.png){kind=icon}
返回
Treatment effect estimation with efficient data aggregation
.png){kind=icon}
PRE
AI
DOI：10.3150/24-BEJ1782.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Data aggregation, also known as meta analysis, is widely used to combine knowledge on parameters shared in common (e.g., average treatment effect) between multiple studies. In this paper, we introduce an attractive data aggregation scheme that pools summary statistics from various existing studies. Our scheme informs the design of new validation studies and yields unbiased estimators for the shared parameters. In our setup, each existing study applies a LASSO regression to select a parsimonious model from a large set of covariates. It is well known that post-hoc estimators, in the selected model, tend to be biased. We show that a novel technique called data carving yields us a new unbiased estimator by aggregating simple summary statistics from all existing studies. The proposed estimator has two key features: (a) we make the fullest possible use of data, from all studies, without the risk of bias from model selection; (b) we enjoy the added benefit of individual data privacy, because raw data from these studies need not be shared or stored for efficient estimation.
Keyword:
Conditional inference
debiased estimation
data carving
LASSO
meta analysis
期刊
B
IF:
1.7
论文数:
106
被引数:
0
机构
引用论文
Individual Data Protected Integrative Regression Analysis of High-Dimensional Heterogeneous Data
OAAI
OAAI分享收藏EXACT POST-SELECTION INFERENCE, WITH APPLICATION TO THE LASSO精确的选择后推理，并应用于套索.png)
ANNALS OF STATISTICSOAAI
ANNALS OF STATISTICSIF3.7
OAAI分享收藏
分享收藏
查看更多内容