×

Stationarity against integration in the autoregressive process with polynomial trend. (English) Zbl 1410.62162

Summary: We tackle the stationarity issue of an autoregressive path with a polynomial trend, and generalize some aspects of the LMC test, the testing procedure of Leybourne and McCabe. First, we show that it is possible to get the asymptotic distribution of the test statistic under the null hypothesis of trend-stationarity as well as under the alternative of nonstationarity for any polynomial trend of order \(r\). Then, we explain the reason why the LMC test, and by extension the KPSS test, does not reject the null hypothesis of trend-stationarity, mistakenly, when the random walk is generated by a unit root located at \(- 1 \). We also observe it on simulated data and correct the procedure. Finally, we describe some useful stochastic processes that appear in our limiting distributions.

MSC:

62M10 Time series, auto-correlation, regression, etc. in statistics (GARCH)
62M07 Non-Markovian processes: hypothesis testing
91B84 Economic time series analysis
60G10 Stationary stochastic processes

Software:

itsmr
PDFBibTeX XMLCite
Full Text: arXiv Link

References:

[1] P. Billingsley, Convergence of Probability Measures, Wiley Ser. Probab. Stat., New York 1999. · Zbl 0944.60003
[2] P. J. Brockwell and R. A. Davis, Introduction to Time Series and Forecasting, Springer, New York 1996. · Zbl 0868.62067
[3] M. Caner and L. Kilian, Size distortions of tests of the null hypothesis ofstationarity: Evidence and implications for the PPP debate, J. Int. Money Finance 20 (2001), pp. 639-657.
[4] R. M. De Jong, C. Amsler, and P. Schmidt, A robust version of the KPSS test,based on indicators, J. Econometrics 137 (2) (2007), pp. 311-333. · Zbl 1360.62442
[5] J. Dedecker and E. Rio, On the functional central limit theorem for stationaryprocesses, Ann. Inst. Henri Poincaré B 36 (1) (2000), pp. 1-34. · Zbl 0949.60049
[6] M. Duflo, Random Iterative Models, Springer, New York 1997. · Zbl 0868.62069
[7] D. Harris, S. J. Leybourne, and B. P. M. McCabe, Modified KPSS tests fornear integration, Econometric Theory 23 (2) (2007), pp. 355-363. · Zbl 1274.62593
[8] R. Ibragimov and P. C. B. Phillips, Regression asymptotics using martingaleconvergence methods, Econometric Theory 24 (4) (2008), pp. 888-947. · Zbl 1284.60053
[9] D. Kwiatkowski, P. C. B. Phillips, P. Schmidt, and Y. Shin, Testing the nullhypothesis of stationarity against the alternative of a unit root: How sure arewe that economic time series have a unit root?, J. Econometrics 54 (1992), pp. 159-178. · Zbl 0871.62100
[10] M. Lanne and P. Saikkonen, Reducing size distortions of parametricstationarity tests, J. Time Series Anal. 24 (2003), pp. 423-439. · Zbl 1036.62083
[11] S. J. Leybourne and B. P. M. McCabe, On the distribution of some teststatistics for parameter constancy, Biometrika 76 (1989), pp. 167-177. · Zbl 0664.62013
[12] S. J. Leybourne and B. P. M. McCabe, A consistent test for a unit root, J. Bus. Econom. Statist. 12 (2) (1994), pp. 157-166.
[13] S. J. Leybourne and B. P. M. McCabe, Modified stationarity tests withdata-dependent model-selection rules, J. Bus. Econom. Statist. 17 (2) (1999), pp. 264-270.
[14] I. B. MacNeill, Properties of sequences of partial sums of polynomialregression residuals with applications to tests for change of regression atunknown times, Ann. Statist. 6 (2) (1978), pp. 422-433. · Zbl 0375.62064
[15] U. Müller, Size and power of tests of stationarity in highly autocorrelated timeseries, J. Econometrics 128 (2) (2005), pp. 195-213. · Zbl 1337.62224
[16] S. Nabeya and K. Tanaka, Asymptotic theory of a test for the constancy ofregression coefficients against the random walk alternative, Ann. Statist. 16 (1) (1988), pp. 218-235. · Zbl 0662.62098
[17] P. Newbold, S. J. Leybourne, and M. E. Wohar, Trend-stationarity,difference-stationarity, or neither: Further diagnostic tests with an application toU.S. Real GNP, J. Econ. Bus. 53 (1) (2001), pp. 85-102.
[18] J. Nyblom, Testing for deterministic linear trend in time series, J. Amer. Statist. Assoc. 81 (1986), pp. 545-549. · Zbl 0594.62103
[19] J. Nyblom and T. Makelainen, Comparisons of tests for the presence ofrandom walk coefficients in a simple linear model, J. Amer. Statist. Assoc. 78 (1983), pp. 856-864. · Zbl 0531.62063
[20] M. M. Pelagatti and P. K. Sen, A robust version of the KPSS test basedon ranks, Working Papers from Universitŕ degli Studi di Milano-Bicocca, Dipartimento di Statistica, No. 2009070 (2009).
[21] P. C. B. Phillips, Time series regression with a unit root, Econometrica 55 (2) (1987), pp. 277-301. · Zbl 0613.62109
[22] P. C. B. Phillips and P. Perron, Testing for a unit root in time series regression, Biometrika 75 (2) (1988), pp. 335-346. · Zbl 0644.62094
[23] B. M. Pötscher, Noninvertibility and pseudo-maximum likelihood estimationof misspecified ARMA models, Econometric Theory 7 (1991), pp. 435-449.
[24] P. Saikkonen and R. Luukkonen, Testing for a moving average unit root inautoregressive integrated moving average models, J. Amer. Statist. Assoc. 88 (1993), pp. 596-601. · Zbl 0775.62240
[25] J. Stock, A class of tests for integration and cointegration, in: Cointegration,Causality, and Forecasting: A Festschrift in Honour of Clive W. J. Granger, R. F. Engle and H. White (Eds.), Oxford University Press, Oxford 1999, pp. 135-167.
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.