Functional Data Analysis of Amplitude and Phase Variation
Open accessThe DOI matches its Crossref record; 31 of the 31 references it cites were found in a registry or an index.
Abstract
The abundance of functional observations in scientific endeavors has led to a significant development in tools for functional data analysis (FDA). This kind of data comes with several challenges: infinite-dimensionality of function spaces, observation noise, and so on. However, there is another interesting phenomena that creates problems in FDA. The functional data often comes with lateral displacements/deformations in curves, a phenomenon which is different from the height or amplitude variability and is termed phase variation. The presence of phase variability artificially often inflates data variance, blurs underlying data structures, and distorts principal components. While the separation and/or removal of phase from amplitude data is desirable, this is a difficult problem. In particular, a commonly used alignment procedure, based on minimizing the $\mathbb{L}^{2}$ norm between functions, does not provide satisfactory results. In this paper we motivate the importance of dealing with the phase variability and summarize several current ideas for separating phase and amplitude components. These approaches differ in the following: (1) the definition and mathematical representation of phase variability, (2) the objective functions that are used in functional data alignment, and (3) the algorithmic tools for solving estimation/optimization problems. We use simple examples to illustrate various approaches and to provide useful contrast between them.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Dynamic Programming Algorithm Optimization for Spoken Word Recognition
Sakoe, H., & Chiba, S. (1978) · IEEE Transactions on Acoustics Speech and Signal Processing · doi:10.1109/tassp.1978.1163055 · Cited by 6,727 · cited 5×
“Sakoe and Chiba (1978) devised an insertion/deletion algorithm that is rather like that of isotonic regression (Barlow et al., 1972).”
BackgroundMethodInfluentialRamsay, J. O., & Silverman, B. W. (2005) · Springer Series in Statistics · doi:10.1007/b98888 · Cited by 3,652
Self-citationStatistical shape analysis: clustering, learning, and testing
Srivastava, A., Joshi, S. H., Mio, W., & Liu, X. (2005) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2005.86 · Cited by 2,727
Self-citationDeformable medical image registration: a survey
Sotiras, A., Davatzikos, C., & Paragios, N. (2013) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2013.2265603 · Cited by 1,587
Statistical Inference Under Order Restrictions
Kalbfleisch, J. D. (1975) · Technometrics · doi:10.1080/00401706.1975.10489288 · Cited by 1,546 · cited 1×
“Sakoe and Chiba (1978) devised an insertion/deletion algorithm that is rather like that of isotonic regression (Barlow et al., 1972).”
Srivastava, A., Kurtek, S., & Klassen, E. (2014) · Computer Vision · doi:10.1007/978-0-387-31439-6_778 · Cited by 848 · cited 4×
“In fact, they form the core idea in statistical shape analysis (Dryden and Mardia, 1998) and in Grenander’s work on pattern theory (Grenander, 1993), including its applications to computational anatomy (Grenander and Miller, 1998). In Kendall’s shape analysis the experimental units are configurations of (landmark) poi…”
BackgroundInfluentialSelf-citationStatistical Inference under Order Restrictions (The Theory and Application of Isotonic Regression)
Vincze, I., Barlow, R. E., Bartholomew, D. J., Bremner, J. M., & Brunk, H. D. (1973) · International Statistical Review / Revue Internationale de Statistique · doi:10.2307/1402630 · Cited by 842 · cited 1×
“tonic regression (Barlow et al. (1972)).”
Shape Analysis of Elastic Curves in Euclidean Spaces
Srivastava, A., Klassen, E., Joshi, S. H., & Jermyn, I. H. (2011) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2010.184 · Cited by 638 · cited 5×
“son for introducing SRVF is that the Fisher–Rao distance between any two functions is given by the L2 distance between their SRVFs, that is, (9) dFR(x1,x2)=kSRVF(x1)−SRVF(x2)k. We refer the reader to Srivastava et al. (2011a) for the details, but mention in passing that the proof hinges on the fact that SRVF(x◦h) =(q◦…”
BackgroundInfluentialSelf-citationComputational anatomy: an emerging discipline
Grenander, U., & Miller, M. I. (1998) · Quarterly of Applied Mathematics · doi:10.1090/qam/1668732 · Cited by 623 · cited 1×
“In fact, they form the core idea in statistical shape analysis (Dryden and Mardia, 1998) and in Grenander’s work on pattern theory (Grenander, 1993), including its applications to computational anatomy (Grenander and Miller, 1998).”
BackgroundGeneral Pattern Theory: A Mathematical Study of Regular Structures
Grenander, U. (1994) · doi:10.1093/oso/9780198536710.001.0001 · Cited by 287
Registration of Functional Data Using Fisher-Rao MetricPreprint
Srivastava, A., Wu, W. L., Kurtek, S., Klassen, E., & Marron, J. S. (2011) · arXiv (Cornell University) · doi:10.48550/arxiv.1103.3817 · Cited by 268
Self-citationPhysical growth of California boys and girls from birth to eighteen years.
Tuddenham, R. D., & Snyder, M. M. (1954) · PubMed · Cited by 199
Analysis of principal nested spheres
Jung, S., Dryden, I. L., & Marron, J. S. (2012) · Biometrika · doi:10.1093/biomet/ass022 · Cited by 191
Self-citationRiemannian Analysis of Probability Density Functions with Applications in Vision
Srivastava, A., Jermyn, I. H., & Joshi, S. (2007) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2007.383188 · Cited by 184 · cited 3×
“Srivastava et al. (2011b) used the nonparametric form of the Fisher-Rao metric (see Srivastava et al.”
BackgroundMethodInfluentialSelf-citationGenerative models for functional data using phase and amplitude separation
Tucker, J. D., Wu, W., & Srivastava, A. (2013) · Computational Statistics & Data Analysis · doi:10.1016/j.csda.2012.12.001 · Cited by 178
Self-citationOverview of object oriented data analysis
Marron, J. S., & Alonso, A. M. (2014) · Biometrical Journal · doi:10.1002/bimj.201300072 · Cited by 178 · cited 2×
“While the origins of these ideas lie in shape theory, an understanding of these concepts can also be obtained using the terminology of object-oriented data analysis (OODA), as defined in Wang and Marron (2007) and more recently discussed in Marron and Alonso (2014).”
MethodSelf-citationObject oriented data analysis: Sets of trees
Wang, H., & Marron, J. S. (2007) · The Annals of Statistics · doi:10.1214/009053607000000217 · Cited by 168 · cited 1×
“While the origins of these ideas lie in shape theory, an understanding of these concepts can also be obtained using the terminology of object-oriented data analysis (OODA), as defined in Wang and Marron (2007) and more recently discussed in Marron and Alonso (2014).”
MethodSelf-citationSelf-Modelling Warping Functions
Gervini, D., & Gasser, T. (2004) · Journal of the Royal Statistical Society Series B (Statistical Methodology) · doi:10.1111/j.1467-9868.2004.b5582.x · Cited by 134 · cited 2×
“Another set of papers (Tang and Müller, 2008, Liu and Müller, 2004, Gervini and Gasser, 2004) takes the approach where some data points serve as templates for others, and the individual warping functions are averaged to find ultimate warpings.”
BackgroundMethodPairwise curve synchronization for functional data
Tang, R., & Muller, H.-G. (2008) · Biometrika · doi:10.1093/biomet/asn047 · Cited by 133 · cited 1×
“Another set of papers (Tang and Müller, 2008, Liu and Müller, 2004, Gervini and Gasser, 2004) takes the approach where some data points serve as templates for others, and the individual warping functions are averaged to find ultimate warpings.”
BackgroundSangalli, L. M., Secchi, P., Vantini, S., & Veneziani, A. (2009) · Journal of the American Statistical Association · doi:10.1198/jasa.2009.0002 · Cited by 127 · cited 1×
“For example, Sangalli et al. (2009, 2010) and Vantini (2012) study this invariance and then specify it in the context of linear or affine transformations of the domain, while Srivastava et al. (2011a) study it for diffeomorphisms.”
BackgroundSelf-citationFunctional Convex Averaging and Synchronization for Time-Warped Random Curves
Liu, X., & Müller, H. (2004) · Journal of the American Statistical Association · doi:10.1198/016214504000000999 · Cited by 122 · cited 2×
“Other proposals in this context are given by Tang and Müller (2009), Liu and Yang (2009), Boudaoud, Rix and Meste (2010). Another set of papers (Tang and Müller (2008), Liu and Müller (2004), Gervini and Gasser (2004)) takes the approach where some data points serve as templates for others, and the individual warping…”
BackgroundCombining Registration and Fitting for Functional Models
Kneip, A., & Ramsay, J. O. (2008) · Journal of the American Statistical Association · doi:10.1198/016214508000000517 · Cited by 119 · cited 2×
“This model, taken from Kneip and Ramsay (2008), can also be derived from a later equation [equation (11)] by setting the function W(t) = βt .”
MethodSelf-citationRate-Invariant Recognition of Humans and Their Activities
Veeraraghavan, A., Srivastava, A., Roy–Chowdhury, A. K., & Chellappa, R. (2009) · IEEE Transactions on Image Processing · doi:10.1109/tip.2009.2017143 · Cited by 106 · cited 2×
“While the origins of these ideas lie in shape theory, an understanding of these concepts can also be obtained using the terminology of object-oriented data analysis (OODA), as defined in Wang and Marron (2007) and more recently discussed in Marron and Alonso (2014).”
MethodSelf-citationSimultaneous curve registration and clustering for functional data
Liu, X., & Yang, M. C. K. (2008) · Computational Statistics & Data Analysis · doi:10.1016/j.csda.2008.11.019 · Cited by 105 · cited 4×
“Other proposals in this context are given by Tang and Müller (2009), Liu and Yang (2009), Boudaoud, Rix and Meste (2010). Another set of papers (Tang and Müller (2008), Liu and Müller (2004), Gervini and Gasser (2004)) takes the approach where some data points serve as templates for others, and the individual warping…”
BackgroundMethodInfluentialLavine, B. K., & Workman, J. (2012) · Analytical Chemistry · doi:10.1021/ac303193j · Cited by 104
Hadjipantelis, P. Z., Aston, J. A. D., Müller, H. G., & Evans, J. P. (2015) · Journal of the American Statistical Association · doi:10.1080/01621459.2015.1006729 · Cited by 46 · cited 1×
“For instance, Hadjipantelis et al. (2015, 2014) study the problem of regression using phase and amplitude components of the given functions.”
Time-synchronized clustering of gene expression trajectories
Tang, R., & Muller, H.-G. (2008) · Biostatistics · doi:10.1093/biostatistics/kxn011 · Cited by 40
On the definition of phase and amplitude variability in functional data analysis
Vantini, S. (2011) · Test · doi:10.1007/s11749-011-0268-9 · Cited by 39 · cited 3×
“The spherical geometry of this space of ψ functions has been used to perform estimation and alignment of curves in several places, including Veeraraghavan et al. (2009). This geometry has also been helpful in developing PCA of warping functions (Tucker et al.”
BackgroundMethodCore Shape modelling of a set of curves
Boudaoud, S., Rix, H., & Meste, O. (2009) · Computational Statistics & Data Analysis · doi:10.1016/j.csda.2009.08.003 · Cited by 22 · cited 2×
“Other proposals in this context are given by Tang and Muller (2009), Liu and Yang (2009), Boudaoud et al. (2010). Another set of papers (Tang and Muller (2008); Liu and Muller (2004); Gervini and Gasser (2004)) take the approach where some data points serve as templates for others, and the individual warping functions…”
BackgroundMethodPrincipal Nested Spheres for Time-Warped Functional Data Analysis
Yu, Q., Lu, X., & Marron, J. S. (2015) · Journal of Computational and Graphical Statistics · doi:10.1080/10618600.2015.1115359 · Cited by 21
Self-citationAnalysis of spike train data: A multivariate mixed effects model for phase and amplitude
Hadjipantelis, P. Z., Aston, J. A. D., Müller, H., & Moriarty, J. (2014) · Electronic Journal of Statistics · doi:10.1214/14-ejs865e · Cited by 12 · cited 1×
“For instance, Hadjipantelis et al. (2015, 2014) study the problem of regression using phase and amplitude components of the given functions.”
Cited by
Statistical Aspects of Wasserstein Distances
Panaretos, V. M., & Zemel, Y. (2019) · Annual Review of Statistics and Its Application · doi:10.1146/annurev-statistics-030718-104938 · Cited by 857
Williams, A. H., Poole, B., Maheswaranathan, N., Dhawale, A. K., Fisher, T., Wilson, C. D., Brann, D. H., Trautmann, E. M., Ryu, S., Shusterman, R., et al. (2020) · Neuron · doi:10.1016/j.neuron.2019.10.020 · Cited by 102
Metadata
- Authors
- Marron, J. S., Ramsay, J. O., Sangalli, L. M., & Srivastava, A.
- Venue
- Statistical Science
- Publisher
- Institute of Mathematical Statistics
- Published
- 2015-11-01
- Volume
- 30
- Issue
- 4
- Pages
- 468-484
- ISSN
- 0883-4237 (ISSN-L)
- OpenAlex
- W2191641151
- Cited by
- 174
- References
- 31
- FWCI
- 9.64
- Type
- journal article
- Language
- en
- Open access
- bronze
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.