Bayesian Reanalyses From Summary Statistics: A Guide for Academic Consumers
Bayesian Reanalyses From Summary Statistics: A Guide for Academic Consumers
复制标题
DOI：
10.1177/2515245918779348
复制
发表时间：
2018-09-01
影响因子：
13.6
通讯作者：
Wagenmakers, Eric-Jan
中科院分区：
文献类型：
--
作者：
Ly, Alexander;Raj, Akash;Wagenmakers, Eric-Jan
在整个社会科学领域，研究人员绝大多数都使用经典的统计范式从数据中得出结论，通常主要集中在一个数字上：近年来，然而，人们对另一种统计范式的兴趣激增：贝叶斯推理，其中概率与参数和模型有关。我们认为这是翔实的，提供统计结论，超越一个单一的数字，和-不管一个人的统计偏好-它可以是谨慎的报告结果从经典和贝叶斯范式。为了促进一个更具包容性和洞察力的方法来统计推断，我们展示了开源软件程序JASP（https：//www.example.com）中的汇总统计模块如何jasp-stats.org从一些常见的汇总统计数据中提供全面的贝叶斯重新分析，例如t和N。和检验者-（a）使用贝叶斯因子在连续尺度上量化证据，（B）评估证据对先验分布变化的稳健性，（c）通过检验效应量的后验分布来衡量哪些后验参数范围比其他参数范围更可信。使用Festinger和Carlsmith（1959）关于认知失调的开创性研究来说明该过程。
Across the social sciences, researchers have overwhelmingly used the classical statistical paradigm to draw conclusions from data, often focusing heavily on a single number: p. Recent years, however, have witnessed a surge of interest in an alternative statistical paradigm: Bayesian inference, in which probabilities are attached to parameters and models. We feel it is informative to provide statistical conclusions that go beyond a single number, and-regardless of one's statistical preference-it can be prudent to report the results from both the classical and the Bayesian paradigms. In order to promote a more inclusive and insightful approach to statistical inference, we show how the Summary Stats module in the open-source software program JASP (https://jasp-stats.org) can provide comprehensive Bayesian reanalyses from just a few commonly reported summary statistics, such as t and N These Bayesian reanalyses allow researchers-and also editors, reviewers, readers, and reporters-to (a) quantify evidence on a continuous scale using Bayes factors, (b) assess the robustness of that evidence to changes in the prior distribution, and (c) gauge which posterior parameter ranges are more credible than others by examining the posterior distribution of the effect size. The procedure is illustrated using Festinger and Carlsmith's (1959) seminal study on cognitive dissonance.