Size and shape analysis of error-prone shape data

We consider the problem of comparing sizes and shapes of objects when landmark data are prone to measurement error. We show that naive implementation of ordinary Procrustes analysis that ignores measurement error can compromise inference. To account for measurement error, we propose the conditional...

Full description

Bibliographic Details
Main Authors: Du, J., Dryden, Ian L., Huang, X.
Format: Article
Published: Taylor & Francis 2015
Subjects:
Online Access:https://eprints.nottingham.ac.uk/41096/
_version_ 1848796195211706368
author Du, J.
Dryden, Ian L.
Huang, X.
author_facet Du, J.
Dryden, Ian L.
Huang, X.
author_sort Du, J.
building Nottingham Research Data Repository
collection Online Access
description We consider the problem of comparing sizes and shapes of objects when landmark data are prone to measurement error. We show that naive implementation of ordinary Procrustes analysis that ignores measurement error can compromise inference. To account for measurement error, we propose the conditional score method for matching configurations, which guarantees consistent inference under mild model assumptions. The effects of measurement error on inference from naive Procrustes analysis and the performance of the proposed method are illustrated via simulation and application in three real data examples. Supplementary materials for this article are available online.
first_indexed 2025-11-14T19:44:07Z
format Article
id nottingham-41096
institution University of Nottingham Malaysia Campus
institution_category Local University
last_indexed 2025-11-14T19:44:07Z
publishDate 2015
publisher Taylor & Francis
recordtype eprints
repository_type Digital Repository
spelling nottingham-410962020-05-04T20:09:31Z https://eprints.nottingham.ac.uk/41096/ Size and shape analysis of error-prone shape data Du, J. Dryden, Ian L. Huang, X. We consider the problem of comparing sizes and shapes of objects when landmark data are prone to measurement error. We show that naive implementation of ordinary Procrustes analysis that ignores measurement error can compromise inference. To account for measurement error, we propose the conditional score method for matching configurations, which guarantees consistent inference under mild model assumptions. The effects of measurement error on inference from naive Procrustes analysis and the performance of the proposed method are illustrated via simulation and application in three real data examples. Supplementary materials for this article are available online. Taylor & Francis 2015-03 Article PeerReviewed Du, J., Dryden, Ian L. and Huang, X. (2015) Size and shape analysis of error-prone shape data. Journal of the American Statistical Association, 110 (509). pp. 368-377. ISSN 1537-274X Complex normal; Configuration; Landmark; Ordinary Procrustes analysis; Quaternion http://www.tandfonline.com/doi/full/10.1080/01621459.2014.908779 doi:10.1080/01621459.2014.908779 doi:10.1080/01621459.2014.908779
spellingShingle Complex normal; Configuration; Landmark; Ordinary Procrustes analysis; Quaternion
Du, J.
Dryden, Ian L.
Huang, X.
Size and shape analysis of error-prone shape data
title Size and shape analysis of error-prone shape data
title_full Size and shape analysis of error-prone shape data
title_fullStr Size and shape analysis of error-prone shape data
title_full_unstemmed Size and shape analysis of error-prone shape data
title_short Size and shape analysis of error-prone shape data
title_sort size and shape analysis of error-prone shape data
topic Complex normal; Configuration; Landmark; Ordinary Procrustes analysis; Quaternion
url https://eprints.nottingham.ac.uk/41096/
https://eprints.nottingham.ac.uk/41096/
https://eprints.nottingham.ac.uk/41096/