基本信息
浏览量:0
职业迁徙
个人简介
Research Interests
Dr. Cuellar's research examines the use of statistics in the law. Her research focuses on two areas: causal inference and the analysis of forensic evidence.
Dr. Cuellar studies how to make appropriate statistical arguments of causal attribution. These include cases of Shaken Baby Syndrome/Abusive Head Trauma, in which it must be determined whether a child was shaken or abused, and toxic torts, in which, for example, it must be determined whether the plaintiffs' cancer was indeed caused by their exposure to a harmful chemical. Dr. Cuellar has developed an innovative influence-function-based method to estimate the probability of causation, a tool to evaluate causal attribution. Under weak structural assumptions, her method allows for statistical inference even with nonparametric estimation of nuisance functions, and thus it is robust to parametric assumptions. This method could help to more accurately estimate probabilities that lead to determining whether an individual or a group is guilty of an action or a crime.
Dr. Cuellar also researches the validity of statistical statements in forensic analysis. She is currently examining how contextual information about a case (such as demographic information about a suspect) influences a forensic examiner’s conclusion (such as concluding that the suspect's firearm is the same as the firearm used in the crime scene). She is also evaluating the foundational validity of tool mark analysis, in which examiners often claim they can determine whether two marks made by a tool, such as a screwdriver, were made by the same tool. Strengthening the statistical foundations of forensic science could help make the criminal justice system more fair.
Dr. Cuellar's research examines the use of statistics in the law. Her research focuses on two areas: causal inference and the analysis of forensic evidence.
Dr. Cuellar studies how to make appropriate statistical arguments of causal attribution. These include cases of Shaken Baby Syndrome/Abusive Head Trauma, in which it must be determined whether a child was shaken or abused, and toxic torts, in which, for example, it must be determined whether the plaintiffs' cancer was indeed caused by their exposure to a harmful chemical. Dr. Cuellar has developed an innovative influence-function-based method to estimate the probability of causation, a tool to evaluate causal attribution. Under weak structural assumptions, her method allows for statistical inference even with nonparametric estimation of nuisance functions, and thus it is robust to parametric assumptions. This method could help to more accurately estimate probabilities that lead to determining whether an individual or a group is guilty of an action or a crime.
Dr. Cuellar also researches the validity of statistical statements in forensic analysis. She is currently examining how contextual information about a case (such as demographic information about a suspect) influences a forensic examiner’s conclusion (such as concluding that the suspect's firearm is the same as the firearm used in the crime scene). She is also evaluating the foundational validity of tool mark analysis, in which examiners often claim they can determine whether two marks made by a tool, such as a screwdriver, were made by the same tool. Strengthening the statistical foundations of forensic science could help make the criminal justice system more fair.
研究兴趣
论文共 46 篇作者统计合作学者相似作者
按年份排序按引用量排序主题筛选期刊级别筛选合作者筛选合作机构筛选
时间
引用量
主题
期刊级别
合作者
合作机构
Michael Rosenblum, Elizabeth T. Chin,Elizabeth L. Ogburn, Akihiko Nishimura, Daniel Westreich,Abhirup Datta,Susan Vanderplas,Maria Cuellar,William C. Thompson
LAW PROBABILITY & RISKno. 1 (2024)
arxiv(2024)
引用0浏览0引用
0
0
arxiv(2024)
引用0浏览0引用
0
0
arxiv(2023)
JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES A-STATISTICS IN SOCIETYno. Supplement_2 (2022): S620-S643
Journal of Analytical Toxicologyno. 5 (2021)
加载更多
作者统计
合作学者
合作机构
D-Core
- 合作者
- 学生
- 导师
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn