A diagram to detect serial dependencies: an application to transport time series

Abstract

The Ljung–Box test is typically used to test serial independence even if, by construction, it is generally powerful only in presence of pairwise linear dependence between lagged variables. To overcome this problem, Bagnato et al. recently proposed a simple statistic defining a serial independence test which, differently from the Ljung–Box test, is powerful also under a linear/nonlinear dependent process characterized by pairwise independence. The authors also introduced a normalized bar diagram, based on p-values from the proposed test, to investigate serial dependence. This paper proposes a balanced normalization of such a diagram taking advantage of the concept of reproducibility probability. This permits to study the strength and the stability of the evidence about the presence of the dependence under investigation. An illustrative example based on an artificial time series, as well as an application to a transport time series, are considered to appreciate the usefulness of the proposal.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3

References

  1. Agresti, A.: Categorical Data Analysis. Wiley, Hoboken, NJ (2002)

    Google Scholar 

  2. Anderson, H.M., Vahid, F.: Nonlinear correlograms and partial autocorrelograms. Oxford Bull. Econ. Stat. 67, 957–982 (2005)

    Article  Google Scholar 

  3. Bagnato, L., Punzo, A.: On the use of χ2-test to check serial independence. Stat. Appl. VIII(1), 57–74 (2010)

    Google Scholar 

  4. Bagnato, L., Punzo, A., Nicolis, O.: The autodependogram: a graphical device to investigate serial dependences. J. Time Ser. Anal. 33(2), 233–254 (2012)

    Article  Google Scholar 

  5. Bagnato, L., De Capitani, L., Punzo, A.: Detecting serial dependencies with the reproducibility probability autodependogram. Adv. Stat. Anal. 98(1), 35–61 (2014a)

    Article  Google Scholar 

  6. Bagnato, L., De Capitani, L., Punzo, A.: Testing serial independence via density-based measures of divergence. Method. Comput. Appl. Probab. 16(3), 627–641 (2014b)

    Article  Google Scholar 

  7. Bagnato, L., De Capitani, L., Mazza, A., Punzo, A.: SDD: an R package for serial dependence diagrams. J. Stat. Softw. 64(Code Snippet 2):1–19 (2015)

  8. Bagnato, L., De Capitani, L., Punzo, A.: The Kullback–Leibler autodependogram. J. Appl. Stat. 43(14), 2574–2594 (2016a)

    Article  Google Scholar 

  9. Bagnato, L., De Capitani, L., Punzo, A.: Testing for serial independence: beyond the Portmanteau approach. Am. Stat. (accepted) (2016b)

  10. Box, G.E.P., Tiao, G.C.: Intervention analysis with applications to economic and environmental problems. J. Am. Stat. Assoc. 70(349), 70–79 (1975)

    Article  Google Scholar 

  11. Chan, K.S.: TSA: time series analysis. R package version 1.01. http://CRAN.R-project.org/package=TSA(2012)

  12. Cochran, W.G.: Some methods for strengthening the common \(\chi ^2\) tests. Biometrics 10(4), 417–451 (1954)

    Article  Google Scholar 

  13. Cryer, J.D., Chan, K.S.: Time Series Analysis: With Applications in R. Springer Texts in Statistics. Springer, New York (2010)

    Google Scholar 

  14. De Capitani, L.: An introduction to RP-testing. Epidemiol. Biostat. Public Health 10(1) (2013)

  15. De Capitani, L., De Martini, D.: On stochastic orderings of the Wilcoxon rank sum test statisticwith applications to reproducibility probability estimation testing. Stat. Probab. Lett. 81(8), 937–946 (2011)

    Article  Google Scholar 

  16. De Capitani, L., De Martini, D.: Reproducibility probability estimation and testing for the Wilcoxon rank-sum test. J. Stat. Comput. Simul. 85(3), 468–493 (2015)

    Article  Google Scholar 

  17. De Capitani, L., De Martini, D.: Reproducibility probability estimation and RP-testing for some nonparametric tests. Entropy 18(4), 142 (2016)

    Article  Google Scholar 

  18. De Martini, D.: Reproducibility probability estimation for testing statistical hypotheses. Stat. Probab. Lett. 78(9), 1056–1061 (2008)

    Article  Google Scholar 

  19. Diks, C.: Nonparametric Tests for Independence. In: Meyers, R.A. (ed.) Encyclopedia of Complexity and Systems Science, pp. 6252–6271. Springer, New York (2009)

    Google Scholar 

  20. Genest, C., Rémillard, B.: Test of independence and randomness based on the empirical copula process. Test 13(2), 335–369 (2004)

    Article  Google Scholar 

  21. Goodman, S.N.: A comment on replication, \(p\)-values and evidence. Stat. Med. 11(7), 875–879 (1992)

    Article  Google Scholar 

  22. Hall, P., Wolff, R.: On the strength of dependence of a time series generated by a chaotic map. J. Time Ser. Anal. 16(6), 571–583 (1995)

    Article  Google Scholar 

  23. Hallin, M., Mélard, G.: Rank-based tests for randomness against first-order serial dependence. J. Am. Stat. Assoc. 83(404), 1117–1128 (1988)

    Article  Google Scholar 

  24. Johnson, N., Kotz, S., Balakrishnan, N.: Continuous Univariate Distributions, vol. 2. Wiley, New York (1995)

    Google Scholar 

  25. King, M.: Testing for autocorrelation in linear regression models: a survey. In: King, M.L., Giles, D.E.A. (eds.) Specification Analysis in the Linear Model, pp. 19–73. Routledge Kegan & Paul, London (1987)

    Google Scholar 

  26. Lehmann, E.L.: Testing Statistical Hypotheses. Springer, New York (1997)

    Google Scholar 

  27. Ljung, G.M., Box, G.E.P.: On a measure of lack of fit in time series models. Biometrika 65(2), 297–303 (1978)

    Article  Google Scholar 

  28. Zhou, Z.: Measuring nonlinear dependence in time-series, a distance correlation approach. J. Time Ser. Anal. 33(3), 438–457 (2012)

    Article  Google Scholar 

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Antonio Punzo.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Bagnato, L., De Capitani, L. & Punzo, A. A diagram to detect serial dependencies: an application to transport time series. Qual Quant 51, 581–594 (2017). https://doi.org/10.1007/s11135-016-0426-y

Download citation

Keywords

  • Chi-squared statistic
  • Serial dependence
  • Reproducibility probability
  • Multi-way contingency table
  • Ljung–Box test