Numerical Issues in Threshold Autoregressive Modeling of Time Series

Posted: 18 Jul 2003

See all articles by Ana-Maria Fuertes

Ana-Maria Fuertes

Cass Business School, City University of London

Jerry Coakley

University of Essex - Essex Business School

María Teresa Pérez Rodríguez

Universidad de Valladolid - Departmento de Matematica Aplicada

Abstract

This paper analyses the contribution of various numerical approaches to making the estimation of threshold autoregressive time series more efficient. It relies on the computational advantages of QR factorizations and proposes Givens transformations to update these factors for sequential LS problems. By showing that the residual sum of squares is a continuous rational function over threshold intervals it develops a new fitting method based on rational interpolation and the standard necessary optimality condition. Taking as benchmark a simple grid search, the paper illustrates via Monte Carlo simulations the efficiency gains of the proposed tools.

Keywords: Band-TAR, QR factorization, Givens rotations, Rational interpolation

JEL Classification: C63, C51, C61

Suggested Citation

Fuertes, Ana-Maria and Coakley, Jerry and Pérez Rodríguez, María Teresa, Numerical Issues in Threshold Autoregressive Modeling of Time Series. Journal of Economic Dynamic and Control, Vol. 27, pp. 2219-2242, 2003; Cass Business School Research Paper. Available at SSRN: https://ssrn.com/abstract=396564

Ana-Maria Fuertes

Cass Business School, City University of London ( email )

Faculty of Finance
106 Bunhill Row
London, EC1Y 8TZ
United Kingdom
+44 207 477 0186 (Phone)
+44 207 477 8881 (Fax)

HOME PAGE: http://www.city.ac.uk/people/academics/ana-maria-fuertes

Jerry Coakley (Contact Author)

University of Essex - Essex Business School ( email )

Wivenhoe Park
Colchester, CO4 3SQ
United Kingdom
+44 1206 872455 (Phone)
+44 1206 873429 (Fax)

HOME PAGE: http://www.essex.ac.uk/afm/staff/coakley.shtm

María Teresa Pérez Rodríguez

Universidad de Valladolid - Departmento de Matematica Aplicada ( email )

ETSII
47002 Valladolid
Spain

Here is the Coronavirus
related research on SSRN

Paper statistics

Abstract Views
936
PlumX Metrics