Estimation of pure autoregressive vector models for revenue series

Autor:	CO Omekara, Anthony E. Usoro
Rok vydání:	2007
Předmět:	Matrix (mathematics) Series (mathematics) Mathematical sciences Autoregressive model Statistics Univariate Linear combination Probability vector STAR model Mathematics
Zdroj:	Global Journal of Mathematical Sciences; Vol 6, No 1 (2007); 31-38
ISSN:	1596-6208
DOI:	10.4314/gjmas.v6i1.21404
Popis:	This paper aims at applying multivariate approach to Box and Jenkins univariate time series modeling to three vector series. General Autoregressive Vector Models with time varying coefficients are estimated. The first vector is a response vector, while others are predictor vectors. By matrix expansion each vector, whether response or predictor is a linear combination of other time varying vectors and itself. The models are linear and parameters are estimated by least squares method. The estimates obtained prove reality of the models estimated. Global Jouranl of Mathematical Sciences Vol. 6 (1) 2007: pp. 31-38
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_dedup___::be089438223a95db75b877433ce460b9 https://doi.org/10.4314/gjmas.v6i1.21404 Zobrazit plný text záznamu