On Bayesian Quantile Regression Using a Pseudo-joint Asymmetric Laplace Likelihood

Abstract

We consider a pseudo-likelihood for Bayesian estimation of multiple quantiles as a function of covariates. This arises as a simple product of multiple asymmetric Laplace densities (ALD), each corresponding to a particular quantile. The ALD has already been used in the Bayesian estimation of a single quantile. However, the pseudo-joint ALD likelihood is a way to incorporate constraints across quantiles, which cannot be done if each of the quantiles is modeled separately. Interestingly, we find that the normalized version of the likelihood turns out to be misleading. Hence, the pseudo-likelihood emerges as an alternative. In this note, we show that posterior consistency holds for the multiple quantile estimation based on such a likelihood for a nonlinear quantile regression framework and in particular for a linear quantile regression model. We demonstrate the benefits and explore potential challenges with the method through simulations.

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

References

  1. Benoit, D.F. and Van den Poel, D. (2012). Binary quantile regression: a Bayesian approach based on the asymmetric Laplace distribution. J. Appl. Econometrics 27, 1174–1188.

    MathSciNet  Article  Google Scholar 

  2. Chernozhukov, V., Fernández-Val, I. and Galichon, A. (2010). Quantile and probability curves without crossing. Econometrica 78, 1093–1125.

    MathSciNet  Article  MATH  Google Scholar 

  3. Dette, H. and Volgushev, S. (2008). Non-crossing non-parametric estimates of quantile curves. J. R. Stat. Soc. Ser. B Stat. Methodol. 70, 609–627.

    MathSciNet  Article  MATH  Google Scholar 

  4. Dunson, D.B. and Taylor, J.A. (2005). Approximate Bayesian inference for quantiles. J. Nonparametr. Stat. 17, 385–400.

    MathSciNet  Article  MATH  Google Scholar 

  5. Ghosal, S. and Roy, A. (2006). Posterior consistency of gaussian process prior for nonparametric binary regression. Ann. Statist. 34, 2413–2429.

    MathSciNet  Article  MATH  Google Scholar 

  6. Ghosal, S. and van der Vaart, A. (2007). Convergence rates of posterior distributions for noniid observations. Ann. Statist. 35, 192–223.

    MathSciNet  Article  MATH  Google Scholar 

  7. Ghosh, J.K. and Ramamoorthi, R.V. (2003). Bayesian nonparametrics. Springer.

  8. He, X. (1997). Quantile curves without crossing. Amer. Statist. 51, 186–192.

    Google Scholar 

  9. Kleijn, B.J.K. and van der Vaart, A.W. (2012). The Bernstein-Von-Mises theorem under misspecification. Electron. J. Stat. 6, 354–381.

    MathSciNet  Article  MATH  Google Scholar 

  10. Koenker, R. (1984). A Noteon L-estimates for linear models. Statist. Probab. Lett. 2, 322–325.

    MathSciNet  Article  Google Scholar 

  11. Koenker, R. and Bassett, G.J. (1978). Regression quantiles. Econometrica 46, 33–50.

    MathSciNet  Article  MATH  Google Scholar 

  12. Ramamoorthi, R., Sriram, K. and Martin, R. (2015). On posterior concentration in misspecified models. (Forthcoming) Available online at http://bayesian.org/BA/19667.

  13. Reich, B.J., Fuentes, M. and Dunson, D.B. (2011). Bayesian spatial quantile regression. J. Amer. Statist. Assoc. 106, 6–20.

    MathSciNet  Article  MATH  Google Scholar 

  14. Sriram, K., Ramamoorthi, R.V. and Ghosh, P. (2013). Posterior consistency of Bayesian quantile regression based on the misspecified asymmetric Laplace density. Bayesian Anal. 8, 479–504.

    MathSciNet  Article  MATH  Google Scholar 

  15. Taddy, M.A. and Kottas, A. (2010). A Bayesian nonparametric approach to inference for quantile regression. J. Bus. Econom. Statist. 28, 357–369.

    MathSciNet  Article  MATH  Google Scholar 

  16. Tokdar, S. T. and Kadane, J. B. (2012). Simultaneous linear quantile regression: a semiparametric Bayesian approach. Bayesian Anal. 7, 51–72.

    MathSciNet  Article  MATH  Google Scholar 

  17. Wu, Y. and Liu, Y. (2009). Stepwise multiple quantile regression estimation using non-crossing constraints. Stat. Interface 2, 299–310.

    MathSciNet  Article  MATH  Google Scholar 

  18. Yang, Y. and He, X. (2012). Bayesian empirical likelihood for quantile regression. Annals Stat. 40, 1102–1131.

    MathSciNet  Article  MATH  Google Scholar 

  19. Yu, K. and Moyeed, R.A. (2001). Bayesian quantile regression. Statist. Probab. Lett. 54, 437–447.

    MathSciNet  Article  MATH  Google Scholar 

  20. Yu, K., van Kerm, P. and Zhang, J. (2005). Bayesian quantile regression: an application to the wage distribution in 1990s Britain. Sankhyā 57, 359–377.

    MathSciNet  MATH  Google Scholar 

  21. Yue, Y.R. and Rue, H. (2011). Bayesian inference for additive mixed quantile regression models. Comput. Statist. Data Anal. 55, 84–96.

    MathSciNet  Article  MATH  Google Scholar 

  22. Zou, H. and Yuan, M. (2008). Composite quantile regression and the oracle model selection theory. Annals Stat. 36, 1108–1126.

    MathSciNet  Article  MATH  Google Scholar 

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Karthik Sriram.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Sriram, K., Ramamoorthi, R.V. & Ghosh, P. On Bayesian Quantile Regression Using a Pseudo-joint Asymmetric Laplace Likelihood. Sankhya A 78, 87–104 (2016). https://doi.org/10.1007/s13171-015-0079-2

Download citation

Keywords and phrases

  • Asymmetric Laplace density
  • Bayesian quantile regression
  • Pseudo-likelihood

AMS (2000) subject classification

  • Primary 62J02
  • Secondary 62C10.