Improving the length of confidence sets for the date of a break in level and trend when the order of integration is unknown

Harvey, David I.; Leybourne, Stephen J.

Abstract

Harvey and Leybourne (2015) construct confidence sets for the timing of a break in level and/or trend, based on inverting sequences of test statistics for a break at all possible dates. These are valid, in the sense of yielding correct asymptotic coverage, for I(0) or I(1) errors. In constructing the tests, location-dependent weights are chosen for values of the break magnitude parameter such that each test conveniently has the same limit null distribution. By not imposing such a scheme, we show that it is generally possible to significantly shorten the length of the confidence sets, whilst maintaining accurate coverage properties.

Citation

Harvey, D. I., & Leybourne, S. J. (in press). Improving the length of confidence sets for the date of a break in level and trend when the order of integration is unknown. Economics Letters, 145, https://doi.org/10.1016/j.econlet.2016.06.015

• Journal Article Type: Article
• Acceptance Date: Jun 11, 2016
• Online Publication Date: Jun 22, 2016
• Deposit Date: Jul 14, 2016
• Publicly Available Date: Jul 14, 2016
• Journal: Economics Letters
• Print ISSN: 0165-1765
• Electronic ISSN: 0165-1765
• Publisher: Elsevier
• Peer Reviewed: Peer Reviewed
• Volume: 145
• DOI: https://doi.org/10.1016/j.econlet.2016.06.015
• Keywords: Level break; Trend break; Stationary; Unit root; Confidence sets
• Public URL: https://nottingham-repository.worktribe.com/output/793918
• Publisher URL: http://www.sciencedirect.com/science/article/pii/S0165176516302191