Asymptotic properties of a stochastic EM algorithm for mixtures with censored data |
| |
Authors: | Ingrid Svensson Sara Sjstedt-de Luna |
| |
Institution: | aDepartment of Statistics, Umeå University, S-901 87 Umeå, Sweden;bDepartment of Mathematics and Mathematical Statistics, Umeå University, S-901 87 Umeå, Sweden |
| |
Abstract: | Weak consistency and asymptotic normality is shown for a stochastic EM algorithm for censored data from a mixture of distributions under lognormal assumptions. The asymptotic properties hold for all parameters of the distributions, including the mixing parameter. In order to make parameter estimation meaningful it is necessary to know that the censored mixture distribution is identifiable. General conditions under which this is the case are given. The stochastic EM algorithm addressed in this paper is used for estimation of wood fibre length distributions based on optically measured data from cylindric wood samples (increment cores). |
| |
Keywords: | Censoring Fibre length distribution Identifiability Increment core Mixture Stochastic EM algorithm |
本文献已被 ScienceDirect 等数据库收录! |