Estimating the rational expectations model of speculative storage: A MonteCarlo comparison of three simulation estimators

The non-negativity constraint on inventories imposed on the rational expect ations theory of speculative storage implies that the conditional mean and variance of commodity prices are non-linear in lagged prices and have a kin k at a threshold point. In this paper, the structural parameters of this mo del are estimated using three simulation-based estimators. In a Monte Carlo experiment, the finite sample properties of the simulated methods of momen ts estimator of Duffie and Singleton (1993, Econometrica 61 (4), 929-952) t he indirect inference estimator of Gourieroux et al. (1993, Journal of Appl ied Economterics 8, S85-S118) and the efficient method of moments estimator of Gallant and Tauchen (1996, Econometric Theory 12, 657-681) are assessed . Exploiting the invariant distribution implied by the theory allows us to evaluate the error induced by simulations. Our results show that the estima tors differ in their sensitivity to the sample size, the number of simulati ons, choice of auxiliary models, and computation demands. For some estimato rs, the test for overidentifying restrictions exhibit significant size dist ortions in small samples. Overall, while the simulation estimators have sma ll bias, they are less efficient than pseudo-maximum likelihood (PMLE). Hen ce for the small sample sizes considered, the simulation estimators are sti ll inferior to the PMLE estimates in a mean-squared sense. (C) 2000 Elsevie r Science S.A. All rights reserved. JEL classification: C15; B4; G1; Q1.