2010
DOI: 10.1007/s00181-010-0389-0
|View full text |Cite
|
Sign up to set email alerts
|

Is real GDP per capita a stationary process? Smooth transitions, nonlinear trends and unit root testing

Abstract: Real GDP per capita, Unit root tests, Persistence, Nonlinearities, Smooth transitions, C22, E31, E32,

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

2
15
0
1

Year Published

2011
2011
2023
2023

Publication Types

Select...
9

Relationship

1
8

Authors

Journals

citations
Cited by 40 publications
(19 citation statements)
references
References 31 publications
(26 reference statements)
2
15
0
1
Order By: Relevance
“…The first step is to determine the order of integration of the time series. Initialised by Nelson and Plosser (1982), there has been an extensive debate on whether macroeconomic time series are trend-stationary or follow a unit root process with a potential drift, see for instance Perron (1989), Shin et al (1992) and Cuestas and Garratt (2011). The latter view seems to be the more prominent in the literature as most authors apply unit root and co-integration techniques to macroeconomic time series like the GDPPC.…”
Section: Methods and Datamentioning
confidence: 99%
See 1 more Smart Citation
“…The first step is to determine the order of integration of the time series. Initialised by Nelson and Plosser (1982), there has been an extensive debate on whether macroeconomic time series are trend-stationary or follow a unit root process with a potential drift, see for instance Perron (1989), Shin et al (1992) and Cuestas and Garratt (2011). The latter view seems to be the more prominent in the literature as most authors apply unit root and co-integration techniques to macroeconomic time series like the GDPPC.…”
Section: Methods and Datamentioning
confidence: 99%
“…As we find no strong evidence against a unit root and for trend-stationarity in both the original and the log transformed GDPPC in any of the countries except for Switzerland, 5 we generally assume the series to follow unit root processes with drift terms. We are aware of the heterogeneity of the countries and the weaknesses of the underlying tests, as pointed out in Cuestas and Garratt (2011). In particular, our simple time trend models might not capture true non-3 Note that this approach is essentially equivalent to the comparison of the log-likelihood between a non-transformed and a log-transformed GDPPC series as done by Wibe and Carlen (2006) who used GDPPC data up to 2005.…”
Section: Methods and Datamentioning
confidence: 99%
“…A similar phenomenon occurs in nonlinear models. If there is nonlinearity in the data, linear unit root tests come across with power problem, and test results are biased to non-rejection of the null hypothesis [20].…”
Section: Empirical Methodologymentioning
confidence: 99%
“…In recent decades there has been a growth in the amount of literature aimed at characterising empirically the nonlinear behaviour of GDP per capita (see, inter alia, Teräsvirta andAnderson, 1992, andGarratt, 2011) and unemployment rates (Skalin and Teräsvirta, 2002, Faria and León-Ledesma, 2008, and Franchi and Ordóñez, 2011. Franchi and Ordóñez (2011) justify the estimation of a nonlinear model for the unemployment rate in Spain, based upon the assumption of multiple equilibria.…”
Section: The Econometric Approachmentioning
confidence: 99%