ABSTRACT

Mixed effects regression models are widely used by language researchers. However, these regressions are implemented with an algorithm which may not converge on a solution. While convergence issues in linear mixed effects models can often be addressed with careful experiment design and model building, logistic mixed effects models introduce the possibility of separation or quasi-separation, which can cause problems for model estimation that result in convergence errors or in unreasonable model estimates. These problems cannot be solved by experiment or model design. In this paper, we discuss (quasi-)separation with the language researcher in mind, explaining what it is, how it causes problems for model estimation, and why it can be expected in linguistic datasets. Using real-linguistic datasets, we then show how Bayesian models can be used to overcome convergence issues introduced by quasi-separation, whereas frequentist approaches fail. On the basis of these demonstrations, we advocate for the adoption of Bayesian models as a practical solution to dealing with convergence issues when modeling binary linguistic data.

摘要

语言研究人员广泛使用混合效果回归模型。但是，这些回归是通过无法收敛于解决方案的算法实现的。虽然通常可以通过仔细的实验​​设计和模型构建来解决线性混合效应模型中的收敛问题，但逻辑混合效应模型会引入分离或准分离的可能性，这可能会导致模型估计出现问题，从而导致收敛误差或模型不合理估计。这些问题无法通过实验或模型设计解决。在本文中，我们将与语言研究者一起讨论（准）分离，解释其含义，它如何引起模型估计问题以及为什么在语言数据集中会出现这种情况。使用真实语言数据集 然后，我们展示了如何使用贝叶斯模型来克服由准分离引起的收敛问题，而频繁性方法却失败了。在这些演示的基础上，我们提倡采用贝叶斯模型作为对二进制语言数据建模时解决收敛问题的实用解决方案。