.png){kind=icon}
.png){kind=icon}
Return
Practicing Meta-Analytics with Rectification
.png){kind=icon}
OA
AI
DOI：10.3390/publications13010002.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This article demonstrates the necessity of assessing homogeneity in meta-analyses using the Higgins method. The researchers realize the importance of assessing homogeneity in meta-analytic work. However, a significant issue with the Higgins method has been identified. In this article, we explain the nature of this problem and propose solutions to address it. Our narrative in this article is to point out the problem, analyze it, and present it well. A prerequisite to check the consistency of findings in comparable studies in meta-analyses is that the studies should be homogeneous, not heterogeneous. The Higgins I2 score, a version of the Cochran Q value, is commonly used to assess heterogeneity. The Higgins score is an improvement in the Q value. However, there is a problem with Higgins score statistically. The Higgins score is supposed to follow a Chi-squared distribution, but it does not do so because the Chi-squared distribution becomes invalid once the Q score is less than the degrees of freedom. This problem was recently rectified using an alternative method (S2 score). Using this method, we examined 14 published articles representing 133 datasets and observed that many studies declared homogeneous by the Higgins method were, in fact, heterogeneous. This article urges the research community to be cautious in making inferences using the Higgins method.
Keywords:
homogeneity
Cochran's Q score
H(2) score
Higgin I(2) score
S(2) score
systematic reviews
meta-analytics
Journal
IF:
2.5
Papers:
231
Citations:
1.2K