Person: Mauricio Arias, José Alberto
Loading...
First Name
José Alberto
Last Name
Mauricio Arias
Affiliation
Universidad Complutense de Madrid
Faculty / Institute
Ciencias Económicas y Empresariales
Department
Análisis Económico y economía cuantitativa
Area
Fundamentos del Análisis Económico
Identifiers
3 results
Search Results
Now showing 1 - 3 of 3
Item The exact likelihood function for the vector ARMA model(1993) Mauricio Arias, José AlbertoThis paper implements in Fortran 77 a new algorithm which has the same purpose as algorithm AS 242 of Shea (1989), namely to compute the exact likelihood function of a vector ARMA model. The new algorithm turns out to be faster in many relevant cases and not appreciably slower in any. In addition to advantages offered by the algorithm of Shea (1989), including the calculation of an appropiate set of residuals, it also permits the automatic detection of noninvertible models as a byproduct. The Fortran 77 code presented here combines improved versions of the algorithms due to Ljung and Box (1979) and Hall and Nicholls (1980) with an algorithm of Kohn and Ansley (1982). The resulting procedure puts together a set of useful features which can only be found separately in other existing methods.Item A corrected algorithm for computing the theoretical autocovariance matrices of a vector ARMA model(Instituto Complutense de Análisis Económico - Documentos de Trabajo, 1995) Mauricio Arias, José AlbertoThe algorithm of Kohn and Ansley(1982)is reconsidered here, in arder to correct several implementation errors concerning the construction of the linear equations that must be solved for computing the theoretical autocovariance matrices of a vector ARMA model. This note presents a concise description of the corrected algorithm.Item Exact Maximum Likelihood Estimation of Stationary Vector ARMA Models(1993) Mauricio Arias, José AlbertoThe problems of evaluating and maximizing the exact likelihood function of vector ARMA models are considered separately. A new and efficient procedure for evaluating the exact likelihood function is presented. This method puts together a set of useful features which can only be found separately in currently available algorithms. A procedure for maximizing the exact likelihood function, which takes full advantage of the properties offered by the evaluation algorithm, is also considered. Combining these two procedures, a new algorithm for exact maximum likelihood estimation of vector ARMA models is obtained. Comparisons with existing procedures, in terms of both analytical arguments and a numerical example, are given in order to show that the new estimation algorithm performs at least as well as existing ones, and that relevant real situations occur in which it do es better.