Unified empirical likelihood ratio tests for functional concurrent linear models and the phase transition from sparse to dense functional data

Summary We consider the problem of testing functional constraints in a class of functional concurrent linear models where both the predictors and the response are functional data measured at discrete time points. We propose test procedures based on the empirical likelihood with bias-corrected estimating equations to conduct both pointwise and simultaneous inferences. The asymptotic distributions of the test statistics are derived under the null and local alternative hypotheses, where sparse and dense functional data are considered in a unified framework. We find a phase transition in the asymptotic null distributions and the orders of detectable alternatives from sparse to dense functional data. Specifically, the tests proposed can detect alternatives of √n-order when the number of repeated measurements per curve is of an order larger than nη0 with n being the number of curves. The transition points η0 for pointwise and simultaneous tests are different and both are smaller than the transition point in the estimation problem. Simulation studies and real data analyses are conducted to demonstrate the methods proposed.

[1]  Jin-Ting Zhang,et al.  STATISTICAL INFERENCES FOR LINEAR MODELS WITH FUNCTIONAL RESPONSES , 2011 .

[2]  Byeong U. Park,et al.  Time-Varying Additive Models for Longitudinal Data , 2013 .

[3]  T. Hsing,et al.  Canonical correlation for stochastic processes , 2008 .

[4]  Chenlei Leng,et al.  Empirical likelihood and quantile regression in longitudinal data analysis , 2011 .

[5]  Paul Marriott,et al.  On the Differential Geometry of the Wald Test With Nonlinear Restrictions , 1996 .

[6]  Hengjian Cui,et al.  On Bartlett correction of empirical likelihood in the presence of nuisance parameters , 2006 .

[7]  A. Owen.  Empirical likelihood ratio confidence intervals for a single functional , 1988 .

[8]  M. Lindquist.  The Statistical Analysis of fMRI Data. , 2008, 0906.3662.

[9]  Wenyang Zhang,et al.  Variable Bandwidth Selection in Varying-Coefficient Models , 2000 .

[10]  Jun Zhang,et al.  Functional Concurrent Linear Regression Model for Spatial Images , 2011 .

[11]  Zhibiao Zhao,et al.  Unified inference for sparse and dense longitudinal models. , 2013, Biometrika.

[12]  A. Balakrishnan.  Estimation and detection theory for multiple stochastic processes , 1960 .

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

[14]  Vincent N. LaRiccia,et al.  Convergence rates for smoothing spline estimators in varying coefficient models , 2010 .

[15]  H. Müller,et al.  Functional Data Analysis for Sparse Longitudinal Data , 2005 .

[16]  Jianqing Fan,et al.  Local polynomial modelling and its applications , 1994 .

[17]  E. Mammen.  Bootstrap and Wild Bootstrap for High Dimensional Linear Models , 1993 .

[18]  Jean-Marie Dufour,et al.  Nonlinear hypotheses, inequality restrictions, and non-nested hypotheses: exact simultaneous tests in linear regressions , 1989 .

[19]  T. Hsing,et al.  Uniform convergence rates for nonparametric regression and principal component analysis in functional/longitudinal data , 2010, 1211.2137.

[20]  Wolfgang Karl Härdle,et al.  An empirical likelihood goodness‐of‐fit test for time series , 2003 .

[21]  T. Lai,et al.  Self-Normalized Processes: Limit Theory and Statistical Applications , 2001 .

[22]  Alois Kneip,et al.  Common Functional Principal Components , 2006 .

[23]  E. Mammen,et al.  Comparing Nonparametric Versus Parametric Regression Fits , 1993 .

[24]  B. Silverman,et al.  Estimating the mean and covariance structure nonparametrically when the data are curves , 1991 .

[25]  Runze Li,et al.  Analysis of Longitudinal Data With Semiparametric Estimation of Covariance Function , 2007, Journal of the American Statistical Association.

[26]  M. Wall.  A close look at the spatial structure implied by the CAR and SAR models , 2004 .

[27]  J. F. Lawless,et al.  Estimating equations, empirical likelihood and constraints on parameters† , 1995 .

[28]  Jin-Ting Zhang,et al.  Statistical inferences for functional data , 2007, 0708.2207.

[29]  R. Bivand.  Spatial Dependence: Weighting Schemes, Statistics and Models , 2015 .

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

[31]  Thomas J. DiCiccio,et al.  Empirical Likelihood is Bartlett-Correctable , 1991 .

[32]  X. Shao,et al.  A self‐normalized approach to confidence interval construction in time series , 2010, 1005.2137.

[33]  J. Faraway.  Regression analysis for a functional response , 1997 .

[34]  Qi-Man Shao,et al.  Self-normalized limit theorems: A survey , 2013 .

[35]  A. Owen.  Empirical Likelihood Ratio Confidence Regions , 1990 .

[36]  Song-xi Chen,et al.  Anova For Longitudinal Data With Missing Values , 2010, 1211.2979.

[37]  Ingrid Van Keilegom,et al.  Two-sample tests in functional data analysis starting from discrete data , 2007 .

[38]  Sw. Banerjee,et al.  Hierarchical Modeling and Analysis for Spatial Data , 2003 .

[39]  Lixing Zhu,et al.  Empirical Likelihood for a Varying Coefficient Model With Longitudinal Data , 2007 .

[40]  Jianqing Fan,et al.  Two‐step estimation of functional linear models with applications to longitudinal data , 1999 .

[41]  Peter C. B. Phillips,et al.  ON THE FORMULATION OF WALD TESTS OF NONLINEAR RESTRICTIONS , 1986 .

[42]  E. A. Sylvestre,et al.  Principal modes of variation for processes with continuous sample curves , 1986 .

[43]  Wenceslao González-Manteiga,et al.  An updated review of Goodness-of-Fit tests for regression models , 2013, TEST.

[44]  Ingrid Van Keilegom,et al.  A review on empirical likelihood methods for regression , 2009 .