Statistics in the Service of Science: Don’t Let the Tail Wag the Dog

Statistics in the Service of Science: Don’t Let the Tail Wag the Dog
复制标题

统计为科学服务:不要让尾巴摇狗

DOI:
10.1007/s42113-022-00129-2
复制
发表时间:
2023
期刊:
Computational Brain & Behavior
影响因子:
--
通讯作者:
Navarro, Danielle J.
Navarro, Danielle J.
中科院分区:
--
文献类型:
--
作者:
Singmann, Henrik;Kellen, David;Cox, Gregory E.;Chandramouli, Suyog H.;Davis-Stober, Clintin P.;Dunn, John C.;Gronau, Quentin F.;Kalish, Michael L.;McMullin, Sara D.;Navarro, Danielle J.

文献摘要

参考文献

被引文献

相似文献

统计建模通常是为了描述数据中的模式,为更广泛的科学目标服务,即开发理论来解释这些模式。当建立模型时,统计模型支持有意义的推断,以便使模型的参数与潜在的因果机制以及它们在数据中的表现方式相一致。相反,当统计模型基于默认选择的假设时,做出推论的尝试可能没有信息,甚至是自相矛盾的--本质上,尾巴是在试图摇摆狗。Van Doorn等人对这些问题进行了说明。在使用贝叶斯因子来确定线性混合模型中的影响和交互作用的背景下。我们表明,在它们的应用中发现的问题(以及这里确定的其他问题)可以通过使用先验而不是标准化标度上的默认先验来绕过。这一案例研究表明,为了支持有意义的推论,研究人员必须直接处理一些实质性问题,其中我们强调两个:第一个是协调问题,这要求研究人员具体说明模型假设的理论结构在功能上如何与可观察变量相关。第二个问题是泛化问题,这要求研究人员考虑一个模型如何表示在相似但不相同的情况下共享的理论构造,以及像贝叶斯因子这样的模型比较度量不直接解决这种形式的泛化的事实。为了使统计建模服务于科学目标,模型不能基于默认假设,而应基于对其协调功能的理解,以及它们如何表示可推广到其他相关情景的因果机制。
Statistical modeling is generally meant to describe patterns in data in service of the broader scientific goal of developing theories to explain those patterns. Statistical models support meaningful inferences when models are built so as to align parameters of the model with potential causal mechanisms and how they manifest in data. When statistical models are instead based on assumptions chosen by default, attempts to draw inferences can be uninformative or even paradoxical—in essence, the tail is trying to wag the dog. These issues are illustrated by van Doorn et al. in the context of using Bayes Factors to identify effects and interactions in linear mixed models. We show that the problems identified in their applications (along with other problems identified here) can be circumvented by using priors over inherently meaningful units instead of default priors on standardized scales. This case study illustrates how researchers must directly engage with a number of substantive issues in order to support meaningful inferences, of which we highlight two: The first is the problem ofcoordination, which requires a researcher to specify how the theoretical constructs postulated by a model are functionally related to observable variables. The second is the problem ofgeneralization, which requires a researcher to consider how a model may represent theoretical constructs shared across similar but non-identical situations, along with the fact that model comparison metrics like Bayes Factors do not directly address this form of generalization. For statistical modeling to serve the goals of science, models cannot be based on default assumptions, but should instead be based on an understanding of their coordination function and on how they represent causal mechanisms that may be expected to generalize to other related scenarios.
DOI: 10.1037/h0042040
发表时间: 1960-01-01
影响因子: 22.4
作者:
ROZEBOOM, WW
通讯作者: ROZEBOOM, WW
测试词典半序作为决策模型:优先支配性、集成、交互和传递性
DOI: 10.1016/j.jmp.2010.03.002
发表时间: 2010
影响因子: 1.8
作者:
M. Birnbaum
通讯作者: M. Birnbaum
DOI: 10.1017/9781107286184
发表时间: 2018-01-01
期刊: STATISTICAL INFERENCE AS SEVERE TESTING: HOW TO GET BEYOND THE STATISTICS WARS
影响因子: --
作者:
Mayo, D. G.
通讯作者: Mayo, D. G.
如果数学心理学不存在,我们可能需要发明它:对心理学理论构建的评论
DOI: --
发表时间: 2021
影响因子: 12.6
作者:
D. Navarro
通讯作者: D. Navarro
心理科学的模型层次结构
DOI: --
发表时间: 2019
期刊: Computational Brain & Behavior
影响因子: --
作者:
David Kellen
通讯作者: David Kellen