Warping Functional Data in R and C via a Bayesian Multiresolution Approach

Phase variation in functional data obscures the true amplitude variation when a typical cross-sectional analysis of these responses would be performed. Time warping or curve registration aims at eliminating the phase variation, typically by applying transformations, the warping functions ?n, to the function arguments. We propose a warping method that jointly estimates a decomposition of the warping function in warping components, and amplitude components. For the estimation routine, adaptive MCMC calculations are performed and implemented in C rather than R to increase computational speed. The R-C interface makes the program user-friendly, in that no knowledge of C is required and all input and output will be handled through R. The R package MRwarping contains all needed files.

[1]  Henry W. Altland,et al.  Applied Functional Data Analysis , 2003, Technometrics.

[2]  Daniel Gervini,et al.  Nonparametric maximum likelihood estimation of the structural mean of a sample of curves , 2005 .

[3]  Sarah J E Barry,et al.  Linear mixed models for longitudinal shape data with applications to facial modeling. , 2008, Biostatistics.

[4]  Gareth M. James.  Curve alignment by moments , 2007, 0712.1425.

[5]  Bjarne Stroustrup,et al.  The C++ programming language (2nd ed.) , 1991 .

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

[7]  Brian W. Kernighan,et al.  The C Programming Language, Second Edition , 1988 .

[8]  Myriam Vimond,et al.  Efficient estimation for a subclass of shape invariant models , 2010, 1010.0796.

[9]  Brian J. Smith,et al.  boa: An R Package for MCMC Output Convergence Assessment and Posterior Inference , 2007 .

[10]  Gareth O. Roberts,et al.  Examples of Adaptive MCMC , 2009 .

[11]  B. Silverman,et al.  A multiresolution approach to time warping achieved by a Bayesian prior–posterior transfer fitting strategy , 2010 .

[12]  Jie Peng,et al.  Distance-based clustering of sparsely observed stochastic processes, with applications to online auctions , 2008, 0805.0463.

[13]  Bernard W. Silverman,et al.  Incorporating parametric effects into functional principal components analysis , 1995 .

[14]  Birgitte B. Rønn,et al.  Nonparametric maximum likelihood estimation for shifted curves , 2001 .

[15]  J'er'emie Bigot,et al.  A deconvolution approach to estimation of a common shape in a shifted curves model , 2008, 0812.3502.

[16]  T. Gasser,et al.  Alignment of curves by dynamic time warping , 1997 .

[17]  T. Gasser,et al.  Statistical Tools to Analyze Data Representing a Sample of Curves , 1992 .

[18]  S. Vantini.  On the definition of phase and amplitude variability in functional data analysis , 2009, TEST.

[19]  Ashish Sood,et al.  Functional Regression: A New Model for Predicting Market Penetration of New Products , 2009, Mark. Sci..

[20]  Radford M. Neal,et al.  Multiple Alignment of Continuous Time Series , 2004, NIPS.

[21]  T. Gasser,et al.  Self‐modelling warping functions , 2004 .

[22]  Brian W. Kernighan,et al.  The C Programming Language , 1978 .

[23]  A. Veneziani,et al.  A Case Study in Exploratory Functional Data Analysis: Geometrical Features of the Internal Carotid Artery , 2009 .