Suchergebnisse

AbstractIn many fields of economics, and also in other disciplines, it is hard to justify the assumption that the random error terms in regression models are uncorrelated. It seems more plausible to assume that they are correlated within clusters, such as geographical areas or time periods, but uncorrelated across clusters. It has therefore become very popular to use "clustered" standard errors, which are robust against arbitrary patterns of within‐cluster variation and covariation. Conventional methods for inference using clustered standard errors work very well when the model is correct and the data satisfy certain conditions, but they can produce very misleading results in other cases. This paper discusses some of the issues that users of these methods need to be aware of.

The astonishing increase in computer performance over the past two decades has made it possible for economists to base many statistical inferences on simulated, or bootstrap, distributions rather than on distributions obtained from asymptotic theory. In this paper, I review some of the basic ideas of bootstrap inference. I discuss Monte Carlo tests, several types of bootstrap test, and bootstrap confidence intervals. Although bootstrapping often works well, it does not do so in every case. Inférence par la méthode d'auto–amorçage (bootstrap) en économétrie. L'incroyable accroissement dans la puissance des ordinateurs au cours des deux dernières décennies a permis aux économistes de fonder plusieurs inférences sur des distributions simulées, ou obtenues par auto–amorçage, plutôt que sur des distributions obtenues par la théorie aymptotique. Dans ce texte, l'auteur passe en revue quelques–unes des idées de base de l'inférence par la méthode d'auto–amorçage. Le texte discute aussi des tests de Monte Carlo, de divers types de tests et des intervalles de confiance obtenus par la méthode d'auto–amorçage. Même si le processus d'auto–amorçage fonctionne souvent bien, cela n'est pas toujours le cas.

Simple techniques for the graphical display of simulation evidence concerning the size and power of hypothesis tests are developed and illustrated. Three types of figures—called P value plots, P value discrepancy plots and size–power curves—are discussed. Some Monte Carlo experiments on the properties of alternative forms of the information matrix test for linear regression models and probit models are used to illustrate these figures. Tests based on the outer‐product‐of‐the‐gradient (OPG) regression generally perform much worse in terms of both size and power than efficient score tests.