Uth

生物统计学虚拟研讨会-Joe Cavanaugh博士在概率成对模型上比较

何时何地

3月21日
12:00 pm -1:00 pm

接触

事件描述

主持人:

乔·卡瓦诺(Joe Cavanaugh)博士
Professor, Head of the Department of Biostatistics at the University of Iowa.

抽象的:

在涉及统计模型选择和评估的问题中,经常采用差异措施。差异衡量了拟合的候选模型与基础生成模型之间的分离。在这项工作中,我们考虑了基于对组成差异的概率评估的拟合模型的成对比较。使用非参数引导程序得出概率的估计器。

In the framework of hypothesis testing, nested models are often compared on the basis of the p-value. Specifically, the simpler null model is favored unless the p-value is sufficiently small, in which case the null model is rejected and the more general alternative model is retained. We argue that in certain settings, the p-value and the bootstrap discrepancy comparison probability (BDCP) are equivalent. In particular, we have established this equivalence for the Wald, score, and likelihood ratio tests by employing suitably defined discrepancy measures.

我们认为,P值与BDCP之间的联系不仅导致有关P值的实用性和局限性的潜在新见解,而且还促进了基于差异的推论,超出了假设检验的受限范围。特别是,BDCP的开发并不假设零模型代表真相,而是根据偏见/可变性权衡评估拟合模型的最佳性。BDCP的使用不需要嵌套模型或大型样本量。此外,对BDCP的简单改进提供了一种概率度量,不仅当替代模型最佳时,它不仅倾向于零,而且在零模型最佳时也倾向于一个。

This work is joint with Andres Dajles, Ben Riedle, and Andrew Neath.

Webex密码:

3PF3PYPWZX6

Event Site Link

https://uthealth.webex.com/uthealth/j.php?mtid=m113cf3cbcba643b4307425b638be93e6

附加信息

生物统计学虚拟研讨会-Joe Cavanaugh博士在概率成对模型上比较

{ "name":"Biostatistics Virtual Seminar - Dr. Joe Cavanaugh on Probabilistic Pairwise Model Comparisons", "description":"

主持人:

乔·卡瓦诺(Joe Cavanaugh)博士
Professor, Head of the Department of Biostatistics at the University of Iowa.

抽象的:

在涉及统计模型选择和评估的问题中,经常采用差异措施。差异衡量了拟合的候选模型与基础生成模型之间的分离。在这项工作中,我们考虑了基于对组成差异的概率评估的拟合模型的成对比较。使用非参数引导程序得出概率的估计器。

In the framework of hypothesis testing, nested models are often compared on the basis of the p-value. Specifically, the simpler null model is favored unless the p-value is sufficiently small, in which case the null model is rejected and the more general alternative model is retained. We argue that in certain settings, the p-value and the bootstrap discrepancy comparison probability (BDCP) are equivalent. In particular, we have established this equivalence for the Wald, score, and likelihood ratio tests by employing suitably defined discrepancy measures.

我们认为,P值与BDCP之间的联系不仅导致有关P值的实用性和局限性的潜在新见解,而且还促进了基于差异的推论,超出了假设检验的受限范围。特别是,BDCP的开发并不假设零模型代表真相,而是根据偏见/可变性权衡评估拟合模型的最佳性。BDCP的使用不需要嵌套模型或大型样本量。此外,对BDCP的简单改进提供了一种概率度量,不仅当替代模型最佳时,它不仅倾向于零,而且在零模型最佳时也倾向于一个。

This work is joint with Andres Dajles, Ben Riedle, and Andrew Neath.

Webex密码:

3PF3PYPWZX6

\ n \ nhttps://uthealth.webex.com/uthealth/j.php?mtid = m113cf3cbcba643b4307425b638be93e6““:“ 12:00”,“末日”:“ 13:00”,“位置”:“ $ con.location”,“ label”:“添加到日历”,“选项”:[“ Apple”,“ Google)“,“ ial”,“ Microsoft365”,“ Microsoftteams”,“ Outlook.com”,“ Yahoo”],“ TimeZone”:“ America/Chicago”,“ trigger”,“触发”:“单击”,“ Inline”:true,true,true,”listStyle”:“模态”,“ iCalfileName”:“提醒 - 事件”}
后退
加载...
加载...
Baidu