Abstract
We propose a procedure for testing the linearity of a scalar-on-function regression relationship. To do so, we use the functional generalized additive model (FGAM), a recently developed extension of the functional linear model. For a functional covariate \(X(t)\), the FGAM models the mean response as the integral with respect to \(t\) of \(F\{X(t),t\}\) where \(F(\cdot ,\cdot )\) is an unknown bivariate function. The FGAM can be viewed as the natural functional extension of generalized additive models. We show how the functional linear model can be represented as a simple mixed model nested within the FGAM. Using this representation, we then consider restricted likelihood ratio tests for zero variance components in mixed models to test the null hypothesis that the functional linear model holds. The methods are general and can also be applied to testing for interactions in a multivariate additive model or for testing for no effect in the functional linear model. The performance of the proposed tests is assessed on simulated data and in an application to measuring diesel truck emissions, where strong evidence of nonlinearities in the relationship between the functional predictor and the response are found.
Similar content being viewed by others
References
Ait-Saïdi, A., Ferraty, F., Kassa, R., Vieu, P.: Cross-valiyeard estimations in the single-functional index model. Statistics 42(6), 475–494 (2008)
Asencio, M., Hooker, G., Gao, H.O.: Functional convolution models. Statist. Model. 4(4), 1–21, http://www.bscb.cornell.edu/~hooker/EmissionsPaper.pdf (2014)
Bates, D., Maechler, M., Bolker, B.: lme4: Linear mixed-effects models using S4 classes. R package version 1.0–4. http://CRAN.R-project.org/package=lme4 (2013)
Cardot, H., Ferraty, F., Mas, A., Sarda, P.: Testing hypotheses in the functional linear model. Scand. J. Stat. 30(1), 241–255 (2003)
Chen, D., Hall, P., Müller, H.G.: Single and multiple index functional regression models with nonparametric link. Ann. Stat. 39(3), 1720–1747 (2011)
Clark, N.N., Gautam, M., Wayne, W.S., Lyons, G.W., Thompson, G.J.: Heavy-duty vehicle chassis dynamometer testing for emissions inventory, air quality modeling, source apportionment, and air toxics emissions inventory. Technical Report CRC Rep. No. E55/59, Coordinating Research Council, Inc. (CRC), http://www.crcao.com/reports/recentstudies2007/E-55-59/E-55_59_Final_Report_23AUG2007.pdf (2007)
Clark, N.N., Vora, K.A., Wang, L., Gautam, M., Wayne, W.S., Thompson, G.J.: Expressing cycles and their emissions on the basis of properties and results from other cycles. Environ. Sci. Technol. 44(15), 5986–5992 (2010)
Core Team, R.: A language and environment for statistical computing. R Foundation for Statistical Computing, http://www.R-project.org/ (2012)
Crainiceanu, C.M., Ruppert, D.: Likelihood ratio tests in linear mixed models with one variance component. J. R. Stat. Soc. 66(1), 165–185 (2004)
Crainiceanu, C.M., Reiss, P.T., Goldsmith, J., Huang, L., Huo, L., Scheipl, F.: Refund: regression with functional data. R package version 0.1-7, http://CRAN.R-project.org/package=refund (2013)
Febrero-Bande, M., Oviedo de la Fuente, M.: Statistical computing in functional data analysis: The R package fda.usc. J. Stat. Softw, 51(4):1–28, http://www.jstatsoft.org/v51/i04/ (2012)
Febrero-Bande, M., Galeano, P., González-Manteiga, W.: Generalized additive models for functional data. TEST 22(2), 278–292 (2013)
Ferraty, F., Vieu, P.: Nonparametric Functional Data Analysis: Theory and Practice. Springer Verlag, Berlin (2006a)
Ferraty, F., Vieu, P.: npfda NonParametric functional data analysis. http://www.math.univ-toulouse.fr/staph/npfda/ (2006b)
Gabrys, R., Horváth, L., Kokoszka, P.: Tests for error correlation in the functional linear model. J. Am. Stat. Assoc. 105(491), 1113–1125 (2010)
García-Portugués, E., González-Manteiga, W., Febrero-Bande, M.: A goodness-of-fit test for the functional linear model with scalar response. J. Comput. Graph. Stat. (2013, page to appear)
Goldsmith, J., Bobb, J., Crainiceanu, C.M., Caffo, B., Reich, D.: Penalized functional regression. J. Comput. Graph. Stat. 20(4), 830–851 (2011)
Greven, S., Crainiceanu, C.M., Küchenhoff, H., Peters, A.: Restricted likelihood ratio testing for zero variance components in linear mixed models. J. Comput. Graph. Stat. 17(4), 870–891 (2008)
Guillas, S., Lai, M.J.: Bivariate splines for spatial functional regression models. J. Nonparametr. Stat. 22(4), 477–497 (2010)
Horváth, L., Reeder, R.W.: A test of significance in functional quadratic regression. Bernoulli. (2014, to appear)
James, G.M., Silverman, B.W.: Functional adaptive model estimation. J. Am. Stat. Assoc. 100(470), 565–577 (2005)
Kong, D., Staicu, A.M., Maity, A.: Classical testing in functional linear models. Technical report, North Carolina State University, http://www4.stat.ncsu.edu/ staicu/papers/ClassicalTest\_FLM\_KSM.pdf. (2013, submitted)
Li, Y., Wang, N., Carroll, R.J.: Generalized functional linear models with semiparametric single-index interactions. J. Am. Stat. Assoc. 105(490), 621–633 (2010)
Marx, B.D., Eilers, P.H.C.: Multidimensional penalized signal regression. Technometrics 47(1), 13–22 (2005)
McLean, M.W., Scheipl, F., Hooker, G., Greven, S., Ruppert, D.: Bayesian functional generalized additive models with sparsely observed covariates. http://arxiv.org/abs/1305.3585 (2013, submitted)
McLean, M.W., Hooker, G., Staicu, A.M., Scheipl, F., Ruppert, D.: Functional generalized additive models. J. Comput. Graph. Stat. 23(1), 249–269 (2014). doi:10.1080/10618600.2012.729985
Müller, H.G., Wu, Y., Yao, Y.: Continuously additive models for nonlinear functional regression. Biometrika. 100(3), doi:10.1093/biomet/ast004. http://biomet.oxfordjournals.org/content/100/3/607 (2013)
Müller, H.G., Wu, Y., Yao, Y.: Continuously additive models for nonlinear functional regression. Biometrika. 100(3), doi:10.1093/biomet/ast004. http://biomet.oxfordjournals.org/content/100/3/607 (2013)
Patterson, H.D., Thompson, R.: Recovery of inter-block information when block sizes are unequal. Biometrika 58(3), 545–554 (1971)
Pinheiro, J.C., Bates, D.M.: Linear mixed-effects models: basic concepts and examples. Springer, New York (2000)
Pinheiro, J.C., Bates, D.M., DebRoy, S., Deepayan Sarkar., Core Team, R.: nlme: Linear and Nonlinear Mixed Effects Models, R package version 3.1-111 (2013)
Ramsay, J.O., Silverman, B.W.: Functional Data Analysis, 2nd edn. Springer, New York (2005)
Reiss, P.T., Ogden, R.T.: Smoothing parameter selection for a class of semiparametric linear models. J. R. Stat. Soc. 71(2), 505–523 (2009)
Ruppert, D., Wand, M.P., Carroll, R.J.: Semiparametric regression. Cambridge University Press, New York (2003)
SAS Institute Inc.: SAS/STAT9.2 User’s Guide (2008)
Scheipl, F., Greven, S., Küchenhoff, H.: Size and power of tests for a zero random effect variance or polynomial regression in additive and linear mixed models. Comput. Stat. Data Anal. 52(7), 3283–3299 (2008)
Swihart Bruce J., Goldsmith Jeff., Crainiceanu Ciprian M.: Restricted likelihood ratio tests for functional effects in the functional linear model. Technometrics, (2014, to appear)
Wang, X., Ruppert, D.: Optimal prediction in an additive functional model. http://arxiv.org/abs/1301.4954 (2013, submitted)
Wang, Y.: Smoothing Splines: Methods and Applications. CRC Press, Boca Raton (2011)
Wang, Y., Chen, H.: On testing an unspecified function through a linear mixed effects model with multiple variance components. Biometrics 68(4), 1113–1125 (2012). doi:10.1111/j.1541-0420.2012.01790.x
Wood, S.N.: Generalized Additive Models: An Introduction with R. CRC Press, Boca Raton (2006a)
Wood, S.N.: Low-rank scale-invariant tensor product smooths for generalized additive mixed models. Biometrics 62(4), 1025–1036 (2006b)
Wood, S.N.: Fast stable restricted maximum likelihood and marginal likelihood estimation of semiparametric generalized linear models. J. R. Stat. Soc. 73(1), 3–36 (2011)
Wood, S.N.: On p values for smooth components of an extended generalized additive model. Biometrika 100(1), 221–228 (2013)
Wood, S.N., Scheipl, F., Faraway, J.J.: Straightforward intermediate rank tensor product smoothing in mixed models. Stat. Comput. 23(3), 341–360 (2013)
Zhang, J.-T., Chen, J.: Statistical inferences for functional data. Ann. Stat. 35(3), 1052–1079 (2007)
Acknowledgments
Much of this work was completed while the first author was a PhD student at Cornell University. He thanks NSERC for support while completing his studies. The authors wish to thank Ray Carroll for helpful comments on an early version of the manuscript and Oliver Gao for providing the emissions data.
Author information
Authors and Affiliations
Corresponding author
Appendix
Appendix
1.1 Form of the one variance component RLRT statistic distribution
For the linear mixed model \(\varvec{y}=\mathbb {X}{\varvec{\beta }}+\mathbb {Z}\varvec{b},\ \varvec{b}\sim N(\mathbf {0},\sigma _1^2\mathbb {I}_{q_1})\),
\({\varvec{\varepsilon }}\sim N(\mathbf {0},\sigma ^2\mathbb {I})\), the restricted likelihood test statistic has distribution
where \(\lambda =\sigma _1^2/\sigma ^2\) and \(U(\lambda )=N(\lambda )/D(\lambda )\) with
for \(w _k\mathop {\sim }\limits ^{{\text{ i.i.d. }}}N(0,1);\ k=1,\ldots ,N-q_0-1\) (Crainiceanu and Ruppert 2004). The \(\mu _k\) are the eigenvalues of the matrix \(\mathbb {Z}^T(\mathbb {I}_N-\mathbb {X}(\mathbb {X}^T\mathbb {X})\mathbb {X}^T)\mathbb {Z}\). The eigendecompostion of the \(q_1\times q_1\) matrix need only be computed once, and then all that is required to obtain a draw from the RLRT distribution is simulation of \(q_1\) \(\chi ^2_1\) random variables and one \(\chi ^2_{N-q_0-q_1-1}\) random variable.
Rights and permissions
About this article
Cite this article
McLean, M.W., Hooker, G. & Ruppert, D. Restricted likelihood ratio tests for linearity in scalar-on-function regression. Stat Comput 25, 997–1008 (2015). https://doi.org/10.1007/s11222-014-9473-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11222-014-9473-1