Short run and long run causality in time series: inference

We propose methods for testing hypothesis of non-causality at various horizons, as defined in Dufour and Renault (Econometrica 66, (1998) 1099–1125). We study in detail the case of VAR models and we propose linear methods based on running vector autoregressions at different horizons. While the hypotheses considered are nonlinear, the proposed methods only require linear regression techniques as well as standard Gaussian asymptotic distributional theory. Bootstrap procedures are also considered. For the case of integrated processes, we propose extended regression methods that avoid nonstandard asymptotics. The methods are applied to a VAR model of the US economy.     

Preferences,Country Bias,and International Trade

The paper analyzes international trade in a Ricardian world where consumer preferences exhibit country bias. In particular, consumers differentiate between identical physical goods by country of manufacture. In contrast to the classical Ricardian model, the pattern of international specialization in production depends on the preference structure. Possible equilibrium configurations include ones where both countries specialize incompletely and trade in both commodities, as well as situations where the pattern of specialization and trade is the reverse of that in the classical Ricardian world. Both interindustry and intraindustry trade can occur simultaneously, though there are no market imperfections or scale economies.     

The demise of commodity price agreements: the role of exchange rates and special interests

We derive the equilibrium joint distribution of exchange rate and commodity price in a two-country rational expectations model. The correlation between commodity price and exchange rate appears crucial for the stability of commodity markets. This result arises from the common practice to quote commodity prices in consuming countries' currency, which subjects producing countries to the currency risk. Welfare results of commodity price stabilization are obtained and facilitate the interpretation of the position taken by industrialized countries long opposed to international commodity agreements. We apply our model to the Philippines and investigate the potential effects of the International Sugar Agreement (ISA) on the various conditional volatilities of the model. We conclude on the relative ineffectiveness of these agreements in limiting fluctuations of sugar prices.     

Social Desirability of Earnings Tests

Abstract. In many countries, pension systems involve some form of earnings test; i.e. an individual's benefits are reduced if he has labor income. This paper examines whether or not such earnings tests emerge when pension system and income tax are optimally designed. We use a simple model with individuals differing both in productivity and in their health status. The working life of an individual has two 'endings': an official retirement age at which he starts drawing pension benefits (while possibly supplementing them with some labor income) and an effective age of retirement at which professional activity is completely given up. Weekly work time is endogenous, but constant in the period before official retirement and again constant (but possibly at a different level), after official retirement. Earnings tests mean that earnings are subject to a higher tax after official retirement than before. We show under which conditions earnings tests emerge both under a linear and under a non-linear tax scheme. In particular, we show that earnings tests will occur if heterogeneities in health or productivity are more significant after official retirement than before.     

Global manufacturing SO2 emissions: does trade matter?

A growth-decomposition (scale, technique and composition effect) covering 62 countries and seven manufacturing sectors over the 1990–2000 period shows that trade, through reallocations of activities across countries, has contributed to a 2–3% decrease in world SO₂ emissions. However, when compared to a constructed counterfactual no-trade benchmark, depending on the base year, trade would have contributed to a 3–10% increase in emissions. Finally adding emissions coming from trade-related transport activities, global emissions are increased through trade by 16% in 1990 and 13% in 2000, the decline being largely attributable to a shift of dirty activities towards cleaner countries.     

Estimating the pro-competitive gains from trade liberalization: an application to Mexican manufacturing

An original two-stage method is proposed to estimate the pro-competitive gains from trade liberalization. In a first step, I estimate the sensitivity of the price-cost margins of domestic firms to changes in the effective rate of protection, on the basis of a structure-performance relationship. This parameter is later exploited in a second step, where the cost of protection is calculated on the basis of a simple partial equilibrium model where domestic and foreign goods are imperfect substitutes. Applied to the Mexican case, this estimation reveals that protection removal depresses margins significantly and suggests that important additional gains can be expected from pro-competitive forces.     

Exact inference and optimal invariant estimation for the stability parameter of symmetric α-stable distributions

Hill estimation (Hill, 1975), the most widespread method for estimating tail thickness of heavy-tailed financial data, suffers from two drawbacks. One is that the optimal number of tail observations to use in the estimation is a function of the unknown tail index being estimated, which diminishes the empirical relevance of the Hill estimation. The other is that the hypothesis test of the underlying data lying in the domain of attraction of an α-stable law (α < 2) or of a normal law (α ≥ 2) for finite samples, is performed on the basis of the asymptotic distribution, which can be different from those for finite samples. In this paper, using the Monte Carlo technique, we propose an exact test method for the stability parameter of α-stable distributions which is based on the Hill estimator, yet is able to provide exact confidence intervals for finite samples. Our exact test method automatically includes an estimation procedure which does not need the assumption of a known number of observations on the distributional tail. Empirical applications demonstrate the advantages of our new method in comparison with the Hill estimation.     

An identification‐robust test for time‐varying parameters in the dynamics of energy prices

We test for the presence of time‐varying parameters (TVP) in the long‐run dynamics of energy prices for oil, natural gas and coal, within a standard class of mean‐reverting models. We also propose residual‐based diagnostic tests and examine out‐of‐sample forecasts. In‐sample LR tests support the TVP model for coal and gas but not for oil, though companion diagnostics suggest that the model is too restrictive to conclusively fit the data. Out‐of‐sample analysis suggests a random‐walk specification for oil price, and TVP models for both real‐time forecasting in the case of gas and long‐run forecasting in the case of coal. Copyright © 2010 John Wiley & Sons, Ltd.