Skip to main content
. 2018 May 18;18:42. doi: 10.1186/s12874-018-0491-0

Fig. 5.

Fig. 5

Difference in treatment ES estimate between trials with presence and lack of “double-blinded” description. A positive value (more than zero) across meta-analyses indicates that trials not described as “double-blinded” inflate the treatment ES estimate when compared with trials described as “double blinded”. Diamond, difference in treatment ES estimate between trial components across all meta-analyses; square, proportional to weight used in meta-meta-analysis; horizontal arrow/line, a 95% confidence interval; solid vertical line, line of no difference in treatment ES estimate