The finite sample performance of two methods for choosing a power transformation when seasonally adjusting a time series with X-13ARIMA-SEATS

Francisco Corona, Víctor M. Guerrero and Jesús López-Pérez

Communications in Statistics - Theory and Methods, 2024, vol. 53, issue 3, 965-979

Abstract: This paper evaluates the finite sample performance of two methods for selecting the power transformation when applying seasonal adjustment with the X-13ARIMA-SEATS package: the automatic method, based on the Akaike Information Criterion (AIC) and Guerrero’s method, that is based on the minimization of a coefficient of variation in order to choose a power transformation. For this purpose, we generate time series with different Data Generating Processes considering traditional Monte Carlo experiments as well as additive and multiplicative time series with linear and time-varying deterministic trends. We also illustrate the performance of both approaches with an empirical application, by seasonally adjusting the Mexican Global Economic Activity Indicator and its components. The results of different statistical tests indicate that Guerrero’s method is more adequate than the automatic one. We conclude that using Guerrero’s method generates better results when seasonally adjusting time series with the X-13ARIMA-SEATS program.

Date: 2024
References: Add references at CitEc
Citations:

Downloads: (external link)
http://hdl.handle.net/10.1080/03610926.2022.2098334 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:taf:lstaxx:v:53:y:2024:i:3:p:965-979

Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/lsta20

DOI: 10.1080/03610926.2022.2098334

Access Statistics for this article

Communications in Statistics - Theory and Methods is currently edited by Debbie Iscoe

More articles in Communications in Statistics - Theory and Methods from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().