Advertisement

Statistics and Computing

, Volume 18, Issue 3, pp 313–320 | Cite as

Copula, marginal distributions and model selection: a Bayesian note

  • Ralph dos Santos SilvaEmail author
  • Hedibert Freitas Lopes
Article

Abstract

Copula functions and marginal distributions are combined to produce multivariate distributions. We show advantages of estimating all parameters of these models using the Bayesian approach, which can be done with standard Markov chain Monte Carlo algorithms. Deviance-based model selection criteria are also discussed when applied to copula models since they are invariant under monotone increasing transformations of the marginals. We focus on the deviance information criterion. The joint estimation takes into account all dependence structure of the parameters’ posterior distributions in our chosen model selection criteria. Two Monte Carlo studies are conducted to show that model identification improves when the model parameters are jointly estimated. We study the Bayesian estimation of all unknown quantities at once considering bivariate copula functions and three known marginal distributions.

Keywords

Copula Deviance information criterion Marginal distribution Measure of dependence Monte Carlo study Skewness 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Akaike, H.: Information theory and an extension of the maximum likelihood principle. In: Second Int. Symp. on Inf. Theory (Tsahkadsor, 1971), pp. 267–281. Akadémia Kiadó, Budapest (1973) Google Scholar
  2. Clayton, D.: A model for association in bivariate life tables and its application in epidemiological studies of familial tendency in chronic disease incidence. Biometrika 65, 141–151 (1978). doi: 10.1093/biomet/65.1.141 CrossRefMathSciNetzbMATHGoogle Scholar
  3. Demarta, S., McNeil, A.J.: The t copula and related copulas. Int. Stat. Rev. 73(1), 111–129 (2005) zbMATHCrossRefGoogle Scholar
  4. Fernández, C., Steel, M.: On Bayesian modelling of fat tails and skewness. J. Am. Stat. Assoc. 93, 359–371 (1998). doi: 10.2307/2669632 CrossRefzbMATHGoogle Scholar
  5. Frank, M.J.: On the simultaneous associative of f(x,y) and x+yf(x,y). Aequ. Math. 19, 194–226 (1979). doi: 10.1007/BF02189866 CrossRefzbMATHGoogle Scholar
  6. Gamerman, D., Lopes, H.F.: Markov Chain Monte Carlo: Stochastic Simulation for Bayesian Inference, 2nd edn. Chapman & Hall, London (2006) zbMATHGoogle Scholar
  7. Genest, C., Quessy, J.-F., Rémillard, B.: Goodness-of-fit procedures for copula models based on the probability integral transformation. Scand. J. Stat. 32(2), 337–366 (2006). doi: 10.1111/j.1467-9469.2006.00470 CrossRefGoogle Scholar
  8. Genest, C., Ghoudi, K., Rivest, L.-P.: A semiparametric estimation procedure of dependence parameters in multivariate families of distributions. Biometrika 82(3), 543–552 (1995). doi: 10.1093/biomet/82.3.543 CrossRefMathSciNetzbMATHGoogle Scholar
  9. Gumbel, E.J.: Distributions des valeurs extrême en plusiers dimensions. Publ. Inst. Stat. Univ. Paris 9, 171–173 (1960) MathSciNetzbMATHGoogle Scholar
  10. Hougaard, P.: A class of multivariate failure time distributions. Biometrika 73, 671–678 (1986). doi: 10.1093/biomet/73.3.671 MathSciNetzbMATHGoogle Scholar
  11. Huard, D., Évin, G., Favre, A.-C.: Bayesian copulas selection. Comput. Stat. Data Anal. 51(2), 809–822 (2006). doi: 10.1016/j.csda.2005.08.010 CrossRefzbMATHGoogle Scholar
  12. Hürliman, W.: Fitting bivariate cumulative returns with copulas. Comput. Stat. Data Anal. 45(2), 355–372 (2004). doi: 10.1016/S0167-9473(02)00346-8 CrossRefGoogle Scholar
  13. Joe, H.: Multivariate Models and Dependence Concepts. Chapman & Hall, London (1997) zbMATHGoogle Scholar
  14. Kruskal, W.H.: Ordinal measures of association. J. Am. Stat. Assoc. 53, 814–861 (1958). doi: 10.2307/2281954 CrossRefMathSciNetzbMATHGoogle Scholar
  15. Neal, R.: Slice sampling (with discussion). Ann. Stat. 31, 705–767 (2003). doi: 10.1214/aos/1056562461 CrossRefMathSciNetzbMATHGoogle Scholar
  16. Nelsen, R.B.: An Introduction to Copulas, 2nd edn. Springer, New York (2006) zbMATHGoogle Scholar
  17. Pitt, M., Chan, D., Kohn, R.: Efficient Bayesian inference for Gaussian copula regression models. Biometrika 93, 537–554 (2006). doi: 10.1093/biomet/93.3.537 CrossRefMathSciNetzbMATHGoogle Scholar
  18. Roch, O., Alegre, A.: Testing the bivariate distribution of daily equity returns using copulas. An application to the Spanish stock market. Comput. Stat. Data Anal. 51(2), 1312–1329 (2006). doi: 10.1016/j.csda.2005.11.007 CrossRefMathSciNetzbMATHGoogle Scholar
  19. Schwarz, G.: Estimating the dimension of a model. Ann. Stat. 6, 461–464 (1978). doi: 10.1214/aos/1176344136 CrossRefzbMATHGoogle Scholar
  20. Sklar, A.: Fonctions de répartition à n dimensions et leurs marges. Publ. Inst. Stat. Univ. Paris 8, 229–231 (1959) MathSciNetGoogle Scholar
  21. Spiegelhalter, D.J., Best, N.G., Carlin, B.P., Linde, A.: Bayesian measures of model complexity and fit (with discussion). J.R. Stat. Soc. Ser. B 64, 583–639 (2002). doi: 10.1111/1467-9868.00353 CrossRefzbMATHGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2008

Authors and Affiliations

  • Ralph dos Santos Silva
    • 1
    Email author
  • Hedibert Freitas Lopes
    • 2
  1. 1.Australian School of BusinessUniversity of New South WalesSydneyAustralia
  2. 2.Graduate School of BusinessUniversity of ChicagoChicagoUSA

Personalised recommendations