Table 4.4 Common methods for quantitative synthesis

Meta-analysis

Aggregate data^a

Individual

participant data^c

Weighted average of effect estimates

Pairwise comparisons of effect estimates, CI

Overall effect estimate, CI, P value

Evaluation of heterogeneity

Forest plot^b with summary statistic for average effect estimate

Network^a

Variable^d

The interventions, which are compared directly versus indirectly

Network diagram or graph, tabular presentations

Comparisons of relative effects between any pair of interventions

Effect estimates for intervention pairings

Summary relative effects for pair-wise comparisons with evaluations of inconsistency and heterogeneity

Forest plot, other methods

Treatment rankings (ie, probability that an intervention is among the best options)

Rankogram plot

Synthesis without meta-analysis^e

Summarizing effect estimates from separate studies (without combination that would provide an average effect estimate)

Range and distribution of observed effects such as median, interquartile range, range

Box-and-whisker plot, bubble plot

Forest plot (without summary effect estimate)

Combining P values

Combined P value, number of studies

Albatross plot (study sample size against P values per outcome)

Vote counting by direction of effect (eg, favors intervention over the comparator)

Proportion of studies with an effect in the direction of interest, CI, P value

Harvest plot, effect direction plot