Nonparametric inference in generalized functional linear models

We propose a roughness regularization approach in making nonparametric inference for generalized functional linear models. In a reproducing kernel Hilbert space framework, we construct asymptotically valid confidence intervals for regression mean, prediction intervals for future response and various statistical procedures for hypothesis testing. In particular, one procedure for testing global behaviors of the slope function is adaptive to the smoothness of the slope function and to the structure of the predictors. As a by-product, a new type of Wilks phenomenon [Ann. Math. Stat. 9 (1938) 60-62; Ann. Statist. 29 (2001) 153-193] is discovered when testing the functional linear models. Despite the generality, our inference procedures are easy to implement. Numerical examples are provided to demonstrate the empirical advantages over the competing methods. A collection of technical tools such as integro-differential equation techniques [Trans. Amer. Math. Soc. (1927) 29 755-800; Trans. Amer. Math. Soc. (1928) 30 453-471; Trans. Amer. Math. Soc. (1930) 32 860-868], Stein's method [Ann. Statist. 41 (2013) 2786-2819] [Stein, Approximate Computation of Expectations (1986) IMS] and functional Bahadur representation [Ann. Statist. 41 (2013) 2608-2638] are employed in this paper.

[1]  Gitta Kutyniok,et al.  1 . 2 Sparsity : A Reasonable Assumption ? , 2012 .

[2]  C. Morris.  Natural Exponential Families with Quadratic Variance Functions , 1982 .

[3]  B. Silverman,et al.  Spline Smoothing: The Equivalent Variable Kernel Method , 1984 .

[4]  Jianqing Fan,et al.  Test of Significance When Data Are Curves , 1998 .

[5]  George D. Birkhoff,et al.  Boundary value and expansion problems of ordinary linear differential equations , 1908 .

[6]  C. Stein.  Approximate computation of expectations , 1986 .

[7]  Douglas W. Nychka,et al.  Splines as Local Smoothers , 1995 .

[8]  Jianqing Fan.  Test of Significance Based on Wavelet Thresholding and Neyman's Truncation , 1996 .

[9]  R. W. Wedderburn.  Quasi-likelihood functions, generalized linear models, and the Gauss-Newton method , 1974 .

[10]  S. S. Wilks.  The Large-Sample Distribution of the Likelihood Ratio for Testing Composite Hypotheses , 1938 .

[11]  Kengo Kato,et al.  Gaussian approximations and multiplier bootstrap for maxima of sums of high-dimensional random vectors , 2012, 1212.6906.

[12]  Sara van de Geer,et al.  Penalized quasi-likelihood estimation in partial linear models , 1997 .

[13]  Jing Lei.  Adaptive Global Testing for Functional Linear Models , 2014 .

[14]  K. Ritter,et al.  MULTIVARIATE INTEGRATION AND APPROXIMATION FOR RANDOM FIELDS SATISFYING SACKS-YLVISAKER CONDITIONS , 1995 .

[15]  M. Stone.  A comparison of the series of Fourier and Birkhoff , 1926 .

[16]  Nadine Hilgert,et al.  Minimax adaptive tests for the Functional Linear model , 2012, 1206.1194.

[17]  Florencio I. Utreras,et al.  Boundary effects on convergence rates for Tikhonov regularization , 1988 .

[18]  T. Tony Cai,et al.  Minimax and Adaptive Prediction for Functional Linear Regression , 2012 .

[19]  Peter F. de Jong,et al.  A central limit theorem for generalized quadratic forms , 1987 .

[20]  G. Reinert,et al.  Multivariate normal approximation with Stein’s method of exchangeable pairs under a general linearity condition , 2007, 0711.1082.

[21]  J. Sacks,et al.  Designs for Regression Problems with Correlated Errors III , 1966 .

[22]  P. Hall.  On the rate of convergence of normal extremes , 1979 .

[23]  J. Sacks,et al.  Designs for Regression Problems With Correlated Errors: Many Parameters , 1968 .

[24]  Jianqing Fan,et al.  Generalized likelihood ratio statistics and Wilks phenomenon , 2001 .

[25]  L. Goldstein,et al.  A New Class of Kernels for Nonparametric Curve Estimation , 1993 .

[26]  I. Molchanov.  Theory of Random Sets , 2005 .

[27]  P. Hall,et al.  Properties of principal component methods for functional and longitudinal data analysis , 2006, math/0608022.

[28]  M. Yuan,et al.  A Reproducing Kernel Hilbert Space Approach to Functional Linear Regression , 2010, 1211.2607.

[29]  Harrison H. Zhou,et al.  Estimation in Functional Regression for General Exponential Families , 2012 .

[30]  Charles R. Johnson,et al.  Matrix analysis , 1985, Statistical Inference for Engineers and Data Scientists.

[31]  H. Muller,et al.  Generalized functional linear models , 2005, math/0505638.

[32]  I. Pinelis.  OPTIMUM BOUNDS FOR THE DISTRIBUTIONS OF MARTINGALES IN BANACH SPACES , 1994, 1208.2200.

[33]  Y. Rinott,et al.  On coupling constructions and rates in the CLT for dependent summands with applications to the antivoter model and weighted $U$-statistics , 1997 .

[34]  T. Tony Cai,et al.  Prediction in functional linear regression , 2006 .

[35]  Florentina Bunea,et al.  Adaptive inference for the mean of a Gaussian process in functional data , 2011 .

[36]  M. Kosorok.  Introduction to Empirical Processes and Semiparametric Inference , 2008 .

[37]  Yosef Rinott,et al.  Multivariate normal approximations by Stein's method and size bias couplings , 1996 .

[38]  Guang Cheng,et al.  Local and global asymptotic inference in smoothing spline models , 2012, 1212.6788.

[39]  Claudia Biermann,et al.  Mathematical Methods Of Statistics , 2016 .

[40]  Joel L. Horowitz,et al.  Methodology and convergence rates for functional linear regression , 2007, 0708.0466.

[41]  Jane-ling Wang,et al.  Functional linear regression analysis for longitudinal data , 2005, math/0603132.

[42]  P. Sarda,et al.  Smoothing splines estimators for functional linear regression , 2009, 0902.4344.

[43]  S. Mendelson.  Empirical Processes with a Bounded Ψ1 Diameter , 2010 .