Summary
The episode works through five questions that students commonly find difficult in evidence synthesis. It considers why systematic reviews sit at the top of the evidence pyramid, how Boolean operators change the size of a search, and why a well-reported review can still receive a critically low AMSTAR 2 rating. The hosts work through inverse-variance pooling, a leave-one-out check, Cochran's Q and I squared with three hypothetical trials, and show that I squared depends on study precision as well as on disagreement between studies. The episode closes with a discussion of when the random-effects model can amplify small-study bias, using the intravenous magnesium trials as a real example.