Premium
Inference on Structural Breaks using Information Criteria
Author(s) -
Hall Alastair R.,
Osborn Denise R.,
Sakkas Nikolaos
Publication year - 2013
Publication title -
the manchester school
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.361
H-Index - 42
eISSN - 1467-9957
pISSN - 1463-6786
DOI - 10.1111/manc.12017
Subject(s) - inference , econometrics , bayesian inference , bayesian probability , regression , function (biology) , economics , linear regression , computer science , mathematics , statistics , artificial intelligence , evolutionary biology , biology
This paper investigates the usefulness of information criteria for inference on the number of structural breaks in a standard linear regression model. In particular, we propose a modified penalty function for such criteria, which implies each break is equivalent to estimation of three individual regression coefficients. A M onte C arlo analysis compares information criteria to sequential testing, with the modified Bayesian and Hannan–Quinn criteria performing well overall, for data‐generating processes both without and with breaks. The methods are also used to examine changes in E uro area monetary policy between 1971 and 2007.