Linear quantile mixed models

Statistics and Computing volume 24, pages461–479(2014)Cite this article

Abstract

Dependent data arise in many studies. Frequently adopted sampling designs, such as cluster, multilevel, spatial, and repeated measures, may induce this dependence, which the analysis of the data needs to take into due account. In a previous publication (Geraci and Bottai in Biostatistics 8:140–154, 2007), we proposed a conditional quantile regression model for continuous responses where subject-specific random intercepts were included to account for within-subject dependence in the context of longitudinal data analysis. The approach hinged upon the link existing between the minimization of weighted absolute deviations, typically used in quantile regression, and the maximization of a Laplace likelihood. Here, we consider an extension of those models to more complex dependence structures in the data, which are modeled by including multiple random effects in the linear conditional quantile functions. We also discuss estimation strategies to reduce the computational burden and inefficiency associated with the Monte Carlo EM algorithm we have proposed previously. In particular, the estimation of the fixed regression coefficients and of the random effects’ covariance matrix is based on a combination of Gaussian quadrature approximations and non-smooth optimization algorithms. Finally, a simulation study and a number of applications of our models are presented.

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

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Notes

  1. 1.

    For this scenario, we increased the number of quadrature nodes K from 11 to 17. The relative bias decreased from 0.135 to 0.051 (τ=0.75) and from 0.459 to 0.075 (τ=0.9).

  2. 2.

    All computations were performed on a 64-bit operating system machine with 16 Gb of RAM and quad-core processor at 2.93 GHz.

References

  1. Alhamzawi, R., Yu, K., Pan, J.: Prior elicitation in Bayesian quantile regression for longitudinal data. J. Biometr. Biostat. 2, 1–7 (2011)

    Article  Google Scholar 

  2. Azzalini, A., Capitanio, A.: Distributions generated by perturbation of symmetry with emphasis on a multivariate skew t-distribution. J. R. Stat. Soc., Ser. B, Stat. Methodol. 65, 367–389 (2003)

    MATH  Article  MathSciNet  Google Scholar 

  3. Barrodale, I., Roberts, F.D.K.: An efficient algorithm for discrete l 1 linear approximation with linear constraints. SIAM J. Numer. Anal. 15, 603–611 (1978)

    MATH  Article  MathSciNet  Google Scholar 

  4. Bassett, G., Koenker, R.: Asymptotic theory of least absolute error regression. J. Am. Stat. Assoc. 73, 618–622 (1978)

    MATH  Article  MathSciNet  Google Scholar 

  5. Boscovich, R.J.: De Litteraria Expeditione per Pontificiam Ditionem, et Synopsis Amplioris Operis, Ac Habentur Plura Ejus Ex Exemplaria Etiam Sensorum Impressa. Bononiesi Scientiarum et Artum Instituto Atque Academia Commentarii, vol. IV (1757)

    Google Scholar 

  6. Bose, A., Chatterjee, S.: Generalized bootstrap for estimators of minimizers of convex functions. J. Stat. Plan. Inference 117, 225–239 (2003)

    MATH  Article  MathSciNet  Google Scholar 

  7. Bottai, M., Orsini, N.: A command for Laplace regression. Stata J. (2012, in press)

  8. Bottai, M., Zhang, J.: Laplace regression with censored data. Biom. J. 52, 487–503 (2010)

    MATH  Article  MathSciNet  Google Scholar 

  9. Buchinsky, M.: Estimating the asymptotic covariance matrix for quantile regression models. A Monte Carlo study. J. Econom. 68, 303–338 (1995)

    MATH  Article  MathSciNet  Google Scholar 

  10. Canay, I.A.: A simple approach to quantile regression for panel data. Econom. J. 14, 368–386 (2011)

    MATH  Article  MathSciNet  Google Scholar 

  11. Clarke, F.H.: Optimization and Nonsmooth Analysis. SIAM, Philadelphia (1990)

    Google Scholar 

  12. Demidenko, E.: Mixed Models. Theory and Applications. Wiley, Hoboken (2004)

    Google Scholar 

  13. DerSimonian, R., Laird, N.: Meta-analysis in clinical trials. Control. Clin. Trials 7, 177–188 (1986)

    Article  Google Scholar 

  14. Doksum, K.: Empirical probability plots and statistical inference for nonlinear models in the two-sample case. Ann. Stat. 2, 267–277 (1974)

    MATH  Article  MathSciNet  Google Scholar 

  15. Eltoft, T., Kim, T., Lee, T.-W.: On the multivariate Laplace distribution. IEEE Signal Process. Lett. 13, 300–303 (2006)

    Article  Google Scholar 

  16. Farcomeni, A.: Quantile regression for longitudinal data based on latent Markov subject-specific parameters. Stat. Comput. 22, 141–152 (2012)

    Article  MathSciNet  Google Scholar 

  17. Feng, X., He, X., Hu, J.: Wild bootstrap for quantile regression. Biometrika 98, 995–999 (2011)

    MATH  Article  MathSciNet  Google Scholar 

  18. Fielding, A., Yang, M., Goldstein, H.: Multilevel ordinal models for examination grades. Stat. Model. 3, 127–153 (2003)

    MATH  Article  MathSciNet  Google Scholar 

  19. Fu, L., Wang, Y.-G.: Quantile regression for longitudinal data with a working correlation model. Comput. Stat. Data Anal. 56, 2526–2538 (2012)

    MATH  Article  MathSciNet  Google Scholar 

  20. Galvao, A.F.: Quantile regression for dynamic panel data with fixed effects. J. Econom. 164, 142–157 (2011)

    Article  MathSciNet  Google Scholar 

  21. Galvao, A.F., Montes-Rojas, G.V.: Penalized quantile regression for dynamic panel data. J. Stat. Plan. Inference 140, 3476–3497 (2010)

    MATH  Article  MathSciNet  Google Scholar 

  22. Genz, A., Keister, B.D.: Fully symmetric interpolatory rules for multiple integrals over infinite regions with Gaussian weight. J. Comput. Appl. Math. 71, 299–309 (1996)

    MATH  Article  MathSciNet  Google Scholar 

  23. Geraci, M.: lqmm: Linear quantile mixed models. R package version 1.02 (2012)

  24. Geraci, M., Bottai, M.: Quantile regression for longitudinal data using the asymmetric Laplace distribution. Biostatistics 8, 140–154 (2007)

    MATH  Article  Google Scholar 

  25. Geraci, M., Salvati, N.: The geographical distribution of the consumption expenditure in Ecuador: estimation and mapping of the regression quantiles. Stat. Appl. 19, 167–183 (2007)

    Google Scholar 

  26. He, X.: Quantile curves without crossing. Am. Stat. 51, 186–192 (1997)

    Google Scholar 

  27. He, X., Hu, F.: Markov chain marginal bootstrap. J. Am. Stat. Assoc. 97, 783–795 (2002)

    MATH  Article  MathSciNet  Google Scholar 

  28. He, X.M., Ng, P., Portnoy, S.: Bivariate quantile smoothing splines. J. R. Stat. Soc., Ser. B, Stat. Methodol. 60, 537–550 (1998)

    MATH  Article  MathSciNet  Google Scholar 

  29. He, X.M., Portnoy, S.: Some asymptotic results on bivariate quantile splines. J. Stat. Plan. Inference 91, 341–349 (2000)

    MATH  Article  MathSciNet  Google Scholar 

  30. Heiss, F., Winschel, V.: Likelihood approximation by numerical integration on sparse grids. J. Econom. 144, 62–80 (2008)

    Article  MathSciNet  Google Scholar 

  31. Higham, N.: Computing the nearest correlation matrix—a problem from finance. IMA J. Numer. Anal. 22, 329–343 (2002)

    MATH  Article  MathSciNet  Google Scholar 

  32. Hinkley, D.V., Revankar, N.S.: Estimation of the Pareto law from underreported data: a further analysis. J. Econom. 5, 1–11 (1977)

    MATH  Article  MathSciNet  Google Scholar 

  33. Karlsson, A.: Nonlinear quantile regression estimation of longitudinal data. Commun. Stat., Simul. Comput. 37, 114–131 (2008)

    MATH  Article  MathSciNet  Google Scholar 

  34. Kim, M.-O., Yang, Y.: Semiparametric approach to a random effects quantile regression model. J. Am. Stat. Assoc. 106, 1405–1417 (2011)

    MATH  Article  MathSciNet  Google Scholar 

  35. Kocherginsky, M., He, X., Mu, Y.: Practical confidence intervals for regression quantiles. J. Comput. Graph. Stat. 14, 41–55 (2005)

    Article  MathSciNet  Google Scholar 

  36. Koenker, R.: Quantile regression for longitudinal data. J. Multivar. Anal. 91, 74–89 (2004)

    MATH  Article  MathSciNet  Google Scholar 

  37. Koenker, R.: Quantile Regression. Cambridge University Press, New York (2005)

    Google Scholar 

  38. Koenker, R., Bassett, G.: Regression quantiles. Econometrica 46, 33–50 (1978)

    MATH  Article  MathSciNet  Google Scholar 

  39. Koenker, R., Machado, J.A.F.: Goodness of fit and related inference processes for quantile regression. J. Am. Stat. Assoc. 94, 1296–1310 (1999)

    MATH  Article  MathSciNet  Google Scholar 

  40. Koenker, R., Mizera, I.: Penalized triograms: total variation regularization for bivariate smoothing. J. R. Stat. Soc., Ser. B, Stat. Methodol. 66, 145–163 (2004)

    MATH  Article  MathSciNet  Google Scholar 

  41. Koenker, R., Ng, P., Portnoy, S.: Quantile smoothing splines. Biometrika 81, 673–680 (1994)

    MATH  Article  MathSciNet  Google Scholar 

  42. Koenker, R., Xiao, Z.J.: Inference on the quantile regression process. Econometrica 70, 1583–1612 (2002)

    MATH  Article  MathSciNet  Google Scholar 

  43. Kotz, S., Kozubowski, T.J., Podgórski, K.: An asymmetric multivariate Laplace distribution. Tech. Rep. 367, Department of Statistics and Applied Probability, University of California at Santa Barbara (2000)

  44. Kozubowski, T.J., Nadarajah, S.: Multitude of Laplace distributions. Stat. Pap. 51, 127–148 (2010)

    MATH  Article  MathSciNet  Google Scholar 

  45. Lamarche, C.: Robust penalized quantile regression estimation for panel data. J. Econom. 157, 396–498 (2010)

    Article  MathSciNet  Google Scholar 

  46. Lee, D., Neocleous, T.: Bayesian quantile regression for count data with application to environmental epidemiology. J. R. Stat. Soc., Ser. C, Appl. Stat. 59, 905–920 (2010)

    Article  MathSciNet  Google Scholar 

  47. Lee, Y., Nelder, J.A.: Conditional and marginal models: another view. Stat. Sci. 19, 219–228 (2004)

    MATH  Article  MathSciNet  Google Scholar 

  48. Lehmann, E.L.: Nonparametrics: Statistical Methods Based on Ranks. Holden-Day, San Francisco (1975)

    Google Scholar 

  49. Li, Q., Xi, R., Lin, N.: Bayesian regularized quantile regression. Bayesian Anal. 5, 533–556 (2010)

    Article  MathSciNet  Google Scholar 

  50. Lipsitz, S.R., Fitzmaurice, G.M., Molenberghs, G., Zhao, L.P.: Quantile regression methods for longitudinal data with drop-outs: application to CD4 cell counts of patients infected with the human immunodeficiency virus. J. R. Stat. Soc., Ser. C, Appl. Stat. 46, 463–476 (1997)

    MATH  Article  Google Scholar 

  51. Liu, Y., Bottai, M.: Mixed-effects models for conditional quantiles with longitudinal data. Int. J. Biostat. 5, 1–22 (2009)

    MATH  MathSciNet  Google Scholar 

  52. Lum, K., Gelfand, A.: Spatial quantile multiple regression using the asymmetric Laplace process. Bayesian Anal. 7, 235–258 (2012)

    Article  MathSciNet  Google Scholar 

  53. Machado, J.A.F., Santos Silva, J.M.C.: Quantiles for counts. J. Am. Stat. Assoc. 100, 1226–1237 (2005)

    MATH  Article  MathSciNet  Google Scholar 

  54. Oberhofer, W., Haupt, H.: The asymptotic distribution of the unconditional quantile estimator under dependence. Stat. Probab. Lett. 73, 243–250 (2005)

    MATH  Article  MathSciNet  Google Scholar 

  55. Parzen, M., Wei, L., Ying, Z.: A resampling method based on pivotal estimating functions. Biometrika 81, 341–350 (1994)

    MATH  Article  MathSciNet  Google Scholar 

  56. Pinheiro, J., Bates, D.: Approximations to the log-likelihood function in the nonlinear mixed-effects model. J. Comput. Graph. Stat. 4, 12–35 (1995)

    Google Scholar 

  57. Pinheiro, J.C., Bates, D.M.: Unconstrained parametrizations for variance-covariance matrices. Stat. Comput. 6, 289–296 (1996)

    Article  Google Scholar 

  58. Pinheiro, J.C., Chao, E.C.: Efficient Laplacian and adaptive Gaussian quadrature algorithms for multilevel generalized linear mixed models. J. Comput. Graph. Stat. 15, 58–81 (2006)

    Article  MathSciNet  Google Scholar 

  59. Pourahmadi, M.: Joint mean-covariance models with applications to longitudinal data: unconstrained parameterisation. Biometrika 86, 677–690 (1999)

    MATH  Article  MathSciNet  Google Scholar 

  60. Prékopa, A.: Logarithmic concave measures and functions. Acta Sci. Math. 34, 334–343 (1973)

    Google Scholar 

  61. R Development Core Team: R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, Vienna (2012). ISBN 3-900051-07-0

    Google Scholar 

  62. Reed, W.: The normal-Laplace distribution and its relatives. In: Balakrishnan, N., Castillo, E., Sarabia Alegria, J.-M. (eds.) Advances in Distribution Theory, Order Statistics, and Inference, pp. 61–74. Birkhäuser Boston, New York (2006)

    Google Scholar 

  63. Reich, B.J., Bondell, H.D., Wang, H.J.: Flexible Bayesian quantile regression for independent and clustered data. Biostatistics 11, 337–352 (2010a)

    Article  Google Scholar 

  64. Reich, B.J., Fuentes, M., Dunson, D.B.: Bayesian spatial quantile regression. J. Am. Stat. Assoc. (2010b)

  65. Rigby, R., Stasinopoulos, D.: Generalized additive models for location, scale and shape. J. R. Stat. Soc., Ser. C, Appl. Stat. 54, 507–554 (2005)

    MATH  Article  MathSciNet  Google Scholar 

  66. Robinson, G.: That BLUP is a good thing: the estimation of random effects. Stat. Sci. 6, 15–32 (1991)

    MATH  Article  Google Scholar 

  67. Rockafellar, R.: Convex Analysis. Princeton University Press, Princeton (1970)

    Google Scholar 

  68. Rogan, W.J., Dietrich, K.N., Ware, J.H., Dockery, D.W., Salganik, M., Radcliffe, J., Jones, R.L., Ragan, N.B., Chisolm, J.J., Rhoads, G.G.: The effect of chelation therapy with succimer on neuropsychological development in children exposed to lead. N. Engl. J. Med. 344, 1421–1426 (2001)

    Article  Google Scholar 

  69. Ruppert, D., Wand, M., Carroll, R.: Semiparametric Regression. Cambridge University Press, New York (2003)

    Google Scholar 

  70. Sarkar, D.: Lattice: Multivariate Data Visualization with R. Springer, New York (2008)

    Google Scholar 

  71. Treatment of Lead-Exposed Children (TLC) Trial Group: Safety and efficacy of succimer in toddlers with blood lead levels of 20–44 μg/dL. Pediatr. Res. 48, 593–599 (2000)

    Article  Google Scholar 

  72. Wagner, H.M.: Linear programming techniques for regression analysis. J. Am. Stat. Assoc. 54, 206–212 (1959)

    MATH  Article  Google Scholar 

  73. Wang, J.: Bayesian quantile regression for parametric nonlinear mixed effects models. Stat. Methods Appl. (2012)

  74. Yu, K., Lu, Z., Stander, J.: Quantile regression: applications and current research areas. Statistician 52, 331–350 (2003)

    MathSciNet  Google Scholar 

  75. Yu, K., Zhang, J.: A three-parameter asymmetric Laplace distribution and its extension. Commun. Stat., Theory Methods 34, 1867–1879 (2005)

    MATH  Article  Google Scholar 

  76. Yu, K.M., Moyeed, R.A.: Bayesian quantile regression. Stat. Probab. Lett. 54, 437–447 (2001)

    MATH  Article  MathSciNet  Google Scholar 

  77. Yuan, Y., Yin, G.: Bayesian quantile regression for longitudinal studies with nonignorable missing data. Biometrics 66, 105–114 (2010)

    MATH  Article  MathSciNet  Google Scholar 

  78. Zhao, Q.S.: Restricted regression quantiles. J. Multivar. Anal. 72, 78–99 (2000)

    MATH  Article  Google Scholar 

Download references

Acknowledgements

The Centre for Paediatric Epidemiology and Biostatistics benefits from funding support from the Medical Research Council in its capacity as the MRC Centre of Epidemiology for Child Health (G0400546). The UCL Institute of Child Health receives a proportion of funding from the Department of Health’s NIHR Biomedical Research Centres funding scheme.

Author information

Affiliations

  1. Centre for Paediatric Epidemiology and Biostatistics, MRC Centre of Epidemiology for Child Health, Institute of Child Health, University College London, 30 Guilford Street, London, WC1N 1EH, UK

    Marco Geraci

  2. Unit of Biostatistics, Institute of Environmental Medicine, Karolinska Institutet, Nobels väg 13, 17177, Stockholm, Sweden

    Matteo Bottai

Authors
  1. Marco Geraci
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Matteo Bottai
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Marco Geraci.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Geraci, M., Bottai, M. Linear quantile mixed models. Stat Comput 24, 461–479 (2014). https://doi.org/10.1007/s11222-013-9381-9

Download citation

Keywords

  • Best linear predictor
  • Clarke’s derivative
  • Hierarchical models
  • Gaussian quadrature