一、报告题目:

A bootstrap approach for high-dimensional model averaging


二、报告人:

潘聚明,美国明尼苏达大学德鲁斯校区数学与统计学系


三、报告时间:

2019年5月13日(周一) 下午16:00-17:30


四、报告地点:

知新楼B321


五、报告人简介:

潘聚明博士,美国明尼苏达大学德鲁斯校区数学与统计学系助理教授,美国保龄格林州立大学博士。主要研究方向为模型选择,模型平均,线性混合模型,高维数据分析等。其研究成果发表在Communications in Statistics - Theory and Methods, Journal of Statistical Computation and Simulation, Mathematics in Engineering, Science and Aerospace, Open Journal of Statistics 等知名学术期刊。


六、 报告摘要:

In high-dimensional data analysis, we propose a new bootstrap model averaging method to make accurate and stable predictions. Specifically, we introduce a hybrid approach that combines strengths of model selection and model averaging, where the weight of each model is determined by its Bayesian information (BIC) score and its frequency. Simulations and empirical examples are presented to illustrate the usefulness of the proposed method.


七、主办单位:

2138cn太阳集团古天乐

上一篇: 高级经济学讲座第254期

下一篇: 复杂世界中的理性与科学高级论坛