Two sample inference in functional linear models

MSC 2000: Primary62J15; Secondary62G08 and 62F03. Abstract: We propose a method of comparing two functional linear models in which explanatoryvariables are functions (curves) and responses can be either scalars or functions. In such models, the role of parameter vectors (or matrices) is played by integral operators acting on a function space. We test the null hypothesis that these operators are the same in two independent samples. The complexityof the test statistics increases as we move from scalar to functional responses and relax assumptions on the covariance structure of the regressors. Theyall, however, have an asy mptotic chi-squared distribution with the number of degrees of freedom which depends on a specific setting. The test statistics are readilycomputable using the R package fda, and have good finite sample properties. The test is applied to egg-laying curves of Mediterranean flies and to data from terrestrial magnetic observatories. The Canadian Journal of Statistics 37: 571-591; 2009 © 2009 Statistical Societyof Canada R´ esumNous proposons une m´

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

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

[3]  Fang Yao,et al.  Functional Variance Processes , 2006 .

[4]  D. Bosq.  Linear Processes in Function Spaces: Theory And Applications , 2000 .

[5]  R. Eubank,et al.  The delta method for analytic functions of random operators with application to functional data , 2007, 0711.4368.

[6]  Badih Ghattas,et al.  Classifying densities using functional regression trees: Applications in oceanology , 2007, Comput. Stat. Data Anal..

[7]  Linda Partridge,et al.  Life history response of Mediterranean fruit flies to dietary restriction , 2002, Aging cell.

[8]  R. Fildes.  Journal of the Royal Statistical Society (B): Gary K. Grunwald, Adrian E. Raftery and Peter Guttorp, 1993, “Time series of continuous proportions”, 55, 103–116.☆ , 1993 .

[9]  Denis Bosq,et al.  Linear Processes in Function Spaces , 2000 .

[10]  J. Ramsay,et al.  The historical functional linear model , 2003 .

[11]  Werner Dubitzky,et al.  Knowledge Exploration in Life Science Informatics , 2004, Lecture Notes in Computer Science.

[12]  Philippe C. Besse,et al.  Autoregressive Forecasting of Some Functional Climatic Variations , 2000 .

[13]  Satoru Miyano,et al.  Functional Data Analysis of the Dynamics of Gene Regulatory Networks , 2004, KELSI.

[14]  P. Kokoszka,et al.  Removal of Nonconstant Daily Variation by Means of Wavelet and Functional Data Analysis , 2009 .

[15]  Piotr Kokoszka,et al.  Testing for lack of dependence in the functional linear model , 2008 .

[16]  James O. Ramsay,et al.  Functional Data Analysis , 2005 .

[17]  Richard H. Glendinning,et al.  Classifying functional time series , 2007, Signal Process..

[18]  Serge Guillas,et al.  The inclusion of exogenous variables in functional autoregressive ozone forecasting , 2002 .

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

[20]  Algirdas Laukaitis,et al.  Functional data analysis for clients segmentation tasks , 2005, Eur. J. Oper. Res..

[21]  Frédéric Ferraty,et al.  Factor-based comparison of groups of curves , 2007, Comput. Stat. Data Anal..

[22]  Piotr Kokoszka,et al.  Portmanteau Test of Independence for Functional Observations , 2007 .

[23]  Z. Q. John Lu,et al.  Nonparametric Functional Data Analysis: Theory And Practice , 2007, Technometrics.

[24]  Ulrich Stadtmüller,et al.  Generalized functional linear models , 2005 .

[25]  Michael E. Brown,et al.  Introduction to Space Physics , 1995 .

[26]  Piotr Kokoszka,et al.  Testing the stability of the functional autoregressive process , 2010, J. Multivar. Anal..

[27]  Jeffrey S. Morris,et al.  Journal of the American Statistical Association Using Wavelet-based Functional Mixed Models to Characterize Population Heterogeneity in Accelerometer Profiles Using Wavelet-based Functional Mixed Models to Characterize Population Heterogeneity in Accelerometer Profiles: a Case Study , 2022 .

[28]  André Mas,et al.  Testing hypotheses in the functional linear model , 2003 .

[29]  M. Febrero,et al.  Outlier detection in functional data by depth measures, with application to identify abnormal NOx levels , 2008 .

[30]  Jane-Ling Wang,et al.  Functional canonical analysis for square integrable stochastic processes , 2003 .

[31]  Belén Fernández de Castro,et al.  Functional Samples and Bootstrap for Predicting Sulfur Dioxide Levels , 2005, Technometrics.

[32]  Manuel Grande,et al.  Current understanding of magnetic storms: storm-substorm relationships , 1998 .

[33]  Piotr Kokoszka,et al.  Detecting changes in the mean of functional observations , 2009 .

[34]  Tailen Hsing,et al.  On rates of convergence in functional linear regression , 2007 .

[35]  H. Müller,et al.  FUNCTIONAL RESPONSE MODELS , 2004 .

[36]  Lubos Prchal,et al.  Changes in atmospheric radiation from the statistical point of view , 2007, Comput. Stat. Data Anal..

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

[38]  Algirdas Laukaitis,et al.  Functional Data Analysis of Payment Systems , 2002 .

[39]  A. Cuevas,et al.  Linear functional regression: The case of fixed design and functional response , 2002 .

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

[41]  Jeng-Min Chiou,et al.  Diagnostics for functional regression via residual processes , 2007, Comput. Stat. Data Anal..