Publication Bias in Three-Armed Trials with Placebo and No-Treatment Groups
Author Information
Author(s): Koog Yun Hyung, We Seo Ryang, Min Byung-Il
Primary Institution: Honam Research Center, Medifarm Hospital, Suncheon, Republic of Korea
Hypothesis
Are three-armed trials with placebo and no-treatment groups subject to publication bias?
Conclusion
Three-armed trials necessary for estimating the placebo effect may be subject to publication bias.
Supporting Evidence
- Small trials showed more benefits than large trials in acupuncture and acupoint stimulation.
- The treatment effect in acupuncture and acupoint stimulation may be subject to publication bias.
- Placebo effects showed no significant differences between large and small trials.
Takeaway
This study looked at trials that tested treatments with placebos and found that smaller trials often showed better results than larger ones, which might be because the smaller ones are more likely to be published.
Methodology
The study analyzed three-armed randomized trials of acupuncture, acupoint stimulation, and transcutaneous electrical stimulation from electronic databases.
Potential Biases
Publication bias may distort the results of meta-analyses based solely on identified trials.
Limitations
The study may have missed some relevant trials and did not search public trial registries.
Participant Demographics
The trials included a total of 3060 patients in the active treatment group, 2576 in the placebo group, and 2533 in the no-treatment group.
Statistical Information
P-Value
0.009 for acupuncture, 0.0005 for acupoint stimulation
Confidence Interval
95% CI for treatment effect sizes ranged from 0.24 to 0.58 for acupuncture.
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website