Remote Access Proceedings of the American Mathematical Society
Green Open Access

Proceedings of the American Mathematical Society

ISSN 1088-6826(online) ISSN 0002-9939(print)

 
 

 

Omnibus CLTs for Fréchet means and nonparametric inference on non-Euclidean spaces


Authors: Rabi Bhattacharya and Lizhen Lin
Journal: Proc. Amer. Math. Soc. 145 (2017), 413-428
MSC (2010): Primary 60F05, 62E20, 60E05, 62G20
DOI: https://doi.org/10.1090/proc/13216
Published electronically: July 26, 2016
MathSciNet review: 3565392
Full-text PDF

Abstract | References | Similar Articles | Additional Information

Abstract: Two central limit theorems for sample Fréchet means are derived, both significant for nonparametric inference on non-Euclidean spaces. The first theorem encompasses and improves upon most earlier CLTs on Fréchet means and broadens the scope of the methodology beyond manifolds to diverse new non-Euclidean data, including those on certain stratified spaces which are important in the study of phylogenetic trees. It does not require that the underlying distribution $ Q$ have a density and applies to both intrinsic and extrinsic analysis. The second theorem focuses on intrinsic means on Riemannian manifolds of dimensions $ d>2$ and breaks new ground by providing a broad CLT without any of the earlier restrictive support assumptions. It makes the statistically reasonable assumption of a somewhat smooth density of $ Q$. The excluded case of dimension $ d=2 $ proves to be an enigma, although the first theorem does provide a CLT in this case as well under a support restriction. The second theorem immediately applies to spheres $ S^d$, $ d>2$, which are also of considerable importance in applications to axial spaces and to landmarks-based image analysis, as these spaces are quotients of spheres under a Lie group $ \mathcal G $ of isometries of $ S^d$.


References [Enhancements On Off] (What's this?)

  • [1] Bijan Afsari, Riemannian $ L^p$ center of mass: existence, uniqueness, and convexity, Proc. Amer. Math. Soc. 139 (2011), no. 2, 655-673. MR 2736346, https://doi.org/10.1090/S0002-9939-2010-10541-5
  • [2] A. Arsigny, P. Fillard, X. Pennec, and N. Ayache, Log-Euclidean metrics for fast and simple calculus on diffusion tensors, Magn. Reson. Med. 56 (2006), no. 2, 411-421.
  • [3] Ananda Bandulasiri, Rabi N. Bhattacharya, and Vic Patrangenaru, Nonparametric inference for extrinsic means on size-and-(reflection)-shape manifolds with applications in medical imaging, J. Multivariate Anal. 100 (2009), no. 9, 1867-1882. MR 2543073, https://doi.org/10.1016/j.jmva.2009.03.007
  • [4] A. Bandulasiri and V. Patrangenaru, Algorithms for nonparametric inference on shape manifolds, Proc. of JSM 2005, MN (2005), 1617-1622.
  • [5] Dennis Barden, Huiling Le, and Megan Owen, Central limit theorems for Fréchet means in the space of phylogenetic trees, Electron. J. Probab. 18 (2013), no. 25, 25. MR 3035753, https://doi.org/10.1214/EJP.v18-2201
  • [6] Bojan Basrak, Limit theorems for the inductive mean on metric trees, J. Appl. Probab. 47 (2010), no. 4, 1136-1149. MR 2752884
  • [7] Yoav Benjamini and Yosef Hochberg, Controlling the false discovery rate: a practical and powerful approach to multiple testing, J. Roy. Statist. Soc. Ser. B 57 (1995), no. 1, 289-300. MR 1325392
  • [8] Abhishek Bhattacharya, Statistical analysis on manifolds: a nonparametric approach for inference on shape spaces, Sankhyā 70 (2008), no. 2, Ser. A, 223-266. MR 2551814
  • [9] A. Bhattacharya and R. N. Bhattacharya, Statistics on Riemannian manifolds: asymptotic distribution and curvature, Proc. Amer. Math. Soc. 136 (2008), 2957-2967.
  • [10] Abhishek Bhattacharya and Rabi Bhattacharya, Nonparametric inference on manifolds, With applications to shape spaces, Institute of Mathematical Statistics (IMS) Monographs, vol. 2, Cambridge University Press, Cambridge, 2012. MR 2934285
  • [11] R. Bhattacharya and L. Lin, A central limit theorem for Fréchet means, arXiv1306.5806 (2013).
  • [12] R. N. Bhattacharya, Smoothness and convexity of the Fréchet function on a Riemannian manifold, uniqueness of the intrinsic mean, and nonsingularity of the asymptotic dispersion of the sample Fréchet mean, unpublished manuscipt (2007).
  • [13] Rabi N. Bhattacharya, Marius Buibaş, Ian L. Dryden, Leif A. Ellingson, David Groisser, Harrie Hendriks, Stephan Huckemann, Huiling Le, Xiuwen Liu, James S. Marron, Daniel E. Osborne, Vic Pătrângenaru, Armin Schwartzman, Hilary W. Thompson, and Andrew T. A. Wood, Extrinsic data analysis on sample spaces with a manifold stratification, Advances in mathematics, Ed. Acad. Române, Bucharest, 2013, pp. 241-251. MR 3203429
  • [14] Rabi Bhattacharya and Vic Patrangenaru, Large sample theory of intrinsic and extrinsic sample means on manifolds. I, Ann. Statist. 31 (2003), no. 1, 1-29. MR 1962498, https://doi.org/10.1214/aos/1046294456
  • [15] Rabi Bhattacharya and Vic Patrangenaru, Large sample theory of intrinsic and extrinsic sample means on manifolds. II, Ann. Statist. 33 (2005), no. 3, 1225-1259. MR 2195634, https://doi.org/10.1214/009053605000000093
  • [16] Louis J. Billera, Susan P. Holmes, and Karen Vogtmann, Geometry of the space of phylogenetic trees, Adv. in Appl. Math. 27 (2001), no. 4, 733-767. MR 1867931, https://doi.org/10.1006/aama.2001.0759
  • [17] Manfredo Perdigão do Carmo, Riemannian geometry, translated from the second Portuguese edition by Francis Flaherty, Mathematics: Theory & Applications, Birkhäuser Boston, Inc., Boston, MA, 1992. MR 1138207
  • [18] Ian L. Dryden, Alexey Koloydenko, and Diwei Zhou, Non-Euclidean statistics for covariance matrices, with applications to diffusion tensor imaging, Ann. Appl. Stat. 3 (2009), no. 3, 1102-1123. MR 2750388, https://doi.org/10.1214/09-AOAS249
  • [19] Ian L. Dryden, Alfred Kume, Huiling Le, and Andrew T. A. Wood, A multi-dimensional scaling approach to shape analysis, Biometrika 95 (2008), no. 4, 779-798. MR 2461211, https://doi.org/10.1093/biomet/asn050
  • [20] Leif Ellingson, Vic Patrangenaru, and Frits Ruymgaart, Nonparametric estimation of means on Hilbert manifolds and extrinsic analysis of mean shapes of contours, J. Multivariate Anal. 122 (2013), 317-333. MR 3189326, https://doi.org/10.1016/j.jmva.2013.08.010
  • [21] J. Felsenstein, Evolutionary trees from dna sequences: A maximum likelihood approach, Journal of Molecular Evolution 17, no. 6, 368-376.
  • [22] Maurice Fréchet, Les éléments aléatoires de nature quelconque dans un espace distancié, Ann. Inst. H. Poincaré 10 (1948), 215-310 (French). MR 0027464
  • [23] Sylvestre Gallot, Dominique Hulin, and Jacques Lafontaine, Riemannian geometry, 2nd ed., Universitext, Springer-Verlag, Berlin, 1990. MR 1083149
  • [24] S. Holmes, Statistical approach to tests involving phylogenetics, in Mathematics of Evolution and Phylogeny (Gascuel, O., editor), OUP, Oxford, 2005.
  • [25] T. Hotz and S. Huckemann, Intrinsic means on the circle: uniqueness, locus and asymptotics, Ann. Inst. Statist. Math. 67 (2015), no. 1, 177-193. MR 3297863, https://doi.org/10.1007/s10463-013-0444-7
  • [26] Thomas Hotz, Stephan Huckemann, Huiling Le, J. S. Marron, Jonathan C. Mattingly, Ezra Miller, James Nolen, Megan Owen, Vic Patrangenaru, and Sean Skwerer, Sticky central limit theorems on open books, Ann. Appl. Probab. 23 (2013), no. 6, 2238-2258. MR 3127934, https://doi.org/10.1214/12-AAP899
  • [27] C. Huang, M. Styner, and H. T. Zhu, Penalized mixtures of offset-normal shape factor analyzers with application in clustering high-dimensional shape data, J. Amer. Statist. Assoc., to appear (2015).
  • [28] Stephan Huckemann, Jonathan C. Mattingly, Ezra Miller, and James Nolen, Sticky central limit theorems at isolated hyperbolic planar singularities, Electron. J. Probab. 20 (2015), no. 78, 34. MR 3371437
  • [29] Sungkyu Jung, Armin Schwartzman, and David Groisser, Scaling-rotation distance and interpolation of symmetric positive-definite matrices, SIAM J. Matrix Anal. Appl. 36 (2015), no. 3, 1180-1201. MR 3379023, https://doi.org/10.1137/140967040
  • [30] H. Karcher, Riemannian center of mass and mollifier smoothing, Comm. Pure Appl. Math. 30 (1977), no. 5, 509-541. MR 0442975
  • [31] Wilfrid S. Kendall, Probability, convexity, and harmonic maps with small image. I. Uniqueness and fine existence, Proc. London Math. Soc. (3) 61 (1990), no. 2, 371-406. MR 1063050, https://doi.org/10.1112/plms/s3-61.2.371
  • [32] Wilfrid S. Kendall and Huiling Le, Limit theorems for empirical Fréchet means of independent and non-identically distributed manifold-valued random variables, Braz. J. Probab. Stat. 25 (2011), no. 3, 323-352. MR 2832889, https://doi.org/10.1214/11-BJPS141
  • [33] Christophe Lenglet, Mikaël Rousson, Rachid Deriche, and Olivier Faugeras, Statistics on the manifold of multivariate normal distributions: theory and application to diffusion tensor MRI processing, J. Math. Imaging Vision 25 (2006), no. 3, 423-444. MR 2283616, https://doi.org/10.1007/s10851-006-6897-z
  • [34] Robby G. McKilliam, Barry G. Quinn, and I. Vaughan L. Clarkson, Direction estimation by minimum squared arc length, IEEE Trans. Signal Process. 60 (2012), no. 5, 2115-2124. MR 2954196, https://doi.org/10.1109/TSP.2012.2186444
  • [35] John W. Milnor, Topology from the differentiable viewpoint, based on notes by David W. Weaver. Princeton Landmarks in Mathematics, Princeton University Press, Princeton, NJ, 1997. Revised reprint of the 1965 original. MR 1487640
  • [36] Daniel Osborne, Vic Patrangenaru, Leif Ellingson, David Groisser, and Armin Schwartzman, Nonparametric two-sample tests on homogeneous Riemannian manifolds, Cholesky decompositions and diffusion tensor image analysis, J. Multivariate Anal. 119 (2013), 163-175. MR 3061421, https://doi.org/10.1016/j.jmva.2013.04.006
  • [37] D. Osborne, V. Patrangenaru, M. Qiu, and H. W. Thompson, Nonparametric data analysis methods in medical imaging, John Wiley & Sons, Ltd, 2015, pp. 182-205.
  • [38] V. Patrangenaru and L. Ellingson, Nonparametric statistics on manifolds and their applications, Texts in Statistical Science, Chapman & Hall/CRC, 2015.
  • [39] J. R. Ramsay, Current status of cognitive-behavioral therapy as a psychosocial treatment for adult attention-deficit/hyperactivity disorder, Curr Psychiatry Rep. 9(5) (2007), 427-433.
  • [40] A. Schwartzman, Lognormal distributions and geometric averages of positive definite matrices, arXiv e-prints (2014).
  • [41] Karl-Theodor Sturm, Probability measures on metric spaces of nonpositive curvature, Heat kernels and analysis on manifolds, graphs, and metric spaces (Paris, 2002) Contemp. Math., vol. 338, Amer. Math. Soc., Providence, RI, 2003, pp. 357-390. MR 2039961, https://doi.org/10.1090/conm/338/06080
  • [42] Bengt von Bahr, On the central limit theorem in $ R_{k}$, Ark. Mat. 7 (1967), 61-69 (1967). MR 0224128
  • [43] Ying Yuan, Hongtu Zhu, Weili Lin, and J. S. Marron, Local polynomial regression for symmetric positive definite matrices, J. R. Stat. Soc. Ser. B. Stat. Methodol. 74 (2012), no. 4, 697-719. MR 2965956, https://doi.org/10.1111/j.1467-9868.2011.01022.x
  • [44] Herbert Ziezold, On expected figures and a strong law of large numbers for random elements in quasi-metric spaces, Transactions of the Seventh Prague Conference on Information Theory, Statistical Decision Functions, Random Processes and of the Eighth European Meeting of Statisticians (Tech. Univ. Prague, Prague, 1974) Reidel, Dordrecht, 1977, pp. 591-602. MR 0501230

Similar Articles

Retrieve articles in Proceedings of the American Mathematical Society with MSC (2010): 60F05, 62E20, 60E05, 62G20

Retrieve articles in all journals with MSC (2010): 60F05, 62E20, 60E05, 62G20


Additional Information

Rabi Bhattacharya
Affiliation: Department of Mathematics, The University of Arizona, Tucson, Arizona 85721
Email: rabi@math.arizona.edu

Lizhen Lin
Affiliation: Department of Statistics and Data Sciences, The University of Texas at Austin, Austin, Texas 78712
Email: lizhen.lin@austin.utexas.edu

DOI: https://doi.org/10.1090/proc/13216
Keywords: Inference on manifolds, Fr\'echet means, Omnibus central limit theorem, stratified spaces
Received by editor(s): February 28, 2015
Received by editor(s) in revised form: November 12, 2015, and March 27, 2016
Published electronically: July 26, 2016
Communicated by: Mark M. Meerschaert
Article copyright: © Copyright 2016 American Mathematical Society

American Mathematical Society