Hi
Regarding Tang's regression to assess publication bias in a meta analysis, the original article states:
"we suggest here an N-based linear regression in which the product (E) of the effect and the square root of the average number of subjects in the two compared groups of the trial (n) is regressed against the latter (regression equation: E=a+b x sqrt(n))."
Article Misleading funnel plot for detection of bias in meta-analysis
Then, why all articles referencing this one declare that it is a regression between the effect size and the inverse of sqrt(n)?. Have I misinterpreted the original sentence?
Many thanks
Can you show me the Tang reference you are referring to? And one of the interpretations of this as regressing on inverse sqrt(n)? I do not have easy access to all articles, since i work for industry.
Hi
yes, this is the reference:
Tang J-L, Liu JLY. Misleading funnel plot for detection of bias in meta-analysis. J Clin Epidemiol. 2000;53(5):477–84. doi: 10.1016/S0895-4356(99)00204-8.
PMID: 10812319
and one of the interpretations, for example here:
Lifeng Lin. Empirical Comparison of Publication Bias Tests in Meta-Analysis. J Gen Intern Med. 2018 Aug; 33(8): 1260–1267.
Published online 2018 Apr 16. doi: 10.1007/s11606-018-4425-7.
PMID: 29663281
"Tang and Liu13 used the inverse of the square root of study-specific sample size as the regression independent variable", referring to the first reference I posted.
- Badges
- Science method
- Similar topics
- Mathematics
- Statistics
- Statistical Techniques
- Meta-Analysis