Contents
Academy · Concepts & Definitions · Reading a forest plot (guide)
Reading a Forest Plot: Two Common Misinterpretations of Marker Size and the Null Line
A video walkthrough of this guide is in preparation. This written version focuses on the two misinterpretations of forest plots that occur most frequently.
Beyond the basic anatomy of a forest plot, two specific misinterpretations recur most frequently: treating marker size as an indicator of effect importance rather than study weight, and treating a confidence interval that crosses the null line as evidence of ‘no effect’ rather than as non-significance at that stage.
Learning objectives
- The two most common misinterpretations of forest plots.
- Why these two errors occur, and what the plot encodes instead.
- How to check an interpretation of an unfamiliar plot against these two errors.
Common misconceptions
- “A large marker indicates a more important or more striking finding.” Marker size conventionally encodes the study’s statistical weight in the pooled analysis (generally related to sample size and precision), not the size or importance of its effect; a small, highly imprecise study may have a striking point estimate and a very small marker.
- “A confidence interval crossing the null line means that study found no effect.” It indicates that the result of that specific study, considered alone, is not statistically significant at the stated confidence level. The point estimate may still suggest a real effect; it is the uncertainty around the estimate, not the estimate itself, that includes the null value.
Misinterpretation of marker size
Per the Cochrane Handbook's description of forest plot conventions1, marker size reflects the study’s weight in the pooled meta-analysis — generally a function of sample size and the precision of its estimate — not how striking or important its result appears. A study with a large, conspicuous point estimate but a wide confidence interval (indicating low precision) will typically have a small marker, while a study with a modest estimate but high precision can have a large one.
Misinterpretation of confidence intervals crossing the null line
The null line sits at 1 for ratio measures (risk ratio, odds ratio) and 0 for difference measures. A study’s confidence-interval line crossing this value means that the study’s result alone does not reach statistical significance at the stated confidence level; it does not mean that the point estimate itself was null, nor that the study found “no evidence of effect” in a stronger sense. The point estimate can lie meaningfully away from the null value while the interval, reflecting genuine uncertainty, still touches it.
A check against both misinterpretations
When an unfamiliar forest plot is read, two questions should be deliberately separated: “how much weight does this study carry?” (read from marker size, not the size of the estimate) and “is this study’s result itself statistically significant?” (read from whether its interval crosses the null line, which is a statement about precision, not about the direction or existence of an effect).
Video walkthrough
A narrated video walking through several real forest plots and flagging these two specific misreadings as they appear is in production and will be added above once complete.
Key points
Key points
The two most common misinterpretations of forest plots are reading marker size as effect importance (it represents statistical weight) and reading a null-line crossing as ‘no effect’ (it indicates non-significance for that study). Keeping these two questions separate avoids both errors.
Practical application
Practical application
- Interpret marker size as an indicator of weight, independent of the apparent size of the point estimate. A striking estimate with a small marker still represents a low-weight, imprecise study.
- Treat a null-line crossing as a statement about statistical significance, not about the existence of an effect. The position of the point estimate should be assessed separately from whether the interval touches the null value.
- Apply the same two checks to the pooled diamond as well as to individual studies. The width of the diamond represents the confidence interval of the pooled estimate, which is interpreted in the same way.
Frequently asked questions
Yes — weight is generally a function of the precision of its estimate (related to, but not identical to, sample size alone), so two similarly sized studies can carry different weights depending on their variance.
Yes — this is a common and meaningful result of meta-analysis: pooling increases precision, so the combined estimate's interval can be narrower and avoid the null line even when individual studies' wider intervals touch it.
The general approach (point estimate, confidence interval, weighted marker, pooled diamond) is used across many meta-analytic fields, not only health research, though specific conventions can vary by discipline.
References
- Cochrane Handbook for Systematic Reviews of Interventions, Chapter 10: Analysing data and undertaking meta-analyses. read 10 October 2026. View Cochrane Handbook Chapter 10
Every source above is a peer-reviewed article, a publisher’s record of one, or a standard issued by the body that owns it. Each carries the date it was last read. Where a standard moves, this article is revised rather than left up with a note.
How to cite this article
Pick your referencing style and copy it. Your university or target journal may vary the punctuation — check its guide if it has one.
Pubrica Academy. (2026, October 10). Reading a Forest Plot: Two Common Misinterpretations of Marker Size and the Null Line. Pubrica. https://pubrica.com/academy/video-guides/reading-a-forest-plot-guide/
Pubrica Academy. “Reading a Forest Plot: Two Common Misinterpretations of Marker Size and the Null Line.” Pubrica, 10 Oct. 2026, pubrica.com/academy/video-guides/reading-a-forest-plot-guide/.
Pubrica Academy (2026) Reading a Forest Plot: Two Common Misinterpretations of Marker Size and the Null Line. Pubrica. Available at: https://pubrica.com/academy/video-guides/reading-a-forest-plot-guide/ (Accessed: 15 October 2026).
Pubrica Academy. “Reading a Forest Plot: Two Common Misinterpretations of Marker Size and the Null Line.” Pubrica. October 10, 2026. https://pubrica.com/academy/video-guides/reading-a-forest-plot-guide/
Pubrica Academy, ‘Reading a Forest Plot: Two Common Misinterpretations of Marker Size and the Null Line’ (Pubrica, 10 October 2026) <https://pubrica.com/academy/video-guides/reading-a-forest-plot-guide/> accessed 15 October 2026.
Pubrica Academy. Reading a Forest Plot: Two Common Misinterpretations of Marker Size and the Null Line. [Internet]. Pubrica; 2026 Oct 10 [cited 2026 Oct 15]. Available from: https://pubrica.com/academy/video-guides/reading-a-forest-plot-guide/
Pubrica Academy, “Reading a Forest Plot: Two Common Misinterpretations of Marker Size and the Null Line,” Pubrica, Oct. 10, 2026. [Online]. Available: https://pubrica.com/academy/video-guides/reading-a-forest-plot-guide/
@misc{reading_a_forest_plot_guide_2026,
author = {{Pubrica Academy}},
title = {Reading a Forest Plot: Two Common Misinterpretations of Marker Size and the Null Line},
howpublished = {Pubrica},
year = {2026},
month = {oct},
url = {https://pubrica.com/academy/video-guides/reading-a-forest-plot-guide/},
note = {Accessed: <span data-cite-acc="iso">2026-10-15</span>}
}This article is written to be learned from. Cite it if you are referring to what it says; if you are using the evidence behind it, cite the sources listed above instead.
Two-question check
This checklist can be applied to any unfamiliar forest plot.
For each study: what does the marker size say about weight (not effect size)? For each study: does the interval cross the null line (significance), separate from where the point estimate sits? For the diamond: read its width as the pooled confidence interval, not a study count or heterogeneity signal.
Pubrica AcademyWritten and maintained by Pubrica’s subject matter experts. Articles are revised when the underlying standards change, and each article states the date on which it was last reviewed.
How Pubrica can help
Pubrica prepares and explains forest plots for both the methods and discussion sections, ensuring that weight and significance are each represented and interpreted correctly.