RT Report
T1 A generalized least squares estimation methodfor Vector Moving Average Models.
A1 Flores de Frutos, Rafael
A1 Serrano García, Gregorio R.
AB Se propone un nuevo método lineal para la estimación de modelos VMA. Este método tiene como característica principal, la de considerar explicitamente la estructura estocástica de los errores de aproximación que se cometen al sustituir las innovaciones del VMA por residuos obtenidos a partir de la estimación de un VAR de orden elevado.
AB A new GLS procedure for estimating VMA models is proposed. Its main feature is to consider explicitly the stochastic structure of the approximation errors arising when lagged VMA innovations are replaced with lagged residuals from a long VAR.
PB Facultad de Ciencias Económicas y Empresarias. Instituto Complutense de Análisis Económico (ICAE).
YR 1996
FD 1996-09
LK https://hdl.handle.net/20.500.14352/64244
UL https://hdl.handle.net/20.500.14352/64244
LA eng
NO Hannan, E.J. and J. Rissanen. 1982. Recursive estimation of mixed autoregressive-moving average order, Biometrica 69, 81-94.Hillmer, S. and G. Tiao. 1979. Likelihood function of stationary multiple autoregressive moving average models, Journal of the American Statiatical Association, 74, 652-60.Koreisha, S.G. and T.H. Pukkila. 1989. Fast linear estimation methods for vector autoregressive moving-average models. Journal of Time Series Analysis, 10, 325-39.Koreisha, S.G. and T.H. Pukkila. 1990. A generalized least-squares approach for estimation of autoregressive moving-average models, Journal of Time Series Analysis,11, 139-51.Spliid, H. 1983. A fast estimation method for the vector autoregressive moving average model with exogenous variables, Journal of the American Statistical Association 78, 843-49.
DS Docta Complutense
RD 7 may 2024