Stephen Gordon

Business Cycle Durations

Abstract While the development of Markov switching extensions to time series modeling has provided a useful way of characterizing business cycle dynamics, these models are not without their weaknesses. One problem is posed by the fact that since the state space for the unobserved state variables grows with the sample size, sampling distributions for maximum-likelihood estimates are difficult to establish. A second problem is that since the transition probabilities are constant, the conditional expected duration of phase is constant. This paper extends the model so that the information contained in leading indicator data can be used to forecast transition probabilities. These transition probabilities can then be used to calculate expected durations. The model is applied to US data to evaluate its ability to explain observed business cycle durations. The technical problems encountered with classical techniques are avoided by using Bayesian methods. Gibbs sampling techniques are used to calculate expected posterior durations.

Multinomial Probit Estimation of Spatially Interdependent Choices: An Empirical Comparison of Two New Techniques

The paper compares the empirical performance of two recently suggested techniques for estimating Multinomial Probit (MNP) models. The application concerns the choice of the first practice location of general practitioners in Quebec (Canada). Regional similarities are accounted for by modeling interdependent choice decisions. One technique is a simulated maximum likelihood based approach that relies on a Geweke, Hajivassiliou, and Keane (GHK) choice probability simulator, and the other one exploits the Gibbs sampler with data augmentation. The results indicate that both estimation techniques give similar results. Compared to its competitor, the Gibbs approach is much simpler to implement both conceptually and computationally.

Costs of Adjustment, the Aggregation Problem and Investment

This paper looks at the empirical consequences of inappropriately using a representative firm to mimic the aggregate investment decisions of a group of heterogeneous firms faced with costs of adjusting capital inputs. Improper aggregation generates a bias with two important consequences: (1) an apparent insensitivity of the aggregate capital stock to the user cost of capital and (2) predicted responses of the capital stock to shocks that are considerably slower than observed. Both of these consequences are features of available investment equations. Copyright 1992 by MIT Press.

Stochastic Trends, Deterministic Trends, and Business Cycle Turning Points

This study examines the relationship between specifications for long-run output patterns and specifications for business cycle dynamics. In an application to US GDP, it is found that inferences about the nature of the trend in output are not robust to changes in the specification for short-run fluctuations. Similarly, the choice of which model best describes the transitory movements in output depends on the way in which the trend is specified. The empirical analysis makes use of Bayesian methods to compare non-nested models for US GDP. Inspection of the predictive likelihoods for the individual data points suggests that the information contained in the data is largely limited to the observations associated with business cycle turning points.

Social choice, optimal inference and figure skating

We approach the social choice problem as one of optimal statistical inference. If individual voters or judges observe the true order on a set of alternatives with error, then it is possible to use the set of individual rankings to make probability statements about the correct social order. Given the posterior distribution for orders and a suitably chosen loss function, an optimal order is one that minimises expected posterior loss. The paper develops a statistical model describing the behaviour of judges, and discusses Markov chain Monte Carlo estimation. We also discuss criteria for choosing the appropriate loss functions. We apply our methods to a well-known problem: determining the correct ranking for figure skaters competing at the Olympic Games.

Business Cycle Turning Points: Two Empirical Business Cycle Model Approaches

This paper compares a set of non-nested empirical business cycle models. The alternative linear models include a VAR and Stock and Watsons (1991) unobserved components model. The alternative nonlinear models include the time-varying transition probability Markov switching model (Filardo 1993) and an integration of the Markov switching model with the Stock and Watson model as proposed by Diebold and Rudebusch (1994) and Chauvet (1994). Generally, this paper finds that no one model dominates in a predictive sense at all times. The nonlinear models, however, tend to outperform the linear models around business cycle turning points. Econometrically, this paper applies the general model comparison methodology of Geweke (1994).

Statistical comparison of aggregation rules for votes

If individual voters observe the true ranking on a set of alternatives with error, then the social choice problem, that is, the problem of aggregating their observations, is one of statistical inference. This study develops a statistical methodology that can be used to evaluate the properties of a given or aggregation rule. These techniques are then applied to some well-known rules.

Comparing Consumption-Based Asset-Pricing Models

We make use of a recently developed method to estimate the intertemporal marginal rate of substitution consistent with the fluctuations of asset return data from the Toronto Stock Exchange. These estimates are then used to evaluate various parametric specifications for preferences often used in empirical studies of consumption and asset returns. In contrast to existing studies, we are able to perform a formal statistical comparison of these models. We consider six extensions of the usual power utility model, and we find that none can be said to be a demonstrable improvement on the standard model.

Finite-sample inferences about mean-standard deviation bounds for stochastic discount factors

Abstract Using Bayesian methods of inference, we develop a procedure for evaluating the finite-sample uncertainty about the estimated Hansen-Jagannathan bounds for the mean and standard deviation of stochastic discount factors.

Bayesian Estimation of Stochastic Discount Factors

This article provides a Bayesian method of estimating the marginal posterior distributions for stochastic discount factors associated with observed asset returns. These estimates can be used to provide measures of fit for asset pricing models and to identify broad features of the characteristics that should be explained. These measures of fit can be used to supplement model evaluation exercises based on L. P. Hansen-R. Jagannathan bounds.