Statistical analysis on high-dimensional spheres and shape spaces
Open Access
- 1 August 2005
- journal article
- Published by Institute of Mathematical Statistics in The Annals of Statistics
- Vol. 33 (4)
- https://doi.org/10.1214/009053605000000264
Abstract
We consider the statistical analysis of data on high-dimensional spheres and shape spaces. The work is of particular relevance to applications where high-dimensional data are available--a commonly encountered situation in many disciplines. First the uniform measure on the infinite-dimensional sphere is reviewed, together with connections with Wiener measure. We then discuss densities of Gaussian measures with respect to Wiener measure. Some nonuniform distributions on infinite-dimensional spheres and shape spaces are introduced, and special cases which have important practical consequences are considered. We focus on the high-dimensional real and complex Bingham, uniform, von Mises-Fisher, Fisher-Bingham and the real and complex Watson distributions. Asymptotic distributions in the cases where dimension and sample size are large are discussed. Approximations for practical maximum likelihood based inference are considered, and in particular we discuss an application to brain shape modeling.Comment: Published at http://dx.doi.org/10.1214/009053605000000264 in the Annals of Statistics (http://www.imstat.org/aos/) by the Institute of Mathematical Statistics (http://www.imstat.orgKeywords
This publication has 24 references indexed in Scilit:
- Saddlepoint approximations for the Bingham and Fisher–Bingham normalising constantsBiometrika, 2005
- The Complex Watson Distribution and Shape AnalysisJournal of the Royal Statistical Society Series B: Statistical Methodology, 1999
- Improved Pivotal Methods for Constructing Confidence Regions with Directional DataJournal of the American Statistical Association, 1996
- On conditional and intrinsic autoregressionsBiometrika, 1995
- The Wiener Sphere and Wiener MeasureThe Annals of Probability, 1993
- The Langevin distribution on high dimensional spheresJournal of Applied Statistics, 1988
- Limit theorems for uniform distributions on spheres in high-dimensional euclidean spacesJournal of Applied Probability, 1982
- Radon-Nikodym Derivatives of Gaussian MeasuresThe Annals of Mathematical Statistics, 1966
- An Asymptotic Expansion for the Distribution of the Latent Roots of the Estimated Covariance MatrixThe Annals of Mathematical Statistics, 1965
- The Distribution of the Latent Roots of the Covariance MatrixThe Annals of Mathematical Statistics, 1960