Advertisement

Statistics and Computing

, 19:255 | Cite as

Measuring non-linear dependence for two random variables distributed along a curve

  • Pedro DelicadoEmail author
  • Marcelo Smrekar
Article

Abstract

We propose new dependence measures for two real random variables not necessarily linearly related. Covariance and linear correlation are expressed in terms of principal components and are generalized for variables distributed along a curve. Properties of these measures are discussed. The new measures are estimated using principal curves and are computed for simulated and real data sets. Finally, we present several statistical applications for the new dependence measures.

Keywords

Dependence measures Independence tests Linearity tests Principal curves Rényi’s axioms Similarity measures for pairs of variables 

References

  1. Bell, C.: Mutual information and maximal correlation as measures of dependence. Ann. Math. Stat. 33, 587–595 (1962) zbMATHCrossRefGoogle Scholar
  2. Bjerve, S., Doksum, K.: Correlation curves: Measures of association as functions of covariate value. Ann. Stat. 21, 890–902 (1993) zbMATHCrossRefMathSciNetGoogle Scholar
  3. Bowman, A.W., Azzalini, A.: Applied Smoothing Techniques for Data Analysis. Oxford University Press, London (1997) zbMATHGoogle Scholar
  4. Brillinger, D.R.: Some data analyses using mutual information. Braz. J. Probab. Stat. 18, 163–183 (2004) MathSciNetGoogle Scholar
  5. Brillinger, D.R., Guha, A.: Mutual information in the frequency domain. J. Stat. Plan. Inference 137, 1076–1084 (2006) CrossRefMathSciNetGoogle Scholar
  6. Delicado, P.: Another look at principal curves and surfaces. J. Multivar. Anal. 77, 84–116 (2001) zbMATHCrossRefMathSciNetGoogle Scholar
  7. Delicado, P., Huerta, M.: Principal Curves of Oriented Points: Theoretical and computational improvements. Comput. Stat. 18, 293–315 (2003) zbMATHMathSciNetGoogle Scholar
  8. Delicado, P., Smrekar, M.: Mixture of nonlinear models: A Bayesian fit for principal curves. In: Proceedings of the International Joint Conference on Neural Networks, Orlando, Florida, USA, August 12–17, 2007. ISBN: 1-4244-1380-X Google Scholar
  9. Dionísio, A., Menezes, R., Mendes, D.A.: Entropy-based independence test. Nonlinear Dyn. 44, 351–357 (2006) zbMATHCrossRefGoogle Scholar
  10. Doksum, K., Blyth, S., Bradlow, E., Meng, X., Zhao, H.: Correlation curves as local measures of variance explained by regression. J. Am. Stat. Assoc. 89, 571–582 (1994) zbMATHCrossRefMathSciNetGoogle Scholar
  11. Doksum, K., Froda, S.: Neighborhood correlation. J. Stat. Plan. Inference 91, 267–294 (2000) zbMATHCrossRefMathSciNetGoogle Scholar
  12. Granger, C.W., Maasoumi, E., Racine, J.: A dependence metric for possibly nonlinear processes. J. Time Ser. Anal. 25, 649–669 (2004) zbMATHCrossRefMathSciNetGoogle Scholar
  13. Hastie, T., Stuetzle, W.: Principal curves. J. Am. Stat. Assoc. 84, 502–516 (1989) zbMATHCrossRefMathSciNetGoogle Scholar
  14. Holland, P., Wang, Y.: Dependence function for continuous bivariate densities. Commun. Stat. 16, 863–876 (1987) zbMATHCrossRefMathSciNetGoogle Scholar
  15. Johnson, R.A., Wichern, D.W.: Applied Multivariate Statistical Analysis, 5th edn. Prentice Hall, Englewood Cliffs (2002) Google Scholar
  16. Jones, M.C.: The local dependence function. Biometrica 83, 899–904 (1996) zbMATHCrossRefGoogle Scholar
  17. Kégl, B., Krzyzak, A., Linder, T., Zeger, K.: Learning and design of principal curves. IEEE Trans. Pattern Anal. Mach. Intel. 22, 281–297 (2000) CrossRefGoogle Scholar
  18. Kendall, M.: A new measure of rank correlation. Biometrika 30, 81–89 (1938) zbMATHMathSciNetGoogle Scholar
  19. Nelsen, R.B.: An Introduction to Copulas, 2nd edn. Springer Series in Statistics. Springer, New York (2006) zbMATHGoogle Scholar
  20. R Development Core Team: R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria (2005). http://www.R-project.org
  21. Rényi, A.: On measures of dependence. Acta Math. Acad. Sci. Hung. 10, 441–451 (1959) zbMATHCrossRefGoogle Scholar
  22. Robinson, P.M.: Consistent nonparametric entropy-based testing. Rev. Econ. Stud. 58, 437–453 (1991) zbMATHCrossRefGoogle Scholar
  23. Schweizer, B., Wolff, E.F.: On nonparametric measures of dependence for random variables. Ann. Stat. 9(4), 879–885 (1981) zbMATHCrossRefMathSciNetGoogle Scholar
  24. Shannon, C.E.: A mathematical theory of communication. Bell Syst. Tech. J. 27, 379–423 (1948), 623–656 zbMATHMathSciNetGoogle Scholar
  25. Spearman, C.: The proof and measurement of association between two things. Am. J. Psychol. 15, 72–101 (1904) CrossRefGoogle Scholar
  26. Tjøstheim, D.: Measures and tests of independence: a survey. Statistics 28, 249–284 (1996) CrossRefMathSciNetGoogle Scholar
  27. Venables, W.N., Ripley, B.D.: Modern Applied Statistics with S, 4th edn. Springer, Berlin (2002) zbMATHGoogle Scholar
  28. Wang, Y.: Construction of continuous bivariate density functions. Stat. Sin. 3, 173–187 (1993) zbMATHGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2008

Authors and Affiliations

  1. 1.Departament d’Estadística i Investigació OperativaUniversitat Politècnica de CatalunyaBarcelonaSpain

Personalised recommendations