003, et Dufour et Farhat (2001). Spécifiquement, nous montrons comment, sans recourir à la méthode de Bonferroni, on peut obtenir des tests induits exacts sur divers modèles paramétriques, possiblement non gaussiens, et même non-paramétriques.…”
Section: Introductionunclassified