Fig. 4From: Comparison of Bayesian Networks, G-estimation and linear models to estimate causal treatment effects in aggregated N-of-1 trials with carry-over effectsOverview of the estimates of the treatment effect differences (y-axis), with a true value of 2 (broken red horizontal line), with standard error bars, across the four scenarios (1-4 displayed in order from top to bottom) with and without missing values, for different sample sizes on the x-axisBack to article page