Get 20M+ Full-Text Papers For Less Than $1.50/day. Subscribe now for You or Your Team.

Learn More →

Discussion on the paper by Peter Müller, Fernando A. Quintana, and Garritt L. Page

Discussion on the paper by Peter Müller, Fernando A. Quintana, and Garritt L. Page The article by Müller, Quintana, and Page reviews a variety of Bayesian nonparametric models and demonstrates them in a few applications. They emphasize applications in spatial data on which our discussion focuses as well. In particular, we consider two types of mixture models based on species sampling models (SSM) for spatial clustering and apply them to the Chilean mathematics testing score data analyzed by the authors. We conclude that only the mixture model of SSM with spatial locations as part of observations renders spatially non-overlapping clusters. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Statistical Methods & Applications Springer Journals

Discussion on the paper by Peter Müller, Fernando A. Quintana, and Garritt L. Page

Loading next page...
 
/lp/springer_journal/discussion-on-the-paper-by-peter-m-ller-fernando-a-quintana-and-P3YLNZNYO8

References (8)

Publisher
Springer Journals
Copyright
Copyright © 2017 by Springer-Verlag GmbH Germany
Subject
Statistics; Statistics, general; Statistical Theory and Methods; Statistics for Business/Economics/Mathematical Finance/Insurance; Statistics for Engineering, Physics, Computer Science, Chemistry and Earth Sciences; Statistics for Life Sciences, Medicine, Health Sciences; Statistics for Social Science, Behavorial Science, Education, Public Policy, and Law
ISSN
1618-2510
eISSN
1613-981X
DOI
10.1007/s10260-017-0396-9
Publisher site
See Article on Publisher Site

Abstract

The article by Müller, Quintana, and Page reviews a variety of Bayesian nonparametric models and demonstrates them in a few applications. They emphasize applications in spatial data on which our discussion focuses as well. In particular, we consider two types of mixture models based on species sampling models (SSM) for spatial clustering and apply them to the Chilean mathematics testing score data analyzed by the authors. We conclude that only the mixture model of SSM with spatial locations as part of observations renders spatially non-overlapping clusters.

Journal

Statistical Methods & ApplicationsSpringer Journals

Published: Sep 9, 2017

There are no references for this article.