Umeå Economic Studies,
Umeå University, Department of Economics

Abstract: Estimation in nonlinear time series models has mainly been performed by least squares or maximum likelihood (ML) methods. The paper suggests and studies the performance of generalized method of moments (GMM) and indirect estimators for the autoregressive asymmetric moving average model. Both approaches are easy to implement and perform well numerically. In a Monte Carlo study it is found that the MSE properties of GMM are close to those of ML. The indirect estimator performs poorly in this respect. On the other hand, the three estimation techniques lead to fairly similar power functions for a linearity test.

Keywords: Estimation; Nonlinearity Test; Small Sample Properties; Time Series.

JEL-codes: C13; C15; C22

10 pages, December 15, 1997

Download statistics

Published as

Kurt Brännäs and Xavier de Luna, (1998), 'Generalized Method of Moment and Indirect Estimation of the ARASMA Model', Computational Statistics, vol 13, pages 485-494

• Umeå University, Department of Economics
• Ordering Working Papers
• Home page for this series

Questions (including download problems) about the papers in this series should be directed to David Skog ()
Report other problems with accessing this service to Sune Karlsson ().

RePEc:hhs:umnees:0436This page generated on 2024-09-13 22:17:25.