The Annals of Statistics

Nonparametric estimation in null recurrent time series

Hans Arnfinn Karlsen and Dag Tjøstheim

Full-text: Open access

Abstract

We develop a nonparametric estimation theory in a nonstationary environment, more precisely in the framework of null recurrent Markov chains. An essential tool is the split chain, which makes it possible to decompose the times series under consideration into independent and identical parts. A tail condition on the distribution of the recurrence time is introduced. This condition makes it possible to prove weak convergence results for sums of functions of the process depending on a smoothing parameter. These limit results are subsequently used to obtain consistency and asymptotic normality for local density estimators and for estimators of the conditional mean and the conditional variance. In contradistinction to the parametric case, the convergence rate is slower than in the stationary case, and it is directly linked to the tail behavior of the recurrence time. Applications to econometric, and in particular to cointegration models, are indicated.

Article information

Source
Ann. Statist., Volume 29, Number 2 (2001), 372-416.

Dates
First available in Project Euclid: 24 December 2001

Permanent link to this document
https://projecteuclid.org/euclid.aos/1009210546

Digital Object Identifier
doi:10.1214/aos/1009210546

Mathematical Reviews number (MathSciNet)
MR1863963

Zentralblatt MATH identifier
1103.62335

Subjects
Primary: 62M10: Time series, auto-correlation, regression, etc. [See also 91B84] 62G07: Density estimation
Secondary: 60J05: Discrete-time Markov processes on general state spaces

Keywords
Nonstationary time series models null recurrent Markov chain nonparametric kernel estimators split chain

Citation

Karlsen, Hans Arnfinn; Tjøstheim, Dag. Nonparametric estimation in null recurrent time series. Ann. Statist. 29 (2001), no. 2, 372--416. doi:10.1214/aos/1009210546. https://projecteuclid.org/euclid.aos/1009210546


Export citation

References

  • Aparicio, F. M. and Escribano, A. (1997). Searching for linear and nonlinear cointegration: a new approach. Working paper 97-65, Univ. Carlos III de Madrid, Statistics and Economics Series.
  • Bergstrøm, H. (1981). Weak Convergence. Academic Press, NewYork. Billingsley, P. (1968). Convergence of Probability. Wiley, NewYork.
  • Bingham, N. H., Goldie, C. M. and Teugels, J. L. (1989). Regular Variation. Cambridge Univ. Press.
  • Chow, Y. S. and Teicher, H. (1988). Probability Theory, 2nd.ed.Springer, NewYork.
  • Darling, D. A. and Kac, M. (1957). On occupation times for Markoff processes.Trans.Amer.Math. Soc. 84 444-458.
  • Dickey, D. A. and Fuller, W. A. (1979). Distribution of the estimators for autoregressive time series with unit root. Econometrica 49 1057-1072.
  • Feigin, P. D. and Tweedie, R. L. (1985). Random coefficient autoregressive processes: a Markov chain analysis of stationarity and finiteness of moments. J.Time Ser.Anal.6 1-14.
  • Feller, W. R. (1971). An Introduction to Probability Theory and Its Application 2, 2nd. ed. Wiley, NewYork.
  • Granger, C. W. J. (1995). Modelling nonlinear relationships between extended-memory variables. Econometrica 63 265-279.
  • Granger, C. W. J. and Hallman, J. (1991). Long memory series with attractors. Oxford Bull. Econom.Statist.53 11-26.
  • Hjellvik, V., Yao, Q. and Tjøstheim, D. (1998). Linearity testing using local polynomial approximation. J.Statist.Plann.Inference 68 295-321.
  • H ¨opfner, R. (1990). Null recurrent birth and death processes: limits for certain martingales and local asymptotic mixed normality. Scand.J.Statist.17 201-215.
  • H ¨opfner, R. (1994). Estimating a parameter in a birth-and-death process model. Statist.Decisions 12 149-160.
  • H ¨opfner, R., Jacod, J. and Ladelli, L. (1990). Local asymptotic normality and mixed normality for Markov statistical models. Probab.Theory Related Fields 86 105-129.
  • Jacod, J. and Shiryaev, A. N. (1987). Limit Theorems for Stochastic Processes. Springer, Berlin.
  • Johansen, S. (1995). Likelihood-based Inference in Cointegrated Vector Autoregressive Models. Oxford Univ. Press.
  • Kallianpur, G. and Robbins, H. (1954). The sequence of sums of independent random variables. Duke Math.J.21 285-307.
  • Karlsen, H. A., Myklebust, T. and Tjøstheim, D. (2000). Nonparametric estimation in a nonlinear cointegration type model. Sonderforschungsbereich 373 33. Humboldt Univ., Berlin.
  • Karlsen, H. A. and Tjøstheim, D. (1998). Nonparametric estimation in null recurrent time series. Sonderforschungsbereich 373 50. Humboldt Univ., Berlin.
  • Kasahara, Y. (1982). A limit theorem for slowly increasing occupation times. Ann.Probab.10 728-736.
  • Kasahara, Y. (1984). Limit theorems for L´evy processes and Poisson point processes and their applications to Brownian excursions. J.Math.Kyoto Univ.24 521-538.
  • Kasahara, Y. (1985). A limit theorem for sums of random number of i.i.d. random variables and its application to occupation times of Markov chains. J.Math.Soc.Japan 37 197-205.
  • Masry, E. and Tjøstheim, D. (1995). Nonparametric estimation and identification of nonlinear ARCH time series. Econometric Theory 11 258-289.
  • Masry, E. and Tjøstheim, D. (1997). Additive nonlinear ARX time series and projection estimators. Econometric Theory 13 214-252.
  • Meyn, S. P. and Tweedie, R. L. (1994). Markov Chains and Stochastic Stability. Springer, London.
  • Myklebust, T., Karlsen, H. A. and Tjøstheim, D. (2001). A Markov chain characterization of unit-root processes and the problem of nonlinear cointegration. Unpublished manuscript.
  • Nummelin, E. (1984). General Irreducible Markov Chains and Nonnegative Operators. Cambridge Univ. Press.
  • Phillips, P. C. B. and Park, J. (1998). Nonstationary density estimation and kernel autoregression. Cowles Foundation Discussion Paper 1181, Yale Univ.
  • Pollard, D. (1984). Convergence of Stochastic Processes. Springer, NewYork.
  • Robinson, P. M. (1983). Nonparametric estimators for time series. J.Time Ser.Anal.4 185-207.
  • Robinson, P. M. (1997). Large sample inference for nonparametric regression with dependent errors. Ann.Statist.25 2054-2083.
  • Stock, J. H. (1994). Unit roots, structural breaks and trends. In Handbook of Econometrics (R. F. Engle and D. L. McFadden, eds.) 4 2740-2843. North-Holland, Amsterdam. Touati, P. A. (1990). Loi fonctionnelle du logarithme iter´e pour les processus de Markov recurrents. Ann.Probab.18 140-159.
  • Tjøstheim, D. and Auestad, B. (1994). Nonparametric identification of nonlinear time series; projections and selecting significant lags. J.Amer.Statist.Assoc.89 1398-1419.
  • Watson, M. W. (1994). Vector autoregression and cointegration. In Handbook of Econometrics (R. F. Engle and D. L. McFadden, eds.) 4 2843-2918. North-Holland, Amsterdam.
  • Wheeden, R. L. and Zygmund, A. (1977). Measure and Integral. Dekker, NewYork.
  • Xia, Y. (1998). Doctoral thesis, Univ. Hong Kong.
  • Yakowitz, S. (1993). Nearest neigbour regression estimation for null-recurrent Markov times series. Stochastic Process.Appl.48 311-318.