Recalibrating expectations about effect size: A multi-method survey of effect sizes in the ABCD study.
Recalibrating expectations about effect size: A multi-method survey of effect sizes in the ABCD study.
复制标题
DOI：
10.1371/journal.pone.0257535
复制
发表时间：
2021
期刊：
影响因子：
3.7
通讯作者：
Garavan H
中科院分区：
文献类型：
--
作者：
Owens MM;Potter A;Hyatt CS;Albaugh M;Thompson WK;Jernigan T;Yuan D;Hahn S;Allgaier N;Garavan H
效应大小通常使用科恩建立的启发式方法来解释(例如，小的：r=.1，中等的r=0.3，大的r=0.5)，尽管越来越多的证据表明，这些指南被错误地校准为心理学研究中通常发现的效果。这项研究的目的是1)描述效应大小在多个工具上的分布，2)考虑影响效应大小分布的因素，3)确定各种效应大小的基准。对于第一个目的，从9/10岁儿童的大的、不同的样本中展示了效应大小分布。这是通过在161个变量之间进行皮尔逊相关性来完成的，这些变量代表了来自青少年大脑和认知发展研究®基线数据的所有问卷和任务的结构。为了达到目标二，通过比较目标一分析的不同修正的效应大小的分布，检验了符合这种分布的因素。这些改进的分析策略包括比较不同类型变量的效应大小分布，使用统计阈值进行分析，以及使用几种协变量策略进行分析。在Aim One分析中，样本内效应大小的中位数为0.03，第一和第三四分位数的值为0.01和0.07。在Aim两项分析中，跨工具、内容领域和记者之间的关联的影响较小，而社会人口因素的影响也较小。当阈值达到统计学意义时，效应大小较大。在旨在模拟ABCD数据的“真实世界”分析中使用的条件的分析中，样本内效应大小的中位数为0.05，第一和第三四分位数的值为0.03和0.09。为了实现目标三，ABCD数据集中报告了不同效果大小的例子，作为该数据集中今后工作的基准。总而言之，这份报告发现，在一个非常大的数据集上，根据经验确定的效应大小比基于现有启发式的预期要小。
Effect sizes are commonly interpreted using heuristics established by Cohen (e.g., small: r = .1, medium r = .3, large r = .5), despite mounting evidence that these guidelines are mis-calibrated to the effects typically found in psychological research. This study’s aims were to 1) describe the distribution of effect sizes across multiple instruments, 2) consider factors qualifying the effect size distribution, and 3) identify examples as benchmarks for various effect sizes. For aim one, effect size distributions were illustrated from a large, diverse sample of 9/10-year-old children. This was done by conducting Pearson’s correlations among 161 variables representing constructs from all questionnaires and tasks from the Adolescent Brain and Cognitive Development Study® baseline data. To achieve aim two, factors qualifying this distribution were tested by comparing the distributions of effect size among various modifications of the aim one analyses. These modified analytic strategies included comparisons of effect size distributions for different types of variables, for analyses using statistical thresholds, and for analyses using several covariate strategies. In aim one analyses, the median in-sample effect size was .03, and values at the first and third quartiles were .01 and .07. In aim two analyses, effects were smaller for associations across instruments, content domains, and reporters, as well as when covarying for sociodemographic factors. Effect sizes were larger when thresholding for statistical significance. In analyses intended to mimic conditions used in “real-world” analysis of ABCD data, the median in-sample effect size was .05, and values at the first and third quartiles were .03 and .09. To achieve aim three, examples for varying effect sizes are reported from the ABCD dataset as benchmarks for future work in the dataset. In summary, this report finds that empirically determined effect sizes from a notably large dataset are smaller than would be expected based on existing heuristics.
登录
查看更多内容
影响因子：
3.7
作者：
Kuehberger, Anton;Fritz, Astrid;Scherndl, Thomas
通讯作者：
Scherndl, Thomas
影响因子：
7
作者：
Kelley, Ken;Preacher, Kristopher J.
通讯作者：
Preacher, Kristopher J.
影响因子：
1.3
作者：
Achenbach, T M;Ruffle, T M
通讯作者：
Ruffle, T M
DOI：
10.1111/j.2517-6161.1995.tb02031.x
发表时间：
1995-01-01
影响因子：
5.8
作者：
BENJAMINI, Y;HOCHBERG, Y
通讯作者：
HOCHBERG, Y
影响因子：
56.9
作者：
ENGEL, GL
通讯作者：
ENGEL, GL