Publication: A New Approach to Dating the Reference Cycle
Authors
Camacho, Maximo ; Gadea, María Dolores ; Gómez Loscos, Ana
item.page.secondaryauthor
item.page.director
Publisher
Taylor & Francis Group
publication.page.editor
publication.page.department
DOI
https://doi.org/10.1080/07350015.2020.1773834
item.page.type
info:eu-repo/semantics/article
Description
© 2022. The authors. This document is the published version of a Published Work that appeared in final form in Journal of Business & Economic Statistics.
To access the final edited and published work see https://doi.org/10.1080/07350015.2020.1773834
Abstract
This article proposes a new approach to the analysis of the reference cycle turning points, defined on thebasis of the specific turning points of a broad set of coincident economic indicators. Each individual pair ofspecific peaks and troughs from these indicators is viewed as a realization of a mixture of an unspecifiednumber of separate bivariate Gaussian distributions whose different means are the reference turningpoints. These dates break the sample into separate reference cycle phases, whose shifts are modeled by ahidden Markov chain. The transition probability matrix is constrained so that the specification is equivalentto a multiple change-point model. Bayesian estimation of finite Markov mixture modeling techniques issuggested to estimate the model. Several Monte Carlo experiments are used to show the accuracy of themodel to date reference cycles that suffer from short phases, uncertain turning points, small samples, andasymmetric cycles. In the empirical section, we show the high performance of our approach to identifyingthe US reference cycle, with little difference from the timing of the turning point dates established by theNBER. In a pseudo real-time analysis, we also show the good performance of this methodology in terms ofaccuracy and speed of detection of turning point dates.
publication.page.subject
Citation
Journal of Business & Economic Statistics Volume 40, 2022 - Issue 1 pp.: 66–81
item.page.embargo
Collections
Ir a Estadísticas
Sin licencia Creative Commons.