Portugaliae Mathematica   EMIS ELibM Electronic Journals PORTUGALIAE
Vol. 57, No. 4, pp. 459-479 (2000)

Previous Article

Next Article

Contents of this Issue

Other Issues

ELibM Journals

ELibM Home



Asymptotic Separation in Bilinear Models

E. Gonçalves, C.M. Martins and N. Mendes-Lopes

Dep. Matemática, Universidade de Coimbra
Coimbra - PORTUGAL

Abstract: This paper presents a generalization of a non-classical decision procedure for simple bilinear models with a general error process, proposed by Gonçalves, Jacob and Mendes-Lopes [11]. This decision method involves two hypotheses on the model and its consistence is obtained by establishing the asymptotic separation of the sequences of probability laws defined by each hypothesis. Studies on the rate of convergence in the diagonal case are presented and an exponential decay is obtained. Simulation experiments are used to illustrate the behaviour of the power and level functions in small and moderate samples when this procedure is used as a test.

Keywords: Time series; asymptotic separation; bilinear models; test.

Classification (MSC2000): 62M10, 62F03.

Full text of the article:

Electronic version published on: 31 Jan 2003. This page was last modified: 27 Nov 2007.

© 2000 Sociedade Portuguesa de Matemática
© 2000–2007 ELibM and FIZ Karlsruhe / Zentralblatt MATH for the EMIS Electronic Edition