Estimating the number of species through Bayesian method in Sampling-based approaches
碩士 === 國立成功大學 === 數學系應用數學碩博士班 === 91 === Gibbs sampler and Data augmentation algorithms can be viewed as two alter- native sampling(or Monte Carlo)-based approaches to calculate the numerical estimates of marginal density distribution. This article is concerned with the estimation of the numbe...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | en_US |
Published: |
2003
|
Online Access: | http://ndltd.ncl.edu.tw/handle/01946910479746783204 |
Summary: | 碩士 === 國立成功大學 === 數學系應用數學碩博士班 === 91 === Gibbs sampler and Data augmentation algorithms can be viewed as two alter-
native sampling(or Monte Carlo)-based approaches to calculate the numerical
estimates of marginal density distribution. This article is concerned with the
estimation of the number of species in a population through a fully hierarchical
Bayesian model and an empirical Bayes approach using two kinds of alternative
sampling-based approaches proposed above. The proposed Bayesian estimators
are based on Poisson random variables with mean that are distributed according
to a prior distribution with unknown parameters.
|
---|