Some analytic simulation techniques for the analysis of the reduced form and of the dynamic properties of econometric models are described. Comparisons are made with analytical methods available for linear models.

Stochastic simulation with antithetic variates is used to evaluate the bias of deterministic simulation in nonlinear econometric models. Application to the Klein-Goldberger model exemplifies the potentiality of the method.

Results of stochastic simulation experiments are described in this paper. The model experimented with is a large scale macroeconometric model, developed at the University of Bonn for the German economy (Model 5).

The importance of the simulation (both deterministic and stochastic) in the validation process of a non linear econometric model is underlined. Synthetic results of a large set of simulations on a non linear model of the Italian economy are presented. The benefits and the risks of the stochastic...

The problem of deriving asymptotic statistical properties of impact multipliers from a consistent estimate of a structural non-linear econometric model is discussed. The theoretical aspects, which generalize the results derived by Goldberger, Nagar and Odeh for linear models, are analyzed in...

The estimator of the coefficient covariance matrix proposed in White (1982) can be used to robustify the classical Wald test. Sampling experiments recently performed on linear regressions and simultaneous equation models, however, suggest that such an estimator tends to underestimate the...

In nonlinear econometric models, the evaluation of forecast errors is usually performed, completely or partially, by resorting to stochastic simulation. However, for evaluating the specific contribution of errors in estimated structural coefficients, several alternative methods have been...

The estimation method of Two Stage Least Squares (2SLS) with Principal Components (2SPC) is applied to a medium-sized nonlinear econometric model of the Italian Economy.

Experiments of stochastic simulation on a nonlinear macroeconometric model are described in this paper. The results are used both for improving the validation of a model of the Italian economy and for revisiting the heuristic value of the stochastic simulation methodology.

This paper presents a Monte-Carlo study on the practical reliability of numerical algorithms for FIML-estimation in nonlinear econometric models. The performance of different techniques of Hessian approximation in trust-region algorithms is compared regarding their "robustness" against "bad"...