a Department of Educational Psychology , Texas A&M University.
Multivariate Behav Res. 2019 Jul-Aug;54(4):578-592. doi: 10.1080/00273171.2018.1552555. Epub 2019 Jan 15.
The multilevel logistic regression model (M-logit) is the standard model for modeling multilevel data with binary outcomes. However, many assumptions and restrictions should be considered when applying this model for unbiased estimation. To overcome these limitations, we proposed a multilevel CART (M-CART) algorithm which combines the M-logit and single level CART (S-CART) within the framework of the expectation-maximization. Simulation results showed that the proposed M-CART provided substantial improvements on classification accuracy, sensitivity, and specific over the M-logit, S-CART, and single level logistic regression model when modeling multilevel data with binary outcomes. This benefit of using M-CART was consistently found across different conditions of sample size, intra-class correlation, and when relationships between predictors and outcomes were nonlinear and nonadditive.
多层次逻辑回归模型（M-logit）是用于对二项结局的多层次数据进行建模的标准模型。然而，在进行无偏估计时，应考虑许多假设和限制。为了克服这些限制，我们提出了一种多层次 CART（M-CART）算法，该算法在期望最大化框架内将 M-logit 和单水平 CART（S-CART）相结合。模拟结果表明，当对二项结局的多层次数据进行建模时，与 M-logit、S-CART 和单水平逻辑回归模型相比，所提出的 M-CART 在分类准确性、敏感性和特异性方面都有显著提高。在不同的样本量、组内相关、预测变量和结果之间的关系是非线性和非加性的情况下，使用 M-CART 都能始终如一地获得这些益处。
