Model Detection for Additive Models with Longitudinal Data

Jian Wu; Liugen Xue

doi:10.4236/ojs.2014.410082

Home > Journals > Physics & Mathematics > OJS

OJS> Vol.4 No.10, December 2014

Share This Article:

Open Access

Model Detection for Additive Models with Longitudinal Data

Abstract Full-Text HTML XML

Download as PDF (Size:2602KB) PP. 868-878

DOI: 10.4236/ojs.2014.410082 2,940 Downloads 3,391 Views Citations

Author(s) Leave a comment

Jian Wu, Liugen Xue

Affiliation(s)

¹College of Applied Sciences, Beijing University of Technology, Beijing, China.
²College of Science, Northeastern University, Shenyang, China.

ABSTRACT

In this paper, we consider the problem of variable selection and model detection in additive models with longitudinal data. Our approach is based on spline approximation for the components aided by two Smoothly Clipped Absolute Deviation (SCAD) penalty terms. It can perform model selection (finding both zero and linear components) and estimation simultaneously. With appropriate selection of the tuning parameters, we show that the proposed procedure is consistent in both variable selection and linear components selection. Besides, being theoretically justified, the proposed method is easy to understand and straightforward to implement. Extensive simulation studies as well as a real dataset are used to illustrate the performances.

KEYWORDS

Additive Model, Model Detection, Variable Selection, SCAD Penalty

Conflicts of Interest

The authors declare no conflicts of interest.

Cite this paper

Wu, J. and Xue, L. (2014) Model Detection for Additive Models with Longitudinal Data. Open Journal of Statistics, 4, 868-878. doi: 10.4236/ojs.2014.410082.

References

[1]	Hastie, T.J. and Tibshirani, R.J. (1990) Generalized Additive Models. Chapman and Hall, London.

[2]	Berhane, K. and Tibshirani, R.J. (1998) Generalized Additive Models for Longitudinal Data. The Canadian Journal of Statistics, 26, 517-535. http://dx.doi.org/10.2307/3315715

[3]	Martinussen, T. and Scheike, T.H. (1999) A Semiparametric Additive Regression Model for Longitudinal Data. Biometrika, 86, 691-702. http://dx.doi.org/10.1093/biomet/86.3.691

[4]	Xue, L. (2010) Consistent Model Selection for Marginal Generalized Additive Model for Correlated Data. Journal of the American Statistical Association, 105, 1518-1530. http://dx.doi.org/10.1198/jasa.2010.tm10128

[5]	Hu, T. and Xia, Y.C. (2012) Adaptive Semi-Varying Coefficient Model Selection. Statistica Sinica, 22, 575-599. http://dx.doi.org/10.5705/ss.2010.105

[6]	Tang, Y.L., Wang, H.X., Zhu, Z.Y. and Song, X.Y. (2012) A Unified Variable Selection Approach for Varying Coefficient Models. Statistica Sinica, 22, 601-628. http://dx.doi.org/10.5705/ss.2010.121

[7]	Lian, H. (2012) Shrinkage Estimation for Identification of Linear Components in Additive Models. Statistics and Probability Letters, 82, 225-231. http://dx.doi.org/10.1016/j.spl.2011.10.009

[8]	Qu, A., Lindsay, B.G. and Li, B. (2000) Improving Generalised Estimating Equations Using Quadratic Inference Functions. Biometrika, 87, 823-836. http://dx.doi.org/10.1093/biomet/87.4.823

[9]	Huang, J.Z. (1998) Projection Estimation in Multiple Regression with Application to Functional ANOVA Models. The Annals of Statistics, 26, 242-272. http://dx.doi.org/10.1214/aos/1030563984

[10]	Xue, L. (2009) A Root-N Consistent Backfitting Estimator for Semiparametric Additive Modeling. Statistica Sinica, 19, 1281-1296.

[11]	Wang, H., Li, R. and Tsai, C.L. (2007) Tuning Parameter Selectors for the Smoothly Clipped Absolute Deviation Method. Biometrika, 94, 553-568. http://dx.doi.org/10.1093/biomet/asm053

[12]	Xue, L.G. and Zhu, L.X. (2007) Empirical Likehood for a Varying Coefficient Model with Longitudinal Data. Journal of the American Statistical Association, 102, 642-654.

[13]	Wu, C.O., Chiang, C.T. and Hoover, D.R. (2010) Asymptotic Confidence Regions for Kernel Smoothing of a Varying-Coefficient Model with Longitudinal Data. Journal of the American Statistical Association, 93, 1388-1402.

[14]	De Boor, C. (2001) A Practical Guide to Splines. Springer, New York.