Les méthodes du bootstrap dans les modèles de régression

Abstract

Bootstrap Methods in Regression Models by Emmanuel Flachaire In practice, we rarely know the true probability distribution of a test statistic and we generally base tests on its asymptotic distribution. If the sample size is not large enough, the asymptotic distribution could be a poor approximation of the true distribution. Consequently, tests based on it could be largely biased. Bootstrap methods yield a more accurate approximation of the distribution of a test statistic than the approximation obtained from the first-order asymptotic theory. Moreover, they provide a way of substituting computation for mathematical analysis when it proves hard to calculate the asymptotic distribution of an estimator or statistic. In this paper, we present a general methodology of the bootstrap in regression models.