Meta-analysis combines and statistically evaluates data from different, yet similar studies. It is a useful tool to employ when individual studies lack substantial power, show conflicting results, or when a more precise estimate of the treatment effect is required. Results are typically shown in a forest plot, which includes the results of each study and the calculated overall effect. To ensure robust conclusions, the included studies should be similar, i.e., should only display an acceptable level of heterogeneity, which must be statistically evaluated. In case of high heterogeneity, further analyses, such as subgroup analyses or meta-regression, can help explain the reason. Another concern is publication bias, the selective non-publication of negative or inconclusive studies. It can be evaluated using the so-called funnel plot and quantified with methods like “trim-and-fill.” A special type of meta-analysis, called network meta-analysis, can compare treatments indirectly when head-to-head trials are lacking. Instead of a single effect size, results from network meta-analysis are often presented as a ranking of treatments or in tables presenting the relative effectiveness between different treatments.