TABLE 2.

Configuration of the simulated scenarios: We considered two total sample sizes for the meta‐analysis, $N=20$, and $N=30$, and four percentages of the number of biased studies, 0%, 10%, 30%, and 50%. For each percentage, we consider different distributions of biased studies: mild, large, and extreme bias.

$N$	% Bias	Biased studies	Mild	Large	Extreme
20	0%	0	0	0	0
	10%	2	0	1	1
	30%	6	2	2	2
	50%	10	3	3	4
30	0%	0	0	0	0
	10%	3	1	1	1
	30%	9	3	3	3
	50%	15	5	5	5