funnel plot

funnel plot

a graphic method of detecting publication bias. The estimate of risk derived from a set of epidemiologic studies used in a metaanalysis is plotted against sample size. If there is no publication bias, the plot is funnel-shaped; if studies giving significant results are more likely to be published than negative studies, the plot is asymmetric.
See also: metaanalysis.
A scatterplot of treatment effect against a measure of study size used primarily as a visual aid for detecting bias or systematic heterogeneity. A symmetric inverted funnel shape is seen in ‘well-behaved’ data for which publication bias is unlikely and which is thus suited for inclusion in a meta-analysis. An asymmetric funnel indicates a relationship between treatment effect and study size, due either to publication bias or a systematic difference between smaller and larger studies—‘small study effects’

fun·nel plot

(fŭn'ĕl plot)
A graphic method of detecting publication bias. The estimate of risk derived from a set of epidemiologic studies used in a metaanalysis is plotted against sample size. If there is no publication bias, the plot is funnel shaped; if studies giving significant results are more likely to be published than negative studies, the plot is asymmetric.
See also: metaanalysis
References in periodicals archive ?
2011 1.90 [1.05, 3.42] Total (95% CI) 1.29 [0.86, 1.94] Total events Heterogeneity: [r.sup.2] = 0.18; [chi square] = 50.25, df = 4 (P < 0.00001); [I.sup.2] = 92% Test for overall effect: Z = 1.23 (P = 0.22) FIGURE 3: Forest plot and funnel plot of overall colostomy rate.
The symmetry of the funnel plot was further evaluated by Egger's linear regression test.7 Statistical analysis was undertaken using the program STATA 11.0 software (Stata Corporation, Texas).
Publication bias of the included articles was assessed using Begg's funnel plot. The results of funnel plot showed that the shape of the funnel plot seemed symmetrical (Figure 4) and did not show an obvious publication bias for rs2856718 or rs7453920 polymorphism.
Publication bias is usually evaluated visually with a funnel plot, which is a simple scatter plot of the intervention effect estimates of individual studies against some measure of each study's size.
The existence of publication bias was initially checked by the graphical display of funnel plot and then test by the Egger's.13,14
Funnel plot and Egger's linear regression tests were conducted to evaluate potential publication bias.
Publication bias was assessed visually using a funnel plot and was tested formally by Egger's test, with p<0.10 indicating the presence of publication bias [13].
An interpretable funnel plot should be based on at least 10 studies (Sterne et al., 2011), applying only to five of the results in Table 2.