Comparing Bayesian Variable Selection to Lasso Approaches for Applications in Psychology.
Comparing Bayesian Variable Selection to Lasso Approaches for Applications in Psychology.
复制标题
DOI：
10.1007/s11336-023-09914-9
复制
发表时间：
2023-09
期刊：
影响因子：
3
通讯作者：
Rao, J. Sunil
中科院分区：
文献类型：
--
作者：
Bainter, Sierra A.;McCauley, Thomas G.;Fahmy, Mahmoud M.;Goodman, Zachary T.;Kupis, Lauren B.;Rao, J. Sunil
关键词：
在本文中，我们回顾了现有的解决心理学变量选择问题的工具。现代正则化方法，如套索回归最近被引入该领域，并被纳入流行的方法，如网络分析。然而，套索正则化的几个公认的局限性可能会限制其适用于心理学研究。在本文中，我们比较了用于变量选择的套索方法的属性贝叶斯变量选择方法。特别是，我们强调随机搜索变量选择（SSVS）的优势，使其非常适合在心理学中的变量选择应用。我们证明了这些优势，并在大样本预测抑郁症状的应用程序和相应的模拟研究中将SSVS与套索类型惩罚进行了对比。我们研究了样本量、效应量和预测因子之间的相关性模式对正确率和错误率的影响。包含和估计中的偏差。这里研究的SSVS在计算上是合理有效的，并且能够在小样本量中检测中等效应（或中等样本量中的小效应），同时防止错误包含，并且不会过度惩罚真实效应。我们推荐SSVS作为一个非常适合该领域的灵活框架，讨论限制，并为未来的发展提出建议。在线版本包含补充材料，可通过10.1007/s11336-023-09914-9获得。
In the current paper, we review existing tools for solving variable selection problems in psychology. Modern regularization methods such as lasso regression have recently been introduced in the field and are incorporated into popular methodologies, such as network analysis. However, several recognized limitations of lasso regularization may limit its suitability for psychological research. In this paper, we compare the properties of lasso approaches used for variable selection to Bayesian variable selection approaches. In particular we highlight advantages of stochastic search variable selection (SSVS), that make it well suited for variable selection applications in psychology. We demonstrate these advantages and contrast SSVS with lasso type penalization in an application to predict depression symptoms in a large sample and an accompanying simulation study. We investigate the effects of sample size, effect size, and patterns of correlation among predictors on rates of correct and false inclusion and bias in the estimates. SSVS as investigated here is reasonably computationally efficient and powerful to detect moderate effects in small sample sizes (or small effects in moderate sample sizes), while protecting against false inclusion and without over-penalizing true effects. We recommend SSVS as a flexible framework that is well-suited for the field, discuss limitations, and suggest directions for future development. The online version contains supplementary material available at 10.1007/s11336-023-09914-9.
登录
查看更多内容
影响因子：
11.3
作者：
Aaron RV;Snodgress MA;Blain SD;Park S
通讯作者：
Park S
影响因子：
2.8
作者：
Ammerman, Brooke A.;Jacobucci, Ross;McCloskey, Michael S.
通讯作者：
McCloskey, Michael S.
DOI：
10.1080/10705511.2019.1642754
发表时间：
2020
期刊：
Structural equation modeling : a multidisciplinary journal
影响因子：
--
作者：
Bauer DJ;Belzak WCM;Cole V
通讯作者：
Cole V
影响因子：
3.3
作者：
Babyak, MA
通讯作者：
Babyak, MA
影响因子：
3.6
作者：
Chen, Jing;Tan, Youguo;Lei, Wei
通讯作者：
Lei, Wei