A Unit Root in Postwar U.S. Real GDP Still Cannot Be Rejected, and Yes, It Matters

David Cushman

Econ Journal Watch, 2016, vol. 13, issue 1, 5–45

Abstract: Contrary to the implications of some recent scholarly papers and blog entries, I conclude that a unit root in U.S. real GDP cannot be rejected in favor of trend stationarity. In addition to small-sample size distortion, sometimes addressed in the past, I adjust for the multiple test problem, which has never been addressed. I go on to estimate the economic importance of the unit root. It is important by three measures: (1) permanent shocks, inherent in a unit root, are of significant size relative to transitory shocks; (2) permanent shocks generate significant real GDP responses; and (3) models specifying permanent shocks give better forecasts than models without permanent shocks, most notably after seven post-World War II recessions. In particular, one should allow for both permanent and transitory shocks, and a bivariate vector error correction model with a specific identification of transitory and permanent shocks is clearly best of several unit root models examined.

Keywords: Economic growth; gross domestic product; national income; time series econometrics (search for similar items in EconPapers)
JEL-codes: E32 E37 O47 (search for similar items in EconPapers)
Date: 2016
References: View complete reference list from CitEc
Citations: View citations in EconPapers (7)

Downloads: (external link)
https://econjwatch.org/File+download/902/CushmanJan2016.pdf?mimetype=pdf (application/pdf)
https://econjwatch.org/1011 (text/html)

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:ejw:journl:v:13:y:2016:i:1:p:5-45

Access Statistics for this article

Econ Journal Watch is currently edited by Daniel Klein

More articles in Econ Journal Watch from Econ Journal Watch Contact information at EDIRC.
Bibliographic data for series maintained by Jason Briggeman ().