Model-based boosting in R: a hands-on tutorial using the R package <Emphasis Type="Bold">mboost</Emphasis>

Benjamin Hofner; Andreas Mayr; Nikolay Robinzonov; Matthias Schmid

doi:10.1007/s00180-012-0382-5

Computational Statistics

February 2014, Volume 29, Issue 1–2, pp 3–35 | Cite as

Model-based boosting in R: a hands-on tutorial using the R package mboost

Authors
Authors and affiliations

Benjamin HofnerEmail author
Andreas Mayr
Nikolay Robinzonov
Matthias Schmid

Original Paper

First Online: 22 December 2012

Received: 01 February 2012

Accepted: 14 November 2012

1.5k Downloads
41 Citations

Abstract

We provide a detailed hands-on tutorial for the R add-on package mboost. The package implements boosting for optimizing general risk functions utilizing component-wise (penalized) least squares estimates as base-learners for fitting various kinds of generalized linear and generalized additive models to potentially high-dimensional data. We give a theoretical background and demonstrate how mboost can be used to fit interpretable models of different complexity. As an example we use mboost to predict the body fat based on anthropometric measurements throughout the tutorial.

Keywords

Boosting Component-wise functional gradient descent Generalized additive models Tutorial

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

Notes

Acknowledgments

The authors thank two anonymous referees for their comments that helped to improve this article.

Appendix: Building your own family

Via the constructor function Family(), in mboost there exists an easy way for the user to set up new families. The main required arguments are the loss to be minimized and the negative gradient (ngradient) of the loss. The risk is then commonly defined as the sum of the loss over all observations.

We will demonstrate the usage of this function by (re-) implementing the family to fit quantile regression (the pre-defined family is QuantReg()). In contrast to standard regression analysis, quantile regression (Koenker 2005) does not estimate the conditional expectation of the conditional distribution but the conditional quantiles. Estimation is carried out by minimizing the check function $\rho _{\tau }(\cdot )$:

$$\begin{aligned} \rho _{\tau }(y_i - f_{\tau i} ) = \left\{ \begin{array}{ll} (y_i - f_{\tau i} ) \cdot \tau&\quad (y_i - f_{\tau i} ) \ge 0 \\ (y_i - f_{\tau i} ) \cdot (\tau -1)&\quad (y_i - f_{\tau i} ) <0, \end{array} \right. \end{aligned}$$

which is depicted in Fig. 10b. The loss for our new family is therefore given as:

The check-function is not differentiable at the point 0. However in practice, as the response is continuous, we can ignore this by defining:

$$\begin{aligned} - \frac{\partial \rho _{\tau }(y_i, f_{\tau i})}{\partial f} = \left\{ \begin{array}{l@{\quad }l} \tau&(y_i - f_{\tau i}) \ge 0 \\ \tau -1&(y_i - f_{\tau i}) <0. \end{array} \right. \end{aligned}$$

The negative gradient of our loss is therefore:¹⁵

Of further interest is also the starting value for the algorithm, which is specified via the offset argument. For quantile regression it was demonstrated that the offset may be set to the median of the response (Fenske et al. 2011). With this information, we can already specify our new family for quantile regression:

Case study (ctd.): prediction of body fat

To try our new family we go back to the case study regarding the prediction of body fat. First, we reproduce the model for the median, computed with the pre-defined QuantReg() family (see Sect. 3.4.1), to show that our new family delivers the same results:

To get a better idea of the shape of the conditional distribution we model the median, and the 0.05 and 0.95 quantiles in a small, illustrative example containing only the predictor hipcirc:

Note that for different quantiles, fitting has to be carried out separately, as $\tau $ enters directly in the loss. It is also important that fitting quantile regression generally requires higher stopping iterations than standard regression with the $L_2$ loss, as the negative gradients which are fitted to the base-learners are vectors containing only small values, i.e., $\tau $ and $1-\tau $.

The resulting plot (see Fig. 12) shows how quantile regression can be used to get a better impression of the whole conditional distribution function in a regression setting. In this case, the upper and lower quantiles are not just parallel lines to the median regression line but adapt nicely to the slight heteroscedasticity found in this data example: For smaller values of hipcirc the range between the quantiles is smaller than for higher values. Note that the outer quantile-lines can be interpreted as prediction intervals for new observations (Meinshausen 2006; Mayr et al. 2012c). For more on quantile regression in the context of boosting we refer to Fenske et al. (2011).

Fig. 12
Resulting quantile regression lines, for the median (*solid line*) and the 0.95 and 0.05 quantiles (*upper* and *lower dashed lines*)

References

Bates D, Maechler M, Bolker B (2011) lme4: linear mixed-effects models using S4 classes. http://CRAN.R-project.org/package=lme4, R package version 0.999375-42
Breiman L (1998) Arcing classifiers (with discussion). Ann Stat 26:801–849CrossRefMATHMathSciNetGoogle Scholar
Breiman L (1999) Prediction games and arcing algorithms. Neural Comput 11:1493–1517CrossRefGoogle Scholar
Breiman L (2001) Random forests. Mach Learn 45:5–32CrossRefMATHGoogle Scholar
Bühlmann P (2006) Boosting for high-dimensional linear models. Ann Stat 34:559–583CrossRefMATHGoogle Scholar
Bühlmann P, Hothorn T (2007) Boosting algorithms: regularization, prediction and model fitting (with discussion). Stat Sci 22:477–522CrossRefMATHGoogle Scholar
Bühlmann P, Yu B (2003) Boosting with the $L_2$ loss: regression and classification. J Am Stat Assoc 98: 324–338Google Scholar
de Boor C (1978) A practical guide to splines. Springer, New YorkCrossRefMATHGoogle Scholar
Efron B, Hastie T, Johnstone L, Tibshirani R (2004) Least angle regression. Ann Stat 32:407–499CrossRefMATHMathSciNetGoogle Scholar
Eilers PHC, Marx BD (1996) Flexible smoothing with B-splines and penalties (with discussion). Stat Sci 11:89–121CrossRefMATHMathSciNetGoogle Scholar
Fan J, Lv J (2010) A selective overview of variable selection in high dimensional feature space. Statistica Sinica 20:101–148MATHMathSciNetGoogle Scholar
Fenske N, Kneib T, Hothorn T (2011) Identifying risk factors for severe childhood malnutrition by boosting additive quantile regression. J Am Stat Assoc 106(494):494–510CrossRefMATHMathSciNetGoogle Scholar
Freund Y, Schapire R (1996) Experiments with a new boosting algorithm. In: Proceedings of the thirteenth international conference on machine learning theory. Morgan Kaufmann, San Francisco, pp 148–156Google Scholar
Friedman JH (2001) Greedy function approximation: a gradient boosting machine. Ann Stat 29:1189–1232CrossRefMATHGoogle Scholar
Friedman JH, Hastie T, Tibshirani R (2000) Additive logistic regression: a statistical view of boosting (with discussion). Ann Stat 28:337–407CrossRefMATHMathSciNetGoogle Scholar
Garcia AL, Wagner K, Hothorn T, Koebnick C, Zunft HJF, Tippo U (2005) Improved prediction of body fat by measuring skinfold thickness, circumferences, and bone breadths. Obes Res 13(3):626–634CrossRefGoogle Scholar
Hastie T (2007) Comment: Boosting algorithms: regularization, prediction and model fitting. Stat Sci 22:513–515CrossRefMATHMathSciNetGoogle Scholar
Hastie T, Tibshirani R (1990) Generalized additive models. Chapman & Hall, LondonMATHGoogle Scholar
Hastie T, Tibshirani R, Friedman J (2009) The elements of statistical learning: data mining, inference, and prediction, 2nd edn. Springer, New YorkCrossRefGoogle Scholar
Hofner B (2011) Boosting in structured additive models. PhD thesis, Department of Statistics, Ludwig-Maximilians-Universität München, MunichGoogle Scholar
Hofner B, Hothorn T, Kneib T, Schmid M (2011a) A framework for unbiased model selection based on boosting. J Comput Graph Stat 20:956–971CrossRefMathSciNetGoogle Scholar
Hofner B, Müller J, Hothorn T (2011b) Monotonicity-constrained species distribution models. Ecology 92:1895–1901CrossRefGoogle Scholar
Hothorn T, Hornik K, Zeileis A (2006) Unbiased recursive partitioning: a conditional inference framework. J Comput Graph Stat 15:651–674CrossRefMathSciNetGoogle Scholar
Hothorn T, Bühlmann P, Kneib T, Schmid M, Hofner B (2010) Model-based boosting 2.0. J Mach Learn Res 11:2109–2113MATHMathSciNetGoogle Scholar
Hothorn T, Bühlmann P, Kneib T, Schmid M, Hofner B (2012) mboost: model-based boosting. http://CRAN.R-project.org/package=mboost, R package version 2.1-3
Kneib T, Hothorn T, Tutz G (2009) Variable selection and model choice in geoadditive regression models. Biometrics 65:626–634. Web appendix accessed at http://www.biometrics.tibs.org/datasets/071127P.htm on 16 Apr 2012Google Scholar
Koenker R (2005) Quantile regression. Cambridge University Press, New YorkCrossRefMATHGoogle Scholar
Mayr A, Fenske N, Hofner B, Kneib T, Schmid M (2012a) Generalized additive models for location, scale and shape for high-dimensional data—a flexible approach based on boosting. J R Stat Soc Ser C (Appl Stat) 61(3):403–427CrossRefMathSciNetGoogle Scholar
Mayr A, Hofner B, Schmid M (2012b) The importance of knowing when to stop—a sequential stopping rule for component-wise gradient boosting. Methods Inf Med 51(2):178–186CrossRefGoogle Scholar
Mayr A, Hothorn T, Fenske N (2012c) Prediction intervals for future BMI values of individual children—a non-parametric approach by quantile boosting. BMC Med Res Methodol 12(6):1–13Google Scholar
McCullagh P, Nelder JA (1989) Generalized linear models, 2nd edn. Chapman & Hall, LondonCrossRefMATHGoogle Scholar
Meinshausen N (2006) Quantile regression forests. J Mach Learn Res 7:983–999MATHMathSciNetGoogle Scholar
Pinheiro J, Bates D (2000) Mixed-effects models in S and S-PLUS. Springer, New YorkCrossRefMATHGoogle Scholar
Pinheiro J, Bates D, DebRoy S, Sarkar D, R Development Core Team (2012) nlme: linear and nonlinear mixed effects models. http://CRAN.R-project.org/package=nlme, R package version 3.1-103
R Development Core Team (2012) R: a language and Environment for statistical computing. R Foundation for Statistical Computing, Vienna. http://www.R-project.org, ISBN 3-900051-07-0
Ridgeway G (2010) gbm: generalized boosted regression models. http://CRAN.R-project.org/package=gbm, R package version 1.6-3.1
Schmid M, Hothorn T (2008a) Boosting additive models using component-wise P-splines. Comput Stat Data Anal 53:298–311CrossRefMATHMathSciNetGoogle Scholar
Schmid M, Hothorn T (2008b) Flexible boosting of accelerated failure time models. BMC Bioinform 9:269CrossRefGoogle Scholar
Schmid M, Potapov S, Pfahlberg A, Hothorn T (2010) Estimation and regularization techniques for regression models with multidimensional prediction functions. Stat Comput 20:139–150CrossRefMathSciNetGoogle Scholar
Schmid M, Hothorn T, Maloney KO, Weller DE, Potapov S (2011) Geoadditive regression modeling of stream biological condition. Environ Ecol Stat 18(4):709–733CrossRefMathSciNetGoogle Scholar
Sobotka F, Kneib T (2010) Geoadditive expectile regression. Comput Stat Data Anal 56(4):755–767CrossRefMathSciNetGoogle Scholar
Tierney L, Rossini AJ, Li N, Sevcikova H (2011) snow: simple network of workstations. http://CRAN.R-project.org/package=snow, R package version 0.3-7
Urbanek S (2011) multicore: parallel processing of R code on machines with multiple cores or CPUs. http://CRAN.R-project.org/package=multicore, R package version 0.1-7

Copyright information

Authors and Affiliations

Benjamin Hofner
- 1
Email author
Andreas Mayr
- 1
Nikolay Robinzonov
- 2
Matthias Schmid
- 1

1.Department of Medical Informatics, Biometry and EpidemiologyFriedrich-Alexander-Universität Erlangen-NürnbergErlangenGermany
2.Department of StatisticsLudwig-Maximilians-Universität MünchenMunichGermany