Multivariate Mixtures of Erlangs for Density Estimation Under Censoring and Truncation
Lifetime Data Analysis, 2016, 22(3), 429-455.
36 Pages Posted: 7 Jan 2015 Last revised: 17 May 2017
Date Written: December 19, 2014
Multivariate mixtures of Erlang distributions form a versatile, yet analytically tractable, class of distributions making them suitable for multivariate density estimation. We present a flexible and effective fitting procedure for multivariate mixtures of Erlangs, which iteratively uses the EM algorithm, by introducing a computationally efficient initialization and adjustment strategy for the shape parameter vectors. We furthermore extend the EM algorithm for multivariate mixtures of Erlangs to be able to deal with censored and truncated data. The effectiveness of the proposed algorithm, which has been implemented in R, is demonstrated on simulated as well as real data sets.
The Addendum for this paper are available at the following URL: http://ssrn.com/abstract=2593016
Keywords: Multivariate Erlang mixtures with a common scale parameter, Density estimation, Censored data, Truncated data, Expectation-maximization algorithm, Maximum likelihood.
Suggested Citation: Suggested Citation