Bayesian Efficiency Analysis With a Flexible Form: The AIM Cost Function
灵活函数形式下的贝叶斯效率分析：AIM 成本函数
In this article, the authors describe the use of Gibbs sampling methods for drawing posterior inferences in a cost frontier model with an asymptotically ideal price aggregator, nonconstant returns to scale, and composed error. An empirical example illustrates the sensitivity of efficiency measures to assumptions made about the functional form of the frontier. The authors also examine the consequences of imposing regularity through parametric restrictions alone.