Let H be the non-negative definite selfadjoint operator associated to a regular irreducible Dirichlet form on L 2 (X, m). Assume that H has discrete spectrum. We study perturbations of this operator which arise through the imposition of Dirichlet boundary conditions on a compact subset of X. The eig
Estimation for dirichlet mixed models
β Scribed by Steve Leeds; Alan E. Gelfand
- Publisher
- John Wiley and Sons
- Year
- 1989
- Tongue
- English
- Weight
- 873 KB
- Volume
- 36
- Category
- Article
- ISSN
- 0894-069X
No coin nor oath required. For personal study only.
β¦ Synopsis
Dirichlet mixed models find wide application. Estimation is usually achieved through the method of moments. Here we present an iterative hybrid algorithm for obtaining the maximum likelihood estimate employing both modified Newton-Raphson and E-M methods. This successful MLE algorithm enables calculation of a jack-knife MLE. Simulation comparison of the three estimates is provided. The MLE substantially improves upon the moments estimator particularly with increasing dimension. The jack-knife MLE in turn offers dramatic improvement over the MLE.
π SIMILAR VOLUMES
In mixed linear models with two variance components, classes of estimators improving on ANOVA estimators for the variance components and the ratio of variances are constructed on the basis of the invariant statistics. Out of the classes, consistent, improved and positive estimators are singled out.
The problem of nonnegative quadratic estimation of a parametric function Necessary and sufficient conditions are given for y$A 0 y to be a minimum biased estimator for #. It is shown how to formulate the problem of finding a nonnegative minimium biased estimator of # as a conic optimization problem
## Introduction The following result on the exponential decay of the eigenfunctions for the Dirichlet Laplacian in horn shaped regions is proved in R. Ban~uelos and B. Davis [5], [6]. Theorem A. Let %: (0, ) Γ (0, 1] be continuous and define Suppose %(x) a 0 as x A and let . \* be any L 2 -eigen