通过因子分析的方法来解释观测变量的相关性，这种方法是通过引入潜在变量来直接刻画相关性。 基于Bayes统计原理、方法用来解决模型的参数估计问题和统计推断，采用Markov Chains Monte Carlo (MCMC)进行统计计算。随机模拟的结果表明所提出的林木存活率预测方法是有效的。最后利用该方法对山 西沁水县沁水林场的林木存活率与林分的鼠兔数关系进行了分析。
Abstract
Factor analysis, which is characterized by the latent variables, is a popular method to interpret the correlation among the observed variables. In this paper, latent constructs are introduced to describe the relationship of the categorical variables. Within the Bayesian framework, parameters estimations and statistical inferences are carried out via a popular technique, i.e., Markov Chains Monte Carlo (MCMC). A simulation study is conducted to assess the proposed method. A pika data set is used to illustrate the real application.
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1]Agresti A. Categorical Data Analysis[M]. NewYork: John Wiley and Sons Inc, 2002.
[2]We B C. Exponential Family Nonlinear Models[M]. Singapore: Springer, 1998.
[3]熊林平,曹秀堂,徐勇勇,等. 纵向观测二分类数据的广义线性模型分析[J]. 第二军医大学学 报,1999,20(7):483-485.
[4]曹铭昌,周广胜,翁恩生. 广义模型及分类回归树在物种分布模拟中的应用与比较[J]. 生态学 报,2005,25(8):2031-2040.
[5]Choi T, Schervish M J, Schmitt K A, et al. A Bayesian approach to Logistic regression model with incomplete information[J]. Biometrics, 2008, 64(2): 424-431.
[6]Bollen K A. Structural equations with latent variable[M]. New York: Wiley, 1989.
[7]Berger J O. Statistical Decision Theory and Bayesian Analysis[M]. New York: Springer Verlag, 1980.
[8]Gilks W R, Richardson S, Spiegelhalter D J. Makov Chain Monte Carlo in Practice [C]//London, England: Chapman and Hall, 1996.
[9]Tanner M A, Wong W H. The calculation of posterior distributions by data augmentation (with discussion)[J]. Journal of the American Statistical Association, 1987, 8: 528-550.
[10]Geman S, Geman D. Stochastic relaxation, Gibbs distribution, and the Bayesian restoration of images[C]//IEEE Transactions on Pattern Analysis and Machine Intelligence, 1984.
[11]Metropolis N, Rosenbluth A W, Rosenbluth M N, et al. Equations of state calculations bu fast computing machines[J]. Journal of Chemical Physics, 1953, 21: 1807-1092.
[12]Hastings W K. Monte Carlo sampling methods using Markov chains and their applications[J]. Biometrika, 1970, 57: 97-100.
[13]Tierney L. Markov Chains for exploring posterior distributions (with discussion)[J]. The Annals of Statistics, 1994, 22: 1701-1786.
[14]郭爱花,陈钰,符利勇. 野兔对人工幼林危害的研究[J]. 山东林业科技,2009,39(1):54-55.
[15]Kass R E, Raftery A E. Bayes factors[J]. Journal of the American Statistical Association, 1995, 90: 773-795.
[16]Gelman A, Meng X L. Simulating normalizing constants: From importance sampling to bridge sampling to pathing sampling[J]. Statistical Sciences, 1998, 13, 163-185.
[17]Lee S Y. Structural Equation Modeling: A Bayesian Perspective[M]. Singapore: John Wiley, 2007.
基金
收稿日期：2009-06-02修回日期：2009-11-10基金项目：国家自然科学基金项目 (10671032)作者简介：夏业茂(1971—)，副教授。Email: ym_xia71@163.com。引文格式：夏业茂,刘应 安,房政. 广义Logistic回归模型Bayes分析及其在林木存活率预报中的应用[J]. 南京林业大学学报:自然 科学版,2010,34(2):47-50.
PDF(521599 KB)
