Identification, Weak Instruments and Statistical Inference in Econometrics

We discuss statistical inference problems associated with identification and testability in econometrics, and we emphasize the common nature of the two issues. After reviewing the relevant statistical notions, we consider in turn inference in nonparametric models and recent developments on weakly identified models (or weak instruments). We point out that many hypotheses, for which test procedures are commonly proposed, are not testable at all, while some frequently used econometric methods are fundamentally inappropriate for the models considered. Such situations lead to ill-defined statistical problems and are often associated with a misguided use of asymptotic distributional results. Concerning nonparametric hypotheses, we discuss three basic problems for which such difficulties occur: (1) testing a mean (or a moment) under (too) weak distributional assumptions; (2) inference under heteroskedasticity of unknown form; (3) inference in dynamic models with an unlimited number of parameters. Concerning weakly identified models, we stress that valid inference should be based on proper pivotal functions —a condition not satisfied by standard Wald-type methods based on standard errors — and we discuss recent developments in this field, mainly from the viewpoint of building valid tests and confidence sets. The techniques discussed include alternative proposed statistics, bounds, projection, split-sampling, conditioning, Monte Carlo tests. The possibility of deriving a finite-sample distributional theory, robustness to the presence of weak instruments, and robustness to the specification of a model for endogenous explanatory variables are stressed as important criteria assessing alternative procedures.

Methods to Estimate Dynamic Stochastic General Equilibrium Models

This paper employs the one-sector Real Business Cycle model as a testing ground for four different procedures to estimate Dynamic Stochastic General Equilibrium (DSGE) models. The procedures are: 1 ) Maximum Likelihood, with and without measurement errors and incorporating Bayesian priors, 2) Generalized Method of Moments, 3) Simulated Method of Moments, and 4) Indirect Inference. Monte Carlo analysis indicates that all procedures deliver reasonably good estimates under the null hypothesis. However, there are substantial differences in statistical and computational efficiency in the small samples currently available to estimate DSGE models. GMM and SMM appear to be more robust to misspecification than the alternative procedures. The implications of the stochastic singularity of DSGE models for each estimation method are fully discussed.

Efficient and Non-Deteriorating Choice

We analyze collective choice procedures with respect to their rationalizability by means of profiles of individual preference orderings. A selection function is a generalization of a choice function where selected alternatives may depend on a reference (or status quo) alternative in addition to the set of feasible options. Given the number of agents n, a selection function satisfies efficient and non-deteriorating n-rationalizability if there exists a profile of n orderings on the universal set of alternatives such that the selected alternatives are (i) efficient for that profile, and (ii) at least as good as the reference option according to each individual preference. We analyze efficient and non-deteriorating collective choice in a general abstract framework and provide a characterization result given a universal set domain.

Bootstrapping Autoregressions with Conditional Heteroskedasticity of Unknown Form

Conditional heteroskedasticity is an important feature of many macroeconomic and financial time series. Standard residual-based bootstrap procedures for dynamic regression models treat the regression error as i.i.d. These procedures are invalid in the presence of conditional heteroskedasticity. We establish the asymptotic validity of three easy-to-implement alternative bootstrap proposals for stationary autoregressive processes with m.d.s. errors subject to possible conditional heteroskedasticity of unknown form. These proposals are the fixed-design wild bootstrap, the recursive-design wild bootstrap and the pairwise bootstrap. In a simulation study all three procedures tend to be more accurate in small samples than the conventional large-sample approximation based on robust standard errors. In contrast, standard residual-based bootstrap methods for models with i.i.d. errors may be very inaccurate if the i.i.d. assumption is violated. We conclude that in many empirical applications the proposed robust bootstrap procedures should routinely replace conventional bootstrap procedures for autoregressions based on the i.i.d. error assumption.

Economic Development under Alternative Trade Regimes

How does openness affect economic development? This question is answered in the context of a dynamic general equilibrium model of the world economy, where countries have technological differences that are both sector-neutral and specific to the investment goods sector. Relative to a benchmark case of trade in credit markets only, consider (i) a complete restriction of trade, and (ii) a full liberalization of trade. The first change decreases the cross-sectional dispersion of incomes only slightly, and produces a relatively small welfare loss. The second change, instead, decreases dispersion by a significant amount, and produces a very large welfare gain.

Exact Multivariate Tests of Asset Pricing Models with Stable Asymmetric Distributions

In this paper, we propose exact inference procedures for asset pricing models that can be formulated in the framework of a multivariate linear regression (CAPM), allowing for stable error distributions. The normality assumption on the distribution of stock returns is usually rejected in empirical studies, due to excess kurtosis and asymmetry. To model such data, we propose a comprehensive statistical approach which allows for alternative - possibly asymmetric - heavy tailed distributions without the use of large-sample approximations. The methods suggested are based on Monte Carlo test techniques. Goodness-of-fit tests are formally incorporated to ensure that the error distributions considered are empirically sustainable, from which exact confidence sets for the unknown tail area and asymmetry parameters of the stable error distribution are derived. Tests for the efficiency of the market portfolio (zero intercepts) which explicitly allow for the presence of (unknown) nuisance parameter in the stable error distribution are derived. The methods proposed are applied to monthly returns on 12 portfolios of the New York Stock Exchange over the period 1926-1995 (5 year subperiods). We find that stable possibly skewed distributions provide statistically significant improvement in goodness-of-fit and lead to fewer rejections of the efficiency hypothesis.

Intertemporal Social Evaluation

Intertemporal social-evaluation rules provide us with social criteria that can be used to assess the relative desirability of utility distributions across generations. The trade-offs between the well-being of different generations implicit in each such rule reflect the underlying ethical position on issues of intergenerational equity or justice. We employ an axiomatic approach in order to identify ethically attractive socialevaluation procedures. In particular, we explore the possibilities of using welfare information and non-welfare information in a model of intertemporal social evaluation. We focus on the individuals’ birth dates and lengths of life as the relevant non-welfare information. As usual, welfare information is given by lifetime utilities. It is assumed that this information is available for each alternative to be ranked. Various weakenings of the Pareto principle are employed in order to allow birth dates or lengths of life (or both) to matter in social evaluation. In addition, we impose standard properties such as continuity and anonymity and we examine the consequences of an intertemporal independence property. For each of the Pareto conditions employed, we characterize all social-evaluation rules satisfying it and our other axioms. The resulting rules are birth-date dependent or lifetime-dependent versions of generalized utilitarianism. Furthermore, we discuss the ethical and axiomatic foundations of geometric discounting in the context of our model.

Alternative Models of Court Administration

Canadian Judicial Council

Monetary Policy by Committee:Consensus, Chairman Dominance or Simple Majority?

This paper studies the theoretical and empirical implications of monetary policy making by committee under three different voting protocols. The protocols are a consensus model, where super-majority is required for a policy change; an agenda-setting model, where the chairman controls the agenda; and a simple majority model, where policy is determined by the median member. These protocols give preeminence to different aspects of the actual decision making process and capture the observed heterogeneity in formal procedures across central banks. The models are estimated by Maximum Likehood using interest rate decisions by the committees of five central banks, namely the Bank of Canada, the Bank of England, the European Central Bank, the Swedish Riksbank, and the U.S. Federal Reserve. For all central banks, results indicate that the consensus model is statically superior to the alternative models. This suggests that despite institutionnal differences, committees share unwritten rules and informal procedures that deliver observationally equivalent policy decisions.

Analyse de la pratique et des besoins des acteurs pour l’utilisation d’aides à la communication en déficience intellectuelle

La présente recherche a pour objet la pratique orthophonique en suppléance à la communication (SC) auprès de personnes qui ont une déficience intellectuelle (DI). Des recherches ont montré que les aides à la communication à sortie vocale (ACSV) pouvaient améliorer la communication des personnes ayant une DI. Cependant, la plupart de ces recherches ont été menées dans des conditions idéales qui ne reflètent pas nécessairement celles que l’on retrouve dans les milieux cliniques typiques. On connaît peu de choses sur les pratiques professionnelles en SC auprès des personnes ayant une DI. Le but de cette recherche est de décrire la pratique orthophonique, de documenter les perspectives des utilisateurs sur les résultats des interventions et de décrire l’implication des parents et leurs habiletés à soutenir leur enfant dans l’utilisation d’une ACSV afin de proposer un modèle d’intervention en SC auprès de cette clientèle qui tienne compte de ces différentes perspectives. Une méthode qualitative a été choisie pour réaliser la recherche. Des entrevues individuelles semi-structurées ont été réalisées avec onze orthophonistes francophones et avec des parents ou familles d’accueil de dix utilisateurs d’ACSV et des entrevues structurées ont été menées avec huit utilisateurs d’ACSV. Un outil d’entrevue a été conçu à l’aide de pictogrammes pour permettre aux utilisateurs d’ACSV de répondre à des questions portant sur leur appréciation et utilisation de leur ACSV, leur satisfaction et priorités de communication. Un cadre conceptuel a été conçu à partir des guides de pratique clinique et un codage semi-ouvert a été utilisé pour réaliser les analyses thématiques des données provenant des orthophonistes. Un codage ouvert a servi à analyser les données provenant des parents. Des analyses descriptives ont servi à examiner les réponses des utilisateurs. Diverses procédures ont assuré la crédibilité des analyses. Entre autres, les analyses des entrevues des orthophonistes ont été validées lors d’un groupe de discussion avec sept participantes orthophonistes. Les résultats montrent que les ACSV sont utilisées surtout dans le milieu scolaire. Elles sont parfois utilisées lors des loisirs et dans la communauté, mais ces contextes sont ceux où les utilisateurs ont exprimé le plus d’insatisfaction et où se situe la majeure partie des priorités qu’ils ont identifiées. Les analyses ont permis d’identifier les facteurs qui rendent compte de ces résultats. Les orthophonistes manquent d’outils pour réaliser des évaluations exhaustives des capacités des clients et elles manquent de procédures pour impliquer les parents et obtenir d’eux une description complète des besoins de communication de leur enfant. Conséquemment, l’ACSV attribuée et le vocabulaire programmé ne répondent pas à l’ensemble des besoins de communication. Certaines orthophonistes manquent de connaissances sur les ACSV ou n’ont pas le matériel pour faire des essais avec les clients. Il en résulte un appariement entre la personne et l’ACSV qui n’est pas toujours parfait. À cause d’un manque de ressources en orthophonie, les parents sont parfois laissés sans soutien pour apporter les changements à la programmation lors des transitions dans la vie de leur enfant et certains ne reçoivent pas d’entraînement visant à soutenir l’utilisation de l’ACSV. Un modèle d’intervention en SC est proposé afin d’améliorer la pratique orthophonique auprès de cette population.