Abstract
In this work, the problem of transformation and simultaneous variable selection is thoroughly treated via objective Bayesian approaches by the use of default Bayes factor variants. Four uniparametric families of transformations (Box–Cox, Modulus, Yeo-Johnson and Dual), denoted by T, are evaluated and compared. The subjective prior elicitation for the transformation parameter \(\lambda _T\), for each T, is not a straightforward task. Additionally, little prior information for \(\lambda _T\) is expected to be available, and therefore, an objective method is required. The intrinsic Bayes factors and the fractional Bayes factors allow us to incorporate default improper priors for \(\lambda _T\). We study the behaviour of each approach using a simulated reference example as well as two real-life examples.
Similar content being viewed by others
References
Bartlett, M.S.: Comment on D.V. Lindley’s statistical paradox. Biometrika 44, 533–534 (1957)
Berger, J.O., Pericchi, L.R.: The intrinsic Bayes factor for linear models. In: Bernardo, J., Berger, J., Dawid, A., Smith, A. (eds.) Bayesian Statistics, vol. 5, pp. 25–44. Oxford University Press, Oxford (1996a)
Berger, J.O., Pericchi, L.R.: The intrinsic Bayes factor for model selection and prediction. J. Am. Stat. Assoc. 91, 109–122 (1996b)
Berger, J.O., Pericchi, L.R.: Objective Bayesian methods for model selection: Introduction and comparison. In: Lahiri, P. (ed.) ‘Model selection’, Lecture Notes-Monograph Series, vol. 38, Institute of Mathematical Statistics, pp. 135–207 (2001)
Berger, J.O., Pericchi, L.R.: Training samples in objective model selection. Ann. Stat. 32, 841–869 (2004)
Box, G.E.P., Cox, D.R.: An analysis of transformations (with discussion). J. R. Stat. Soc. Ser. B 26, 211–252 (1964)
Casella, G., Moreno, E.: Objective Bayesian variable selection. J. Am. Stat. Assoc. 101, 157–167 (2006)
Charitidou, E., Fouskakis, D., Ntzoufras, I.: Bayesian transformation family selection: moving towards a transformed Gaussian universe. Can. J. Stat. 43, 600–623 (2015)
Consonni, G., Veronese, P.: Compatibility of prior specifications accross linear models. Stat. Sci. 23, 332–363 (2008)
Gottardo, R., Raftery, A.E.: Bayesian robust variable and transformation selection: a unified approach. Can. J. Stat. 37, 1–20 (2009)
Hald, A.: Statistical Theory with Engineering Applications. Wiley, New York (1952)
Hoeting, J.A., Ibrahim, J.G.: Bayesian predictive simultaneous variable and transformation selection in the linear model. J. Comput. Stat. Data Anal. 28, 87–103 (1998)
Hoeting, J.A., Raftery, A.E., Madigan, D.: A method for simultaneous variable and transformation selection in linear regression. J. Comput. Graph. Stat. 11, 485–507 (2002)
Ibrahim, J.G., Chen, M.H.: Power prior distributions for regression models. Stat. Sci. 15, 46–60 (2000)
John, J.A., Draper, N.R.: An alternative family of transformations. Appl. Stat. 29, 190–197 (1980)
Kim, S., Chen, M.H., Ibrahim, J.G., Shah, A.K., Lin, J.: Bayesian inference for multivariate meta-analysis Box–Cox transformation models for individual patient data with applications to evaluation of cholesterol-lowering drugs. Stat. Med. 32, 3972–3990 (2013)
Kuo, L., Mallick, B.: Variable selection for regression models. Sankhyā B 60, 65–81 (1998)
Laud, P.W., Ibrahim, J.G.: Predictive model selection. J. R. Stat. Soc. B 57, 247–262 (1995)
Ley, E., Steel, M.F.J.: On the effect of prior assumptions in Bayesian model averaging with applications to growth regression. J. Appl. Econom. 24, 651–674 (2009)
Madigan, D., York, J.: Bayesian graphical models for discrete data. Int. Stat. Rev. 63, 215–232 (1995)
Miranda, M.F., Zhu, H., Ibrahim, J.G.: Bayesian spatial transformation models with applications in neuroimaging data. Biometrics 69, 1074–1083 (2013)
O’Hagan, A.: Fractional Bayes factors for model comparison. J. R. Stat. Soc. B 57, 99–138 (1995)
Pérez, J.M., Berger, J.O.: Expected-posterior prior distributions for model selection. Biometrika 89, 491–511 (2002)
Pericchi, L.R.: A Bayesian approach to transformations to normality. Biometrika 68, 35–43 (1981)
Scott, J.G., Berger, J.O.: Bayes and empirical-Bayes multiplicity adjustment in the variable-selection problem. Ann. Stat. 38, 2587–2619 (2010)
Sweeting, T.J.: On the choice of the prior distribution for the Box–Cox transformed linear model. Biometrika 71, 127–134 (1984)
Thall, P.F., Russell, K.E., Simon, R.M.: Variable selection in regression via repeated data splitting. J. Am. Stat. Assoc. 6, 416–434 (1997)
Villa, C., Lee, J.E.: Model prior distribution for variable selection in linear regression models (2016). arXiv:1512.08077. http://arxiv.org/abs/1104.0861
Weisberg, S.: Applied Linear Regression, 3rd edn. Wiley-Interscience, New Jersey (2005)
Westerberg, I., Guerrero, J.L., Seibert, J., Beven, K.J., Halldin, S.: Stage-discharge uncertaintly derived with a non-stationary rating curve in the Choluteca river, honduras. Hydrol. Process. 25, 603–613 (2011)
Yang, Y., Christensen, O.F., Sorensen, D.: Analysis of a genetically structured variance heterogeneity model using the Box–Cox transformation. Genet. Res. 93, 33–46 (2011)
Yang, Z.: A modified family of power transformations. Econ. Lett. 92, 14–19 (2006)
Yeo, I.K., Johnson, R.A.: A new family of power transformations to improve normality or symmetry. Biometrika 87, 954–959 (2000)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Charitidou, E., Fouskakis, D. & Ntzoufras, I. Objective Bayesian transformation and variable selection using default Bayes factors. Stat Comput 28, 579–594 (2018). https://doi.org/10.1007/s11222-017-9749-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11222-017-9749-3