A note on the uncertain trend in US real GNP: Evidence from robust unit root test

Amelie Charles and Olivier Darné

Working Papers from HAL

Abstract: In this paper, we test the presence of stochastic trend in long series of US real GNP measured by Balke and Gordon (1989) and Romer (1989). This is analyzed from two recent robust unit root tests proposed by Cavaliere and Georgiev (2009) and Lima and Xiao (2010), for which critical values are adapted to the small sample size. The former is improved by selecting optimally GLS detrending parameter to make the test in small samples powerful. We obtain mixed results on the full sample (1869--1993). However, the post-1929 GNP and GNP per capita series reject the unit-root null hypothesis, whereas for the pre-1929 GNP data, i.e. the period where the GNP series have been reconstructed, the unit-root hypothesis is not rejected for GNP series proposed by Balke-Gordon and Romer but this hypothesis is rejected for the same series in per capita form. This difference can be explained by the data-construction procedure employed for the pre-1929 GNP series.

Keywords: GNP; robust unit root test (search for similar items in EconPapers)
Date: 2010-12-17
Note: View the original document on HAL open archive server: https://hal.science/hal-00547737
References: Add references at CitEc
Citations: View citations in EconPapers (5)

Downloads: (external link)
https://hal.science/hal-00547737/document (application/pdf)

Related works:
Journal Article: A note on the uncertain trend in US real GNP: Evidence from robust unit root tests (2012)
Working Paper: A note of the uncertain trend in US real GNP: Evidence from robust unit root tests (2012)
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:hal:wpaper:hal-00547737

Access Statistics for this paper

More papers in Working Papers from HAL
Bibliographic data for series maintained by CCSD ().