Abstract
This paper introduces wild bootstrap tests for unit root in exponential smooth transition autoregressive (ESTAR) models. Asymptotic unit root tests in ESTAR models have severe size distortions in the presence of heteroskedastic variances such as generalized autoregressive conditional heteroskedasticity and stochastic volatility, and hence, to improve these distortions, we use a wild bootstrap. Monte Carlo simulations show that in asymptotic tests, severe over-rejection of the null hypothesis occurs under heteroskedastic variances, whereas the proposed wild bootstrap tests have reasonable size and power properties.
Similar content being viewed by others
Notes
Park and Shintani (2010) also introduce unit root tests based on threshold autoregressive (TAR), logistic STAR (LSTAR), and double-LSTAR (D-LSTAR) models.
Another distribution for \(\epsilon _t\) is the Rademacher distribution (see Davidson and Flachaire 2008).
Cavaliere and Taylor (2009) developed wild bootstrap tests for unit root based on local generalized least squares (GLS).
References
Busetti F, Taylor AMR (2003) Variance shifts, structural breaks, and stationarity tests. J Bus Econ Stat 21:510–531
Cavaliere G (2004a) Testing stationarity under a permanent variance shift. Econ Lett 82:403–408
Cavaliere G (2004b) Unit root tests under time-varying variances. Economet Revi 23:259–292
Cavaliere G, Taylor AMR (2007) Testing for unit roots in time series models with non-stationary volatility. J Economet 140:919–947
Cavaliere G, Taylor AMR (2008) Bootstrap unit root tests for time series with nonstationary volatility. Economet Theory 24:43–71
Cavaliere G, Taylor AMR (2009) Bootstrap M unit root tests. Economet Rev 28:393–421
Chou RY (1988) Volatility persistence and stock valuations: some empirical evidence using GARCH. J Appl Economet 3:279–294
Davidson R, Flachaire E (2008) The wild bootstrap, tamed at last. J Economet 146:162–169
Dickey DA, Fuller WA (1979) Distribution of the estimates for autoregressive time series with a unit root. J Am Stat Assoc 74:427–431
Gonçalves S, Kilian L (2004) Bootstrapping autoregressions with conditional heteroskedasticity of unknown form. J Economet 123:89–120
Hamori S, Tokihisa A (1997) Testing for a unit root in the presence of a variance shift. Econ Lett 57:245–253
Harvey A, Ruiz E, Shephard N (1994) Multivariate stochastic variance models. Rev Econ Stud 61:247–264
Kapetanios G, Shin Y, Snell A (2003) Testing for a unit root in the nonlinear STAR framework. J Economet 112:359–379
Kiliç R (2011) Testing for a unit root in a stationary ESTAR process. Economet Rev 30:274–302
Kim S, Shephard N, Chib S (1998) Stochastic volatility: likelihood inference and comparison with ARCH models. Rev Econ Stud 65:361–393
Kim TH, Leybourne S, Newbold P (2002) Unit root tests with a break in innovation variance. J Economet 109:365–387
Liu RY (1988) Bootstrap procedure under some non-i.i.d. models. Ann Stat 16:1696–1708
Maki D (2008) The size performance of a nonparametric unit root test under a variance shift. Stat Probab Lett 78:743–748
Park JY, Shintani M (2010) Testing for a unit root test against transitional autoregressive models. Working paper, Vanderbilt University
Pavlidis E, Paya I, Peel D (2010) Specifying smooth transition regression models in the presence of conditional heteroskedasticity of unknown form. Stud Nonlinear Dyn Economets 14(3). Article 3:1–40
Sensier M, van Dijk D (2004) Testing for volatility changes in U.S. macroeconomic time series. Rev Econ Stat 86:833–839
Shintani M (2013) The inf-\(t\) test for a unit root against asymmetric exponential smooth transition autoregressive models. Jpn Econ Rev 64:3–15
van Dijk D, Franses PH, Lucas A (1999a) Testing for smooth transition nonlinearity in the presence of outliers. J Bus Econ Stat 17:217–235
van Dijk D, Franses PH, Lucas A (1999b) Testing for ARCH in the presence of additive outliers. J Appl Economet 14:539–562
White H (1980) A heteroskedasticity-consistent covariance matrix estimator and a direct test for heteroskedasticity. Econometrica 14:1261–1295
Author information
Authors and Affiliations
Corresponding author
Additional information
This research was supported by KAKENHI (Grant Numbers: 25380272 and 24530375).
Rights and permissions
About this article
Cite this article
Maki, D. Wild bootstrap tests for unit root in ESTAR models. Stat Methods Appl 24, 475–490 (2015). https://doi.org/10.1007/s10260-014-0289-0
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10260-014-0289-0