The EM Algorithm for Censored Data.
Abstract
Three methods for applying the expectation maximization algorithm to censored data are considered, the Buckley-James, a proposed simpler nonparametric method and a normal model for censored data. A new estimator for the variance of y in the Buckley-James model is proposed and simulations comparing the three methods are described. To illustrate the use of these methods they are applied to the Stanford heart transplant data. (Author)
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 01, 1984
- Accession Number
- ADA148136
Entities
People
- H. Schneider
- L. Weissfeld
Organizations
- University of North Carolina at Chapel Hill