Model Selection when there are Multiple Breaks
Jennifer L. Castle, Jurgen A. Doornik, David F. Hendry
Abstract
We consider model selection when there is uncertainty over the choice of variables and the occurrence and timing of multiple location shifts. General-to-simple selection is extended using Autometrics by adding an impulse indicator for every observation to the set of candidate regressors (see Hendry, Johansen and Santos, 2008, and Johansen and Nielsen, 2009). We apply that approach to a fat-tailed distribution and processes with breaks: Monte Carlo experiments show its capability of detecting up to 20 shifts in 100 observations, while jointly selecting variables. An illustration to U.S. real interest rates compares impulse-indicator saturation with the procedure in Bai and Perron (1998).
Keywords: Impulse-indicator saturation, Location shifts, Model selection, Autometrics
Date: January 2010 | Reference number(s): 472
Series: Department of Economics Discussion Paper Series
JEL Classifications: C51, C22