Analytical Derivatives for Markov Switching Models

Paper No.: 95-7

33 Pages Posted: 23 Aug 1998

See all articles by Jeff Gable

Jeff Gable

affiliation not provided to SSRN

Simon van Norden

HEC Montreal - Department of Finance; CIRANO; University of Montreal - Center for Interuniversity Research in Econometrics

Robert J. Vigfusson

Board of Governors of the Federal Reserve System

Abstract

This paper derives analytical gradients for a broad class of regime-switching models with Markovian state-transition probabilities. Such models are usually estimated by maximum likelihood methods, which require the derivatives of the likelihood function with respect to the parameter vector. These gradients are usually calculated by means of numerical techniques. The paper shows that analytical gradients considerably speed up maximum-likelihood estimation with no loss in accuracy. A sample program listing is included.

JEL Classification: C4, C6

Suggested Citation

Gable, Jeff and van Norden, Simon and Vigfusson, Robert John, Analytical Derivatives for Markov Switching Models. Paper No.: 95-7, Available at SSRN: https://ssrn.com/abstract=6790 or http://dx.doi.org/10.2139/ssrn.6790

Jeff Gable

affiliation not provided to SSRN

Simon Van Norden (Contact Author)

HEC Montreal - Department of Finance ( email )

3000 Chemin de la Cote-Sainte-Catherine
Montreal, Quebec H3T 2A7
Canada
514-340-6781 (Phone)
514-340-5632 (Fax)

HOME PAGE: http://svannorden.org

CIRANO ( email )

2020 rue University, 25th floor
Montreal H3C 3J7, Quebec
Canada

HOME PAGE: http://svannorden.org

University of Montreal - Center for Interuniversity Research in Econometrics ( email )

C.P. 6128, Succursale Centre-ville
Montreal, Quebec H3C 3J7
Canada

Robert John Vigfusson

Board of Governors of the Federal Reserve System ( email )

20th Street and Constitution Avenue NW
Washington, DC 20551
United States