| 主讲人 |
Cristiano Villa |
简介 |
<p>The purpose is to present a novel prior for tree topology within Bayesian additive regression trees (BART) models. This approach quantifies the hypothetical loss in information and the loss due to the complexity associated with choosing the wrong tree structure. The resulting prior distribution is compellingly geared toward sparsity, a critical feature considering BART models’ tendency to overfit. The method incorporates prior knowledge into the distribution via two parameters that govern the tree’s depth and balance between its left and right branches. Additionally, a default calibration is proposed for these parameters, offering an objective version of the prior. The method’s efficacy is demonstrated on both simulated and real datasets. </p> |
| 时间 |
2026-05-27 (Wednesday) 16:40-18:00 |
地点 |
Room N302, Economics Building |
| 讲座语言 |
English |
主办单位 |
厦门大学经济学院、王亚南经济研究院、邹至庄经济研究院 |
| 承办单位 |
厦门大学经济学院、王亚南经济研究院、邹至庄经济研究院 |
类型 |
系列讲座 |
| 联系人信息 |
林老师，电话2180723，邮箱yurenlin@xmu.edu.cn |
主持人 |
Weixuan Zhu |
| 专题网站 |
|
专题 |
|
| 主讲人简介 |
<p>Cristiano Villa’s research focuses on Bayesian statistics, with a particular emphasis on developing objective methods. His work addresses core challenges in prior specification, model selection, and computational statistics. At Duke Kunshan University, he teaches within the Applied Mathematics major, offering courses in probability, statistics, and stochastic processes. He holds an M.Sc. and a Ph.D. in Statistics from the University of Kent. Prior to his doctorate, he gained over 12 years of international experience as an auditor and advisor at KPMG, working in Italy, the UK, New Zealand, and Singapore. He transitioned to academia in 2014, holding positions at the University of Kent and Newcastle University before joining Duke Kunshan. </p> |
期数 |
高级计量经济学与统计学系列讲座2026年春季学期第十一讲（总204讲） |
