论文标题
一种放松方法，以选择线性混合效应模型的选择
A Relaxation Approach to Feature Selection for Linear Mixed Effects Models
论文作者
论文摘要
线性混合效应（LME）模型是建模相关数据的基本工具，包括队列研究，纵向数据分析和荟萃分析。对于线性回归而言，LME的可变选择方法的设计和分析更加困难，因为LME模型是非线性的。在这项工作中，我们提出了一种放松策略和优化方法，该方法可以使用凸和非convex正规机构，包括$ \ ell_1 $，Adaptive-$ \ ell_1 $，cad和$ \ ell_0 $。该计算框架仅需要每个正常器的近端运算符，并且该实现可在开源Python软件包PYSR3中可用，该软件包PYSR3与Sklearn标准一致。模拟数据集的数值结果表明，所提出的策略在准确性和计算时间都改善了最新技术的状态。使用有关欺凌受害的数据集，在真实示例上还验证了变量选择技术。
Linear Mixed-Effects (LME) models are a fundamental tool for modeling correlated data, including cohort studies, longitudinal data analysis, and meta-analysis. Design and analysis of variable selection methods for LMEs is more difficult than for linear regression because LME models are nonlinear. In this work we propose a relaxation strategy and optimization methods that enable a wide range of variable selection methods for LMEs using both convex and nonconvex regularizers, including $\ell_1$, Adaptive-$\ell_1$, CAD, and $\ell_0$. The computational framework only requires the proximal operator for each regularizer to be available, and the implementation is available in an open source python package pysr3, consistent with the sklearn standard. The numerical results on simulated data sets indicate that the proposed strategy improves on the state of the art for both accuracy and compute time. The variable selection techniques are also validated on a real example using a data set on bullying victimization.
