Econometric method of economic data with measurement error and its application

带有测量误差的经济数据的计量方法及其应用

• 批准号: 10630019
• 负责人: HASEGAWA Hikaru
• 金额: $ 1.86万
• 依托单位: HOKKAIDO UNIVERSITY
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for Scientific Research (C)
• 财政年份: 1998
• 资助国家: 日本
• 起止时间: 1998 至 1999
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-10630019/
• 关键词: Measurement errors; Bayesian analysis; Engel curve; Markov chain Monte Carlo (MCMC); HOGLEX demand system; エンゲル関数; 需要モデル

In this research, we considered the Bayesian estimation of some economic models with the measurement errors on both the left and the right hand side. It is noteworthy that in the Bayesian approach no additional data are required in contrast with the non-Bayesian approach. In particular, we estimate the HOGLEX demand system and the Engel curves specified as Working-Leser form. We also derived the Bayesian estimation procedure in both models with and without an instrumental variable. Using household expenditure unit records from Thailand, Philippines and United Kingdom, this research applied the developed Bayesian methods to estimate the models. From the results of this research, the Bayesian methods are very suitable to the estimation of models with measurement errors and are applied to complex models, which are not estimated easily by the non-Bayesian methods.

在本研究中，我们考虑了一些经济模型的贝叶斯估计的测量误差的左侧和右侧。值得注意的是，与非贝叶斯方法相比，贝叶斯方法不需要额外的数据。特别是，我们估计HOGLEX需求系统和恩格尔曲线指定为Working-Leser形式。我们还推导了贝叶斯估计过程中的两个模型和没有一个工具变量。本研究以泰国、菲律宾和英国的家庭支出单位记录为例，应用贝叶斯方法对模型进行估计。从研究结果来看，贝叶斯方法非常适合于具有测量误差的模型的估计，并且适用于非贝叶斯方法难以估计的复杂模型。