Robust maximum likelihood estimation

Dimitris Bertsimas; Omid Nohadani

首页> 外文期刊>Quality Control and Applied Statistics >Robust maximum likelihood estimation

【24h】

Robust maximum likelihood estimation

机译：Robust maximum likelihood estimation

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相关主题

摘要

In statistics, conclusions are drawn dependent on uncertainties in the data. Given data errors, this article provides robust maximum likelihood estimators (RMLEs) that are protected against such errors using robust optimization principles. The adversarial type and probabilistic type errors are considered. In order to obtain the RMLEs, efficient local and global search algorithms are developed for the case of multivariate normally-distributed data. To demonstrate the findings and performance of the proposed estimators, both computer simulated data and real time data are used. From the results, it is observed that given the uncertainties in the data, the proposed RMLEs are superior in the sense that they lead to more reliable decisions. (28 refs.).

著录项

来源
《Quality Control and Applied Statistics》 |2021年第6期|397-398|共2页
作者
Dimitris Bertsimas; Omid Nohadani;
展开▼
作者单位

Operations Research Center and Sloan School of Management, Massachusetts Institute of Technology, Cambridge, MA 02139;

Department of Industrial Engineering and Management Sciences, Northwestern University, Evanston, IL 60208;

展开▼
收录信息
原文格式 PDF
正文语种英语
中图分类概率论、数理统计的应用;
关键词

Robust maximum likelihood estimation

摘要

著录项

相关主题

期刊订阅