dc.contributor.author |
Wang, Yong |
en |
dc.date.accessioned |
2012-03-14T19:18:16Z |
en |
dc.date.issued |
2008 |
en |
dc.identifier.citation |
Computational Statistics and Data Analysis 52(5):2388-2402 2008 |
en |
dc.identifier.issn |
0167-9473 |
en |
dc.identifier.uri |
http://hdl.handle.net/2292/14341 |
en |
dc.description.abstract |
A general technique is proposed for efficient computation of the nonparametric maximum likelihood estimate (NPMLE) of a survival function. The main idea is to include a new support interval that has the largest gradient value between inclusively every two neighbouring support intervals in the support set at each iteration. It is thus able to expand the support set exponentially fast during the initial stage of computation and tends to produce the same support set of the NPMLE afterward. The use of the proposed technique needs to be combined with an algorithm that can effectively find and remove redundant support intervals, for example, the constrained Newton method, the iterative convex minorant algorithm and the subspace-based Newton method. Numerical studies show that the dimension-reducing technique works very well, especially for purely interval-censored data, where a significant computational improvement via dimension reduction is possible. Strengths and weaknesses of various algorithms are also discussed and demonstrated. (c) 2007 Elsevier B.V. All rights reserved. |
en |
dc.language |
EN |
en |
dc.publisher |
Elsevier |
en |
dc.relation.ispartofseries |
Computational Statistics & Data Analysis |
en |
dc.rights |
Items in ResearchSpace are protected by copyright, with all rights reserved, unless otherwise indicated. Previously published items are made available in accordance with the copyright policy of the publisher. details obtained from: http://www.sherpa.ac.uk/romeo/issn/0167-9473/ |
en |
dc.rights.uri |
https://researchspace.auckland.ac.nz/docs/uoa-docs/rights.htm |
en |
dc.subject |
censored data |
en |
dc.subject |
constrained Newton method |
en |
dc.subject |
iterative convex minorant algorithm |
en |
dc.subject |
nonparametric maximum likelihood |
en |
dc.subject |
subspace-based Newton method |
en |
dc.subject |
survival function |
en |
dc.subject |
EMPIRICAL DISTRIBUTION FUNCTION |
en |
dc.subject |
ISOTONIC REGRESSION |
en |
dc.subject |
MIXING DISTRIBUTION |
en |
dc.subject |
ALGORITHM |
en |
dc.subject |
ESTIMATOR |
en |
dc.subject |
MLE |
en |
dc.title |
Dimension-reduced nonparametric maximum likelihood computation for interval-censored data |
en |
dc.type |
Journal Article |
en |
dc.identifier.doi |
10.1016/j.csda.2007.10.018 |
en |
pubs.issue |
5 |
en |
pubs.begin-page |
2388 |
en |
pubs.volume |
52 |
en |
dc.rights.holder |
Copyright: Elsevier |
en |
pubs.end-page |
2402 |
en |
dc.rights.accessrights |
http://purl.org/eprint/accessRights/RestrictedAccess |
en |
pubs.subtype |
Article |
en |
pubs.elements-id |
78420 |
en |
pubs.org-id |
Science |
en |
pubs.org-id |
Statistics |
en |
pubs.record-created-at-source-date |
2010-09-01 |
en |