Please wait a minute...
高校应用数学学报
Applied Mathematics A Journal of Chinese Universities  2016, Vol. 31 Issue (2): 127-135    DOI:
    
Bayesian inference for dynamic heterogeneity stochastic frontier model
CHENG Di1, ZHANG Shi-bin2
1. School of Math. Sci., Inner Mongolian Univ., Hohhot 010021, China
2. Dept. of Math., Shanghai Maritime Univ., Shanghai 201306, China
Download:   PDF(0KB)
Export: BibTeX | EndNote (RIS)      

Abstract  If heterogeneity of the “inefficiency” term is disregarded, it will result in the incorrect estimate of this term in the stochastic frontier model. By combining the influence from characteristic differences of individuals with the time-varying property of variance, a dynamic heterogeneity stochastic frontier model is proposed. By the Gibbs sampling, the methodology for Bayesian analysis of the dynamic heterogeneity stochastic frontier model is given. For each model parameter, the posterior distribution is derived. A simulation study shows that under the criterion of minimizing the posterior mean square error, the Bayesian estimate is close to its true value for small and medium sized samples. From the Bayesian analysis based on the real electric power company generation data, it is evidenced that there exists the time-varying property for the variance of the logarithm “inefficiency” term.

Key words： stochastic frontier model      Bayesian inference      heterogeneity      Gibbs sampling      Metropolis-Hastings sampling     
Received: 13 November 2015      Published: 17 May 2018
CLC:  O212.8  
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
CHENG Di
ZHANG Shi-bin
Cite this article:

CHENG Di, ZHANG Shi-bin. Bayesian inference for dynamic heterogeneity stochastic frontier model. Applied Mathematics A Journal of Chinese Universities, 2016, 31(2): 127-135.

URL:

http://www.zjujournals.com/amjcua/     OR     http://www.zjujournals.com/amjcua/Y2016/V31/I2/127


动态异方差随机前沿模型的Bayesian推断

随机前沿模型中如果忽略单边干扰项的异质性(heterogeneity)往往导致错误的效率估计. 从个体特征的影响和方差的时变性两方面对单边干扰项进行考虑,提出异方差动态随机前沿模型. 利用Gibbs抽样方法对动态异方差随机前沿模型进行Bayesian分析. 导出了模型参数的后验条件分布, 对中小样本的模拟实验显示在最小后验均方误差准则下得到的参数估计值非常接近真值. 对电力公司的实际数据进行 分析显示对数无效率项的方差有一定的时变性.

关键词： 随机前沿模型,  Bayesian分析,  异方差,  Gibbs抽样,  Metropolis-Hastings抽样 
[1] HE Chao-bing. Bayesian parameter estimation of failure rate model with a change point for truncated and censored data[J]. Applied Mathematics A Journal of Chinese Universities, 2016, 31(4): 413-427.