Simulation-based Regularized Logistic Regression
Simulation-based Regularized Logistic Regression
复制标题
DOI：
10.1214/12-ba719
复制
发表时间：
2012-01-01
影响因子：
4.4
通讯作者：
Polson, Nicholas G.
中科院分区：
文献类型：
--
作者：
Gramacy, Robert B.;Polson, Nicholas G.
在本文中，我们开发了一个基于模拟的框架，正则化逻辑回归，利用两个新的结果，规模混合的法线。通过仔细选择一种类型的混合物的可能性的分层模型，并与另一个实施正则化，我们得到新的MCMC计划与不同的效率取决于数据类型（二进制与二项式，说）和所需的估计（最大似然，最大后验概率，后验均值）。我们的综合方法的优点包括灵活性，计算效率，p >> n设置中的适用性，不确定性估计，变量选择和评估最佳正则化程度。我们比较我们的方法，现代的替代品合成和真实的数据。CRAN上提供了一个名为reglogit的R包。
In this paper, we develop a simulation-based framework for regularized logistic regression, exploiting two novel results for scale mixtures of normals. By carefully choosing a hierarchical model for the likelihood by one type of mixture, and implementing regularization with another, we obtain new MCMC schemes with varying efficiency depending on the data type (binary v. binomial, say) and the desired estimator (maximum likelihood, maximum a posteriori, posterior mean). Advantages of our omnibus approach include flexibility, computational efficiency, applicability in p >> n settings, uncertainty estimates, variable selection, and assessing the optimal degree of regularization. We compare our methodology to modern alternatives on both synthetic and real data. An R package called reglogit is available on CRAN.