MIDAS regression: a new horse in the race of filtering macroeconomic time series

Michal Bencik

No WP 8/2023, Working and Discussion Papers from Research Department, National Bank of Slovakia

Abstract: We propose a new method of dealing with the end point problem when filtering economic time series. The main idea is to replace filtered quarterly observations at the end of the sample with static forecasts from a MIDAS regression using higher frequency time series. This method is capable to improve stability of output gap estimates or other cyclical series, as we confirm by empirical analysis on selected CEE countries and the United States. We find that stability may still be violated due to structural breaks in business cycles, or by an excessive amount of short-term noise. While MIDAS regressions have the potential to improve output gap estimates compared to the HP filter approach, the country-specific circumstances play a considerable role and need to be considered.

JEL-codes: C22 E32 (search for similar items in EconPapers)
Pages: 36 pages
Date: 2023-10
New Economics Papers: this item is included in nep-ecm, nep-ets and nep-tra
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://nbs.sk/dokument/65c1467d-8255-4b3c-bbe1-2d ... tiahnut/?force=false (application/pdf)

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:svk:wpaper:1100

Access Statistics for this paper

More papers in Working and Discussion Papers from Research Department, National Bank of Slovakia Contact information at EDIRC.
Bibliographic data for series maintained by ().