潛在類別模型的蒙地卡羅馬可夫鍊分析

Latent Class Models in Monte Carlo Markov Chain Analysis

尹維烘(Wei-Hung Yin)

指導教授 ： 林余昭 ； 鄭子韋

中原大學/理學院/應用數學研究所/碩士(2013年)

https://doi.org/10.6840/cycu201300956

摘要

潛類別模型概念簡單、容易了解。潛在類別參數的傳統估計方法有最大概似估計、EM 演算法。本文將使用WinBUGS軟體，利用蒙地卡羅馬可夫鍊的方法去估計潛在類別參數及條件機率，並將其應用於中原大學101年下學期微積分第一次會考成績的分析。

關鍵字

蒙地卡羅馬可夫鍊 ； EM 演算法 ； 最大概似估計 ； 潛類別模型

並列摘要

The concepts of latent class models are easy to understand.Maximum likelihood estimations (MLE) and EM algorithm are two methods used to estimate the latent class parameters. In this paper, we use the WinBUGS software and the Monte Carlo Markov Chain (MCMC) methods to estimate these latent class parameters and conditional probabilities. We apply the techniques to analyze the CYCU calculus examinations.

並列關鍵字

Monte Carlo Markov Chain ； EM algorithm ； Maximum Likelihood Estimation ； Latent Class Model

參考文獻

[2] Carlin, J. B.(1992). Meta-analysis for 2 x 2 tables: a Bayesian approach.

Statistics in Medicine,11,141-159.

[4] Dayton,C.M.and Macready, G.B.(1988).A Latent Class Covariate Model with Applications toCriterion-ReferencedTesting.InLangeheine,R.and Rost,J. (Eds.), Latent Trait and Latent Class Models New York:Plenum Publications Inc,129-143.

[6] Evans, M. and Swartz T.(1995). Methods for Approximating Integrals in Statisticswith Special Emphasis on Bayesian Integration problems.Statistical Science 10:254–272.

[7] Geman,S.and Geman,D.(1984).Stochastic Relaxation, Gibbs Distributions and the Bayesian Restoration of Images. IEEE Transactions on Pattern Analysis and Machine Intelligence.6:6 721–741.