Gary Koop

IMPULSE RESPONSE ANALYSIS IN NONLINEAR MULTIVARIATE MODELS

Abstract This paper presents a unified approach to impulse response analysis which can be used for both linear and nonlinear multivariate models. After discussing the advantages and disadvantages of traditional impulse response functions for nonlinear models, we introduce the concept of a generalized impulse response function which, we argue, is applicable to both linear and nonlinear models. We develop measures of shock persistence and asymmetric effects of shocks derived from the generalized impulse response function. We illustrate the use of these measures for a nonlinear bivariate model of US output and the unemployment rate.

Do recessions permanently change output

Abstract This paper examines whether negative innovations to GNP are more or less persistent than positive innovations. We find that once we allow for the impulse response of GNP to be asymmetric, negative innovations to GNP are observed to be much less persistent than positive ones. In particular, the effect of a recession on the forecast of output is found to be negligible after only eight to twelve quarters, while the effect of a positive shock is estimated to be persistent and amplified over time. Our results may therefore help reconcile two antagonistic views about the nature of business cycle fluctuations.

Stochastic frontier models: a bayesian perspective

A Bayesian approach to estimation, prediction and model comparison in composed error production models is presented. A broad range of distributions on the inefficiency term define the contending models, which can either be treated separately or pooled. Posterior results are derived for the individual efficiencies as well as for the parameters, and the differences with the usual sampling-theory approach are highlighted. The required numerical integrations are handled by Monte Carlo methods with Importance Sampling, and an empirical example illustrates the procedures.

Is there an environmental Kuznets curve for deforestation

Abstract This paper examines the relationship between deforestation and gross domestic product (GDP) per capita; in particular, whether an inverted-U relationship (indicative of worsening then improving deforestation) exists between them. We note that previous work has used models with restrictive assumptions, and recommend a more flexible random coefficients specification which allows for a greater degree of cross-country heterogeneity. Empirical results using data for 76 developing countries between 1961–1992 suggest that the inverted-U shaped relationship observed in other studies does not appear to be an empirical regularity with our less restrictive specification. Statistical tests indicate that this specification is supported by the data. We argue that such results are not surprising in view of the wide diversity of physical and social characteristics that exist across countries.

Bayesian efficiency analysis through individual effects: Hospital cost frontiers

Abstract This paper develops Bayesian tools for making inferences about firm-specific inefficiencies in panel data models. We begin by establishing a Bayesian setting in which fixed and random effects models are defined. What distinguishes these classes of models is the marginal prior independence of the effects. We show how such models can be analyzed using Monte Carlo integration or Gibbs sampling. These techniques are applied to a panel of U.S. hospitals. Our empirical findings illustrate the different characteristics of both types of models, as well as the influence of the particular priors used on the firm effects.

Modelling Recreation Demand Using Choice Experiments: Climbing in Scotland

This paper is concerned with the use of thechoice experiment method for modelling thedemand for recreation, using the example ofrock-climbing in Scotland. We begin byoutlining the method itself, including itstheoretical and econometric underpinnings. Datacollection procedures are then outlined. Wepresent results from both nested and non-nestedmodels, and report some tests for theimplications of choice complexity andrationality. Finally, we compare our resultswith a revealed preference data model based onthe same sample of climbers.

Forecasting Inflation Using Dynamic Model Averaging

We forecast quarterly US in‡ation based on the generalized Phillips curve using econometric methods which incorporate dynamic model averaging. These methods not only allow for coe¢ cients to change over time, but also allow for the entire forecasting model to change over time. We …nd that dynamic model averaging leads to substantial forecasting improvements over simple benchmark regressions and more sophisticated approaches such as those using time varying coe¢ cient models. We also provide evidence on which sets of predictors are relevant for forecasting in each period.

Dynamic Asymmetries in U.S. Unemployment

We examine dynamic asymmetries in U.S. unemployment using nonlinear time series models and Bayesian methods. We find strong statistical evidence in favor of a two-regime threshold auto-regressive model. Empirical results indicate that, once we take into account both parameter and model uncertainty, there are economically interesting asymmetries in the unemployment rate. One finding of particular interest is that shocks that lower the unemployment rate tend to have a smaller effect than shocks that raise the unemployment rate. This finding is consistent with unemployment rises being sudden and falls gradual.

Bayes factors and nonlinearity: Evidence from economic time series

This paper argues in favor of a Bayesian approach to evaluating evidence of nonlinearity in economic time series over the classical approach that has been dominant in the applied literature. An application is presented concerning nonlinearity in US GNP.

The components of output growth : A stochastic frontier analysis

This paper uses Bayesian stochastic frontier methods to decompose output change into technical, efficiency and input changes. In the context of macroeconomic growth exercises, which typically involve small and noisy data sets, we argue that stochastic frontier methods are useful since they incorporate measurement error and assume a (flexible) parametric form for the production relationship. These properties enable us to calculate measures of uncertainty associated with the decomposition and minimize the risk of overfitting the noise in the data. Tools for Bayesian inference in such models are developed. An empirical investigation using data from 17 OECD countries for 10 years illustrates the practicality and usefulness of our approach. Copyright 1999 by Blackwell Publishing Ltd