Springer Nature is making SARS-CoV-2 and COVID-19 research free. View research | View latest news | Sign up for updates

Circular autocorrelation of stationary circular Markov processes

  • 206 Accesses

  • 1 Citations

Abstract

The stationary Markov process is considered and its circular autocorrelation function is investigated. More specifically, the transition density of the stationary Markov circular process is defined by two circular distributions, and we elucidate the structure of the circular autocorrelation when one of these distributions is uniform and the other is arbitrary. The asymptotic properties of the natural estimator of the circular autocorrelation function are derived. Furthermore, we consider the bivariate process of trigonometric functions and provide the explicit form of its spectral density matrix. The validity of the model was assessed by applying it to a series of wind direction data.

This is a preview of subscription content, log in to check access.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Notes

  1. 1.

    The similar term “circular serial correlation coefficient” is used in Anderson (1971, Section 6.5.2) in a different context, where he considered a process whose first and last observations are connected to each other.

  2. 2.

    The cacf function at lag \(k(\ge 0)\) in Holzmann et al. (2006) should be read as \(R_{\mathrm {C}}(k)=(I_1(\kappa )/I_0(\kappa ))^{2k}\). Here, \(I_r(\kappa )\) is the modified Bessel function of the first kind of order r. See Sect. 4 for details.

References

  1. Abe T, Pewsey A (2011) Sine-skewed circular distributions. Stat Pap 52:683–707

  2. Anderson TW (1971) The statistical analysis of time series. Wiley, New York

  3. Artes R, Paula GA, Ranvaud R (2000) Analysis of circular longitudinal data based on generalized estimating equations. Aust N Z J Stat 42:347–358

  4. Breckling J (1989) The analysis of directional time series: application to wind speed and direction. Springer, Berlin

  5. Brockwell PJ, Davis RA (1991) Time series: theory and methods, 2nd edn. Springer, New York

  6. Fisher NI, Lee AJ (1983) A correlation coefficient for circular data. Biometrika 70:327–332

  7. Fisher NI, Lee AJ (1994) Time series analysis of circular data. J R Stat Soc B 70:327–332

  8. Hall P, Heyde CC (1980) Martingale limit theory and its application. Academic Press, New York

  9. Hannan EJ (1970) Multiple time series. Wiley, New York

  10. Holzmann H, Munk A, Suster M, Zucchini W (2006) Hidden Markov models for circular and linear–circular time series. Environ Ecol Stat 13:325–347

  11. Jammalamadaka SA, SenGupta AS (2001) Topics in circular statistics. World Scientific Publishing Co., New York

  12. Jona-Lasinio G, Gelfand A, Jona-Lasinio M (2012) Spatial analysis of wave direction data using wrapped Gaussian processes. Ann Appl Stat 6:1478–1498

  13. Jones MC, Pewsey A (2005) A family of symmetric distributions on the circle. J Am Stat Assoc 100:1422–1428

  14. Jones MC, Pewsey A, Kato S (2015) On a class of circulas: copulas for circular distributions. Ann Inst Stat Math 67:843–862

  15. Kato S (2010) A Markov process for circular data. J R Stat Soc B 72:655–672

  16. Kato S, Jones MC (2010) A family of distributions on the circle with links to, and applications arising from, Möbius transformation. J Am Stat Assoc 105:249–262

  17. Kato S, Jones MC (2013) An extended family of circular distributions related to wrapped Cauchy distributions via Brownian motion. Bernoulli 19:154–171

  18. Kato S, Pewsey A (2015) A Möbius transformation-induced distribution on the torus. Biometrika 102:359–370

  19. Mardia KV, Jupp PE (2000) Directional statistics. Wiley, Chichester

  20. Paparoditis E (1994) On vector autocorrelation and generalized second-order function for time series. J Time Ser Anal 15:235–334

  21. Pewsey A, Neuhäuser M, Ruxton GD (2013) Circular statistics in R. Oxford University Press, London

  22. Wehrly TE, Johnson RA (1980) Bivariate models for dependence of angular observations and a related Markov process. Biometrika 67:255–256

  23. Yeh S-Y, Harris KDM, Jupp PE (2013) A drifting Markov process on the circle, with physical applications. Proc R Soc A 469:20130092

Download references

Acknowledgements

The authors would like to express their gratitude to the editor and two anonymous referees, whose invaluable comments improved the paper.

Author information

Correspondence to Hiroaki Ogata.

Additional information

The research reported herein was supported by JSPS KAKENHI Grant Numbers 15K17593, 26380401, 15K21433, and 26870655.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Abe, T., Ogata, H., Shiohama, T. et al. Circular autocorrelation of stationary circular Markov processes. Stat Inference Stoch Process 20, 275–290 (2017). https://doi.org/10.1007/s11203-016-9154-0

Download citation

Keywords

  • Circular statistics
  • Time series models
  • Toroidal data
  • Wind direction
  • Wrapped cauchy distribution