Bias correction for Cohen's d.

IF 1.9 4区心理学 Q2 PSYCHOLOGY, MULTIDISCIPLINARY

Journal of General Psychology Pub Date : 2024-01-01 Epub Date: 2023-02-15 DOI:10.1080/00221309.2023.2172545

Xiaofeng Steven Liu

引用次数: 0

Abstract

Cohen's d - a common effect size - contains a positive bias. The traditional bias correction, based on strict distribution assumption, does not always work for a small study with limited data. The non-parametric bootstrapping is not limited by distribution assumption and can be used to remove the bias in Cohen's d. A real example is included to illustrate the implementation of bootstrap bias estimation and the removal of sizable bias in Cohen's d.

查看原文本刊更多论文

Cohen's d 的偏差校正。

Cohen's d 是一种常见的效应大小，其中包含正偏差。基于严格分布假设的传统偏倚校正并不总是适用于数据有限的小型研究。非参数引导法不受分布假设的限制，可用于消除 Cohen's d 中的偏差。本研究中的一个实际例子说明了引导法偏差估计的实施以及消除 Cohen's d 中的显著偏差的方法。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Journal of General Psychology PSYCHOLOGY, MULTIDISCIPLINARY-

CiteScore

5.20

自引率

4.00%

发文量

期刊介绍： The Journal of General Psychology publishes human and animal research reflecting various methodological approaches in all areas of experimental psychology. It covers traditional topics such as physiological and comparative psychology, sensation, perception, learning, and motivation, as well as more diverse topics such as cognition, memory, language, aging, and substance abuse, or mathematical, statistical, methodological, and other theoretical investigations. The journal especially features studies that establish functional relationships, involve a series of integrated experiments, or contribute to the development of new theoretical insights or practical applications.