Some challenges in causal inference in large,sparse administrative data

来源 :上海交通大学 | 被引量 : 0次 | 上传用户：Leichenglin8888

【摘要】

：

Large administrative data from healthcare claims and electronic health records provide significant opportunities for health services,drug safety,and other health research,due to large sample sizes and

【作者】

：

Robert W Platt

【机构】

：

McGill University,Montreal,Canada

【出处】

：

上海交通大学

【发表日期】

：

2016年4期

【关键词】

：

Causal inference administrative data big data confounding targeted maximum likel

下载到本地 , 更方便阅读

下载此文赞助VIP

声明 : 本文档内容版权归属内容提供方 , 如果您对本文有版权争议 , 可与客服联系进行内容授权或下架

论文部分内容阅读

其他文献

圆柱壳振动试验系统建模

本文以圆柱壳、夹具为研究对象，用数值模拟和试验方法对振动试验系统建模。以试验前四阶固有频率为优化目标，以圆柱壳材料属性、组合体连接属性为优化对象，用随机优化算法修正有限元模型，最终得到合理的有限元模型。

会议

vibration system of cylinder shell FEA EMA model updating

耐火耐候建筑用钢与普通碳素结构钢高温及耐火性能的对比研究

钢结构建筑的耐火性能主要依靠材料本身的高温耐火强度和材料表面的防火保护涂料.本文对武钢研制生产的高性能耐火耐候建筑用钢WGJ510C2和普通建筑用钢Q235在实验室条件下进行了中型炉耐火试验的对比分析,结果表明:两种钢在不同涂料以及同一涂料的不同厚度下,其耐火极限均有明显的差异,在裸露条件下,WGJ510C2的耐火极限明显优于Q235;同样的涂料在一定厚度范围内,随着防火涂料厚度增加,耐火钢的优势

会议

耐火性能耐候性能建筑用钢防火涂料碳素结构钢

弓长岭井下铁矿1950~2002年工亡事故统计分析

本文通过对弓长岭矿业公司井下铁矿1950~2002年近52年的工亡事故案例分析,吸取事故教训,采取相应的预防措施,从而指导生产,实现企业工亡事故为零的目标.

会议

铁矿工亡事故案例分析

Integration of high-dimensional genomic and imaging features for risk prediction of lung cancers

Introduction: High‐dimensional genomics,genetics and proteomics techniques have been widely used in cancer research for over two decades.

会议

结合济钢第一炼铁厂生产工艺,浅论高炉区域渣铁罐发生行车事故后的铁路运输保产办法

本文介绍了济钢第一炼铁厂高炉区域渣铁罐发生行车事故后的铁路运输保产办法,适用于同类型冶金企业,有较好的借鉴作用.

会议

高炉区域渣铁罐铁路运输保产行车事故

From Multiple Gaussian Sequences to Functional Data

We expand the notion of Gaussian sequence model to n experiments and propose a re-fined Stein estimation which relies on pooling information across experiments.

会议

Functional dataLe Cam equivalenceOracle inequalityNonparametric regressionSt

A joint Bayesian modeling for integrating microarray and RNA-seq transcroptomic data

With rapid accumulation of public gene expression data,meta-analysis to combine multiple transcriptomic studies for biomarker detection improves detection accuracy and robustness.

会议

Bayesian hierarchical modelmeta-analysistranscriptomic data analysismicroarra

Bayesian Nonparametric Inference for Tumor Purity and Tumor Subclones

A solid tumor sample consists of mixed populations of cells,normal cells and cancer cells.Heterogeneity among cancer cells is further explained by multiple distinct tumor subclones.

会议

Categorical Indian buffet processFeature allocation modelsMarkov chain Monte C

Design Considerations in Integrated Phase Ⅱ/Ⅲ Oncology Clinical Trials

In oncology clinical development,randomized phase Ⅱ studies have been increasingly used in recent years for a variety of reasons.

会议

clinical trialsexperiment designsurvival analysiscancer

Nonparametric Kernel-Based Estimation for Time-Varying Coefficient Models with Multivariate Integrat

This paper studies nonlinear cointegration models in which the structural coefficients may evolve smoothly over time,and considers time-varying coefficient functions estimated by nonparametric kernel

会议

CointegrationKernel degeneracyNonparametric regressionSuper-consistencyTime

Some challenges in causal inference in large,sparse administrative data

与本文相关的学术论文