Efficient pooling of cross-section and time series data using Bayesian machine learning with two econometric applications

使用贝叶斯机器学习和两个计量经济学应用程序有效汇集横截面和时间序列数据

• 批准号: DP0343650
• 负责人: A/Prof David Dowe
• 金额: $ 7.4万
• 依托单位: Monash University
• 依托单位国家: 澳大利亚
• 项目类别: Discovery Projects
• 财政年份: 2003
• 资助国家: 澳大利亚
• 起止时间: 2003-04-14 至 2007-09-30
• 项目状态: 已结题
• 来源: https://dataportal.arc.gov.au/RGS/Web/Grants/DP0343650
• 关键词: Efficient; pooling; cross; section; time

In this project, we adapt a Bayesian modelling strategy, namely the minimum message length principle, to the problem of efficient partitioning of economic units, such as firms or countries, into groups whose behavioural patterns are similar within each group but distinct across groups. This methodology can incorporate the requirements of economic theory. The resulting software will be developed for the Web. We consider two specific applications, namely modelling gasoline demand in OECD countries, and finding the foreign factor with the most predictive power for the growth rate of the Australian economy. The second application is of considerable national interest.

在这个项目中，我们适应贝叶斯建模策略，即最小信息长度原则，经济单位，如公司或国家，有效的分区成组的行为模式是相似的，但不同的群体之间的问题。这种方法可以结合经济理论的要求。由此产生的软件将为网络开发。我们考虑两个具体的应用，即在经合组织国家的汽油需求建模，并找到最具预测力的澳大利亚经济增长率的外国因素。第二个应用程序是相当大的国家利益。