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"...

This paper is a survey (in Italian) of the estimation methods for econometric systems of nonlinear simultaneous equations

Purpose of this paper is the description of the tecniques used to generate pseudo-random numbers, to be added as disturbance terms to the stochastic structural equations of econometric models. These disturbance terms should have the same statistical properties as the residuals obtained, in each...

The numerical example which completes the paper by Goldberqer, Nagar and Odeh, on the estimated asymptotic covariance matrix of the reduced form coefficients for the Klein-I model estimated by Two Stage Least Squares (2SLS), has led to some misinterpretations of the properties of the model. In...

Experiments of stochastic simulation on a macro model of the Italian economy; this paper describes the first results produced by the research team.

Five alternative techniques have been applied to measure the degree of uncertainty associated with the forecasts produced by a macro-model of the French economy, the Mini-DMS developed at INSEE. They are bootstrap, analytic simulation on coefficients, Monte Carlo on coefficients, parametric...

This work is mainly intended for applied econometricians and students interested in development and application of estimation methods for structural econometric models. For the Klein-I model, detailed numerical tables of the parameters of the structural and restricted reduced form, of their...

In this paper, a package implemented at the Scientific Center of IBM Italy in Pisa for the stochastic simulation of linear and non-linear econometric models is presented. After a survey on the adopted methodologies, the input requirements and the produced output are described in some details,...

This paper describes the results of some stochastic simulation experiments performed on the most updated version of the Italian model. Due to a change in the income accounts system, the model has been completely reestimated using the new quarterly data. It consists of 128 equations, 50 of which...

With most of the available software packages, estimates of the parameter covariance matrix in a GARCH model are usually obtained from the outer products of the first derivatives of the log-likelihoods (BHHH estimator). However, other estimators could be defined and used, analogous to the...