Longitudinal functional principal component analysis.

We introduce models for the analysis of functional data observed at multiple time points. The dynamic behavior of functional data is decomposed into a time-dependent population average, baseline (or static) subject-specific variability, longitudinal (or dynamic) subject-specific variability, subject-visit-specific variability and measurement error. The model can be viewed as the functional analog of the classical longitudinal mixed effects model where random effects are replaced by random processes. Methods have wide applicability and are computationally feasible for moderate and large data sets. Computational feasibility is assured by using principal component bases for the functional processes. The methodology is motivated by and applied to a diffusion tensor imaging (DTI) study designed to analyze differences and changes in brain connectivity in healthy volunteers and multiple sclerosis (MS) patients. An R implementation is provided.87.

[1]  Martin Styner,et al.  FRATS: Functional Regression Analysis of DTI Tract Statistics , 2010, IEEE Transactions on Medical Imaging.

[2]  Kari Karhunen,et al.  Über lineare Methoden in der Wahrscheinlichkeitsrechnung , 1947 .

[3]  T. Ptak,et al.  Investigation of apparent diffusion coefficient and diffusion tensor anisotrophy in acute and chronic multiple sclerosis lesions. , 1999, AJNR. American journal of neuroradiology.

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

[5]  D. Ruppert,et al.  Likelihood ratio tests in linear mixed models with one variance component , 2003 .

[6]  Peter A. Calabresi,et al.  Multiparametric magnetic resonance imaging analysis of the corticospinal tract in multiple sclerosis , 2007, NeuroImage.

[7]  Joan G. Staniswalis,et al.  Nonparametric Regression Analysis of Longitudinal Data , 1998 .

[8]  P. V. van Zijl,et al.  Three‐dimensional tracking of axonal projections in the brain by magnetic resonance imaging , 1999, Annals of neurology.

[9]  P. Calabresi,et al.  MRI of the corpus callosum in multiple sclerosis: association with disability , 2010, Multiple sclerosis.

[10]  S. F. Witelson.  Hand and sex differences in the isthmus and genu of the human corpus callosum. A postmortem morphological study. , 1989, Brain : a journal of neurology.

[11]  B. Silverman,et al.  Functional Data Analysis , 1997 .

[12]  John A. Rice,et al.  FUNCTIONAL AND LONGITUDINAL DATA ANALYSIS: PERSPECTIVES ON SMOOTHING , 2004 .

[13]  Wensheng Guo.  Functional Mixed Effects Models , 2002 .

[14]  Brian S. Caffo,et al.  Multilevel functional principal component analysis , 2009 .

[15]  C. Crainiceanu,et al.  Restricted Likelihood Ratio Testing for Zero Variance Components in Linear Mixed Models , 2008 .

[16]  R. Carroll,et al.  Nonparametric Function Estimation for Clustered Data When the Predictor is Measured without/with Error , 2000 .

[17]  G. Barker,et al.  Diffusion tensor imaging of lesions and normal-appearing white matter in multiple sclerosis , 1999, Neurology.

[18]  H. Müller,et al.  Shrinkage Estimation for Functional Principal Component Scores with Application to the Population Kinetics of Plasma Folate , 2003, Biometrics.

[19]  J. Ware,et al.  Random-effects models for longitudinal data. , 1982, Biometrics.

[20]  H. Müller,et al.  Modelling sparse generalized longitudinal observations with latent Gaussian processes , 2008 .

[21]  B. Silverman,et al.  Nonparametric Regression and Generalized Linear Models: A roughness penalty approach , 1993 .

[22]  Peter A. Calabresi,et al.  419 – Multiple Sclerosis and Demyelinating Conditions of the Central Nervous System , 2011 .

[23]  Ying Zhang,et al.  Time‐Varying Functional Regression for Predicting Remaining Lifetime Distributions from Longitudinal Trajectories , 2005, Biometrics.

[24]  S. Wood.  Generalized Additive Models: An Introduction with R , 2006 .

[25]  P. Vieu,et al.  Nonparametric Functional Data Analysis: Theory and Practice (Springer Series in Statistics) , 2006 .

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

[27]  HighWire Press.  Philosophical Transactions of the Royal Society of London , 1781, The London Medical Journal.

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

[29]  Calyampudi R. Rao,et al.  The theory of least squares when the parameters are stochastic and its application to the analysis of growth curves. , 1965, Biometrika.

[30]  J. Rice,et al.  Smoothing spline models for the analysis of nested and crossed samples of curves , 1998 .

[31]  P. Basser,et al.  MR diffusion tensor spectroscopy and imaging. , 1994, Biophysical journal.

[32]  F. Vaida,et al.  Conditional Akaike information for mixed-effects models , 2005 .

[33]  S. Greven,et al.  On the behaviour of marginal and conditional AIC in linear mixed models , 2010 .

[34]  S. Greven,et al.  On the Behavior of Marginal and Conditional Akaike Information Criteria in Linear Mixed Models , 2009 .

[35]  P. Diggle,et al.  Analysis of Longitudinal Data , 2003 .

[36]  Hong Sun,et al.  Quantitative analysis along the pyramidal tract by length-normalized parameterization based on diffusion tensor tractography: Application to patients with relapsing neuromyelitis optica , 2006, NeuroImage.

[37]  H. Müller.  Functional Modelling and Classification of Longitudinal Data * , 2005 .

[38]  P. Basser,et al.  Microstructural and physiological features of tissues elucidated by quantitative-diffusion-tensor MRI. 1996. , 1996, Journal of magnetic resonance.

[39]  Wensheng Guo.  Functional data analysis in longitudinal settings using smoothing splines , 2004, Statistical methods in medical research.

[40]  Ciprian M. Crainiceanu,et al.  Nonparametric Regression Methods for Longitudinal Data Analysis. Mixed-effects Modeling Approaches , 2007 .

[41]  Jeffrey S. Morris,et al.  Wavelet-based functional mixed model analysis: Computational considerations , 2006 .

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

[43]  F. Yao,et al.  Penalized spline models for functional principal component analysis , 2006 .

[44]  In Chan Song,et al.  Tractography-guided statistics (TGIS) in diffusion tensor imaging for the detection of gender difference of fiber integrity in the midsagittal and parasagittal corpora callosa , 2007, NeuroImage.

[45]  Hua Liang,et al.  A Note on Conditional AIC for Linear Mixed-Effects Models. , 2008, Biometrika.

[46]  Paul H. C. Eilers,et al.  3D space-varying coefficient models with application to diffusion tensor imaging , 2007, Comput. Stat. Data Anal..

[47]  Ana-Maria Staicu,et al.  Fast methods for spatially correlated multilevel functional data. , 2010, Biostatistics.

[48]  Jeffrey S. Morris,et al.  Wavelet‐based functional mixed models , 2006, Journal of the Royal Statistical Society. Series B, Statistical methodology.

[49]  G. Molenberghs,et al.  Linear Mixed Models for Longitudinal Data , 2001 .

[50]  G. Kauermann,et al.  A Note on Penalized Spline Smoothing With Correlated Errors , 2007 .

[51]  J. Mercer.  Functions of Positive and Negative Type, and their Connection with the Theory of Integral Equations , 1909 .

[52]  Ana-Maria Staicu,et al.  Generalized Multilevel Functional Regression , 2009, Journal of the American Statistical Association.