Bayesian Analysis

Bayesian Functional Linear Regression with Sparse Step Functions

Paul-Marie Grollemund, Christophe Abraham, Meïli Baragatti, and Pierre Pudlo

Full-text: Open access


The functional linear regression model is a common tool to determine the relationship between a scalar outcome and a functional predictor seen as a function of time. This paper focuses on the Bayesian estimation of the support of the coefficient function. To this aim we propose a parsimonious and adaptive decomposition of the coefficient function as a step function, and a model including a prior distribution that we name Bayesian functional Linear regression with Sparse Step functions (Bliss). The aim of the method is to recover periods of time which influence the most the outcome. A Bayes estimator of the support is built with a specific loss function, as well as two Bayes estimators of the coefficient function, a first one which is smooth and a second one which is a step function. The performance of the proposed methodology is analysed on various synthetic datasets and is illustrated on a black Périgord truffle dataset to study the influence of rainfall on the production.

Article information

Bayesian Anal., Volume 14, Number 1 (2019), 111-135.

First available in Project Euclid: 19 April 2018

Permanent link to this document

Digital Object Identifier

Primary: 62F15: Bayesian inference
Secondary: 62J05: Linear regression

Bayesian regression functional data support estimate parsimony

Creative Commons Attribution 4.0 International License.


Grollemund, Paul-Marie; Abraham, Christophe; Baragatti, Meïli; Pudlo, Pierre. Bayesian Functional Linear Regression with Sparse Step Functions. Bayesian Anal. 14 (2019), no. 1, 111--135. doi:10.1214/18-BA1095.

Export citation


  • Arlot, S. and Celisse, A. (2010). “A survey of cross-validation procedures for model selection.” Statistics Surveys, 4: 40–79.
  • Baragatti, M. and Pommeret, D. (2012). “A study of variable selection using g-prior distribution with ridge parameter.” Computational Statistics and Data Analysis, 56(6): 1920–1934.
  • Brown, P. J., Fearn, T., and Vannucci, M. (2001). “Bayesian Wavelet Regression on Curves With Application to a Spectroscopic Calibration Problem.” Journal of the American Statistical Association, 96(454): 398–408.
  • Büntgen, U., Egli, S., Camarero, J., Fischer, E., Stobbe, U., Kauserud, H., Tegel, W., Sproll, L., and Stenseth, N. (2012). “Drought-induced decline in Mediterranean truffle harvest.” Nature Climate Change, 2: 827–829.
  • Büntgen, U., Tegel, W., Egli, S., Stobbe, U., Sproll, L., and Stenseth, N. (2011). “Truffles and climate change.” Frontiers in Ecology and the Environment, 9(3): 150–151.
  • Cardot, H., Ferraty, F., and Sarda, P. (1999). “Functional linear model.” Statistics & Probability Letters, 45(1): 11–22.
  • Cardot, H., Ferraty, F., and Sarda, P. (2003). “Spline estimators for the functional linear model.” Statistica Sinica, 13(3): 571–591.
  • Crainiceanu, C. and Goldsmith, A. (2010). “Bayesian Functional Data Analysis Using WinBUGS.” Journal of Statistical Software, Articles, 32(11): 1–33.
  • Crainiceanu, C., Ruppert, D., and Wand, M. P. (2005). “Bayesian Analysis for Penalized Spline Regression Using WinBUGS.” Journal of Statistical Software, 14(14): 1–24.
  • Demerson, J. and Demerson, M. (2014). La truffe, la trufficulture, vues par les Demerson, Uzès (1989–2015). Les éditions de la Fenestrelle.
  • Gelman, A. and Meng, X.-L. (1998). “Simulating normalizing constants: from importance sampling to bridge sampling to path sampling.” Statistical Science, 13(2): 163–185.
  • Goldsmith, J., Huang, L., and Crainiceanu, C. (2014). “Smooth Scalar-on-Image Regression via Spatial Bayesian Variable Selection.” Journal of Computational and Graphical Statistics, 23(1): 46–64.
  • Goldsmith, J., Wand, M. P., and Crainiceanu, C. (2011). “Functional regression via variational Bayes.” Electronic Journal of Statistics, 5: 572–602.
  • Grollemund, P.-M., Abraham, C., Baragatti, M., and Pudlo, P. (2019). “Supplementary Materials: Bayesian Functional Linear Regression with Sparse Step Functions.” Bayesian Analysis.
  • Healy, R., Smith, M., Bonito, G., Pfister, D., Ge, Z., Guevara, G., Williams, G., Stafford, K., Kumar, L., Lee, T., Hobart, C., Trappe, J., Vilgalys, R., and McLaughlin, D. (2013). “High diversity and widespread occurence of mitotic spore mats in ectomycorrhizal Pezizales.” Molecular Ecology, 22(6): 1717–1732.
  • James, G., Wang, J., and Zhu, J. (2009). “Functional linear regression that’s interpretable.” The Annals of Statistics, 37(5A): 2083–2108.
  • Kang, J., Reich, B. J., and Staicu, A.-M. (2016). “Scalar-on-Image Regression via the Soft-Thresholded Gaussian Process.” ArXiv preprint arXiv:1604.03192.
  • Le Tacon, F., Marçais, B., Courvoisier, M., Murat, C., Montpied, P., and Becker, M. (2014). “Climatic variations explain annual fluctuations in French Périgord black truffle wholesale markets but do not explain the decrease in black truffle production over the last 48 years.” Mycorrhiza, 24: S115–S125.
  • Le Tacon, F., Rubini, A., Murat, C., Riccioni, C., Robin, C., Belfiori, B., Zeller, B., De La Varga, H., Akroume, E., Deveau, A., Martin, F., and Paolocci, F. (2016). “Certainties and uncertainties about the life cycle of the Périgord black Truffle (Tuber melanosporum Vittad.).” Annals of Forest Science, 73(1): 105–117.
  • Li, F., Zhang, T., Wang, Q., Gonzalez, M., Maresh, E., and Coan, J. (2015). “Spatial Bayesian Variable Selection and Grouping for High-Dimensional Scalar-on-Image Regression.” The Annals of Applied Statistics, 23(2): 687–713.
  • Marin, J.-M. and Robert, C. (2010). Importance sampling methods for Bayesian discrimination between embedded models, chapter 14, 513–527. New York: Springer-Verlag.
  • Murat, C., Rubini, A., Riccioni, C., De La Varga, H., Akroume, E., Belfiori, B., Guaragno, M., Le Tacon, F., Robin, C., Halkett, F., Martin, F., and Paolocci, F. (2013). “Fine-scale spatial genetic structure of the black truffle (Tuber Melanosporum) investigated with neutral microsatellites and functional mting type genes.” The New Phytologist, 199(1): 176–187.
  • Picheny, V., Servien, R., and Villa-Vialaneix, N. (2016). “Interpretable sparse SIR for functional data.” arXiv preprint arXiv:1606.00614.
  • Ramsay, J. and Silverman, B. (2005). Functional Data Analysis. Springer-Verlag New York.
  • Reiss, P., Goldsmith, J., Shang, H., and Ogden, T. R. (2016). “Methods for scalar-on-function regression.” International Statistical Review.
  • Robert, C. P. (2007). The Bayesian choice: from decision-theoretic foundations to computational implementation. Springer-Verlag New York.
  • Splivallo, R., Rittersma, R., Valdez, N., Chevalier, G., Molinier, V., Wipf, D., and Karlovsky, P. (2012). “Is climate change altering the geographic distribution of truffles?.” Frontiers in Ecology and the Environment, 10(9): 461–462.
  • Tibshirani, R., Saunders, M., Rosset, S., Zhu, J., and Knight, K. (2005). “Sparsity and smoothness via the fused lasso.” Journal of the Royal Statistical Society Series B, 67(1): 91–108.
  • Yuan, M. and Cai, T. (2010). “A reproducing kernel Hilbert space approach to functional linear regression.” The Annals of Statistics, 38(6): 3412–3444.
  • Zhao, Y., Ogden, T., and Reiss, P. (2012). “Wavelet-Based LASSO in Functional Linear Regression.” Journal of Computational and Graphical Statistics, 21(3): 600–617.
  • Zhou, J., Wang, N.-Y., and Wang, N. (2013). “Functional Linear Model with Zero-Value Coefficient Function at Sub-Regions.” Statistica Sinica, 23(1): 25–50.
  • Zhu, H., Yao, F., and Zhang, H. (2014). “Structured functional additive regression in reproducing kernel Hilbert spaces.” Journal of the Royal Statistical Society Series B, 76(3): 581–603.

Supplemental materials

  • Supplementary Materials: Bayesian Functional Linear Regression with Sparse Step Functions. The code of the method is available as an R package at