Computational Algorithms for Censored-Data Problems Using Intersection Graphs
- 1 September 2001
- journal article
- Published by Taylor & Francis in Journal of Computational and Graphical Statistics
- Vol. 10 (3) , 403-421
- https://doi.org/10.1198/106186001317114901
Abstract
This article presents methods for finding the nonparametric maximum likelihood estimate (NPMLE) of the distribution function of time-to-event data. The basic approach is to use graph theory (in particular intersection graphs) to simplify the problem. Censored data can be represented in terms of their intersection graph. Existing combinatorial algorithms can be used to find the important structures, namely the maximal cliques. When viewed in this framework there is no fundamental difference between right censoring, interval censoring, double censoring, or current status data and hence the algorithms apply to all types of data. These algorithms can be extended to deal with bivariate data and indeed there are no fundamental problems extending the methods to higher dimensional data. Finally this article shows how to obtain the NPMLE using convex optimization methods and methods for mixing distributions. The implementation of these methods is greatly simplified through the graph-theoretic representation of the...Keywords
This publication has 16 references indexed in Scilit:
- Nonparametric Methods for Doubly Truncated DataJournal of the American Statistical Association, 1999
- The Iterative Convex Minorant Algorithm for Nonparametric EstimationJournal of Computational and Graphical Statistics, 1998
- Interval censored data: A note on the nonparametric maximum likelihood estimator of the distribution functionBiometrika, 1996
- A review of reliable maximum likelihood algorithms for semiparametric mixture modelsJournal of Statistical Planning and Inference, 1995
- Maximum likelihood for interval censored data: Consistency and computationBiometrika, 1994
- Iterated Exponentiation, Matrix-Matrix Exponentiation, and EntropyJournal of Mathematical Analysis and Applications, 1994
- An Algorithm for Computing the Nonparametric MLE of a Mixing DistributionJournal of the American Statistical Association, 1992
- A vertex-exchange-method in D-optimal design theoryMetrika, 1986
- The Geometry of Mixture Likelihoods: A General TheoryThe Annals of Statistics, 1983
- Incidence matrices and interval graphsPacific Journal of Mathematics, 1965