Regression of data represented as points on a hypersphere has traditionally been treated using parametric families of transformations that include the simple rigid rotation as an important, special case. On the other hand, nonparametric methods have generally focused on modelling a scalar response through a spherical predictor by representing the regression function as a polynomial, leading to component-wise estimation of a spherical response. We propose a very flexible, simple regression model where for each location of the manifold a specific rotation matrix is to be estimated. To make this approach tractable, we assume continuity of the regression function that, in turn, allows for approximations of rotation matrices based on a series expansion. It is seen that the non-rigidity of our technique motivates an iterative estimation within a Newton-Raphson learning scheme which exhibits bias reduction properties. Extensions to general shape matching are also outlined. Both simulations and real data are used to illustrate the results.

Nonparametric rotations for sphere-sphere regression / Di Marzio, M.; Panzera, A.; Taylor Charles, C.. - In: JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION. - ISSN 1537-274X. - STAMPA. - 114:(2019), pp. 466-476. [10.1080/01621459.2017.1421542]

Nonparametric rotations for sphere-sphere regression

Panzera A.;
2019

Abstract

Regression of data represented as points on a hypersphere has traditionally been treated using parametric families of transformations that include the simple rigid rotation as an important, special case. On the other hand, nonparametric methods have generally focused on modelling a scalar response through a spherical predictor by representing the regression function as a polynomial, leading to component-wise estimation of a spherical response. We propose a very flexible, simple regression model where for each location of the manifold a specific rotation matrix is to be estimated. To make this approach tractable, we assume continuity of the regression function that, in turn, allows for approximations of rotation matrices based on a series expansion. It is seen that the non-rigidity of our technique motivates an iterative estimation within a Newton-Raphson learning scheme which exhibits bias reduction properties. Extensions to general shape matching are also outlined. Both simulations and real data are used to illustrate the results.
2019
114
466
476
Di Marzio, M.; Panzera, A.; Taylor Charles, C.
File in questo prodotto:
File Dimensione Formato  
Nonparametric rotations for sphere.pdf

Accesso chiuso

Tipologia: Pdf editoriale (Version of record)
Licenza: Tutti i diritti riservati
Dimensione 1.1 MB
Formato Adobe PDF
1.1 MB Adobe PDF   Richiedi una copia

I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificatore per citare o creare un link a questa risorsa: https://hdl.handle.net/2158/1107255
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 9
  • ???jsp.display-item.citation.isi??? 7
social impact