Bayesian Model Averaging in the Instrumental Variable Regression Model
Bayesian Model Averaging in the Instrumental Variable Regression Model
复制标题
DOI：
10.1016/j.jeconom.2012.06.005
复制
发表时间：
2012-12
影响因子：
6.3
通讯作者：
G. Koop;R. León-González;Rodney W. Strachan
中科院分区：
文献类型：
--
作者：
G. Koop;R. León-González;Rodney W. Strachan
本文考虑了工具集、外生性约束、识别约束的有效性和外生性回归变量集均存在不确定性时的工具变量回归模型。这种不确定性可能导致大量的模型。为了避免与标准模型选择程序相关的统计问题，我们开发了一种可逆跳跃马尔可夫链蒙特卡罗算法，使我们能够进行贝叶斯模型平均。该算法是非常灵活的，可以很容易地适应于分析任何不同的先验已提出的贝叶斯工具变量文献。我们展示了如何计算任何相关限制的概率，如外生性或过度识别。我们说明了我们的方法在返回到学校的应用程序。
This paper considers the instrumental variable regression model when there is uncertainty about the set of instruments, exogeneity restrictions, the validity of identifying restrictions and the set of exogenous regressors. This uncertainty can result in a huge number of models. To avoid statistical problems associated with standard model selection procedures, we develop a reversible jump Markov chain Monte Carlo algorithm that allows us to do Bayesian model averaging. The algorithm is very flexible and can be easily adapted to analyze any of the different priors that have been proposed in the Bayesian instrumental variables literature. We show how to calculate the probability of any relevant restriction such as exogeneity or over-identification. We illustrate our methods in a returns-to-schooling application.