Bayesian variable selection for understanding mixtures in environmental exposures.
Bayesian variable selection for understanding mixtures in environmental exposures.
复制标题
DOI：
10.1002/sim.9099
复制
发表时间：
2021-09-30
影响因子：
2
通讯作者：
Miranda ML
中科院分区：
文献类型：
--
作者：
Kowal DR;Bravo M;Leong H;Bui A;Griffin RJ;Ensor KB;Miranda ML
社会和环境压力是儿童发展的关键因素。然而，存在大量可测量的社会和环境因素，其影响可能是累积的，相互作用的，或零。使用一个全面的队列儿童在北卡罗来纳州，我们研究的影响，社会和环境变量对第四届年底的年级考试成绩在阅读和数学。为了确定预测这些教育成果的基本因素，我们设计了新的工具，贝叶斯线性变量选择决策分析。我们提取一个预测的最佳子集的解释变量耦合损失函数与一个新的基于模型的惩罚方案，这导致连贯的贝叶斯决策分析和经验改进变量的选择，估计和预测模拟数据。贝叶斯线性模型将不确定性量化传播到所有预测评估，这对于可解释和鲁棒的模型比较非常重要。这些预测比较是在样本外进行的，使用定制的近似算法，避免了计算密集型模型重新拟合。我们应用我们的变量选择技术，以确定社会和环境压力的联合收集及其相互作用，提供明确的和可量化的改善预测阅读和数学考试成绩。
Social and environmental stressors are crucial factors in child development. However, there exists a multitude of measurable social and environmental factors—the effects of which may be cumulative, interactive, or null. Using a comprehensive cohort of children in North Carolina, we study the impact of social and environmental variables on 4th end-of-grade exam scores in reading and mathematics. To identify the essential factors that predict these educational outcomes, we design new tools for Bayesian linear variable selection using decision analysis. We extract a predictive optimal subset of explanatory variables by coupling a loss function with a novel model-based penalization scheme, which leads to coherent Bayesian decision analysis and empirically improves variable selection, estimation, and prediction on simulated data. The Bayesian linear model propagates uncertainty quantification to all predictive evaluations, which is important for interpretable and robust model comparisons. These predictive comparisons are conducted out-of-sample with a customized approximation algorithm that avoids computationally intensive model re-fitting. We apply our variable selection techniques to identify the joint collection of social and environmental stressors—and their interactions—that offer clear and quantifiable improvements in prediction of reading and mathematics exam scores.
登录
查看更多内容
影响因子：
5.5
作者：
Kramer MR;Hogue CR
通讯作者：
Hogue CR
DOI：
10.1214/10-aoas388
发表时间：
2011-01-01
期刊：
The annals of applied statistics
影响因子：
--
作者：
Breheny P;Huang J
通讯作者：
Huang J
影响因子：
2
作者：
Gelman, Andrew
通讯作者：
Gelman, Andrew
影响因子：
158.5
作者：
Canfield, RL;Henderson, CR;Lanphear, BP
通讯作者：
Lanphear, BP
影响因子：
4.5
作者：
Ishwaran, H;Rao, JS
通讯作者：
Rao, JS