Fig. 7

Extension 1 results (continuous outcome, multiple covariates, no interaction) for sample size 50. The performance of analytic methods in terms of bias, coverage and power are shown when there are 3 covariates, 17 covariates and 17 covariates plus 4 noise variables. The effect of treatment is 40. Model-based standard errors are shown in black and empirical standard errors are shown in red. Estimates are shown with \(\pm 1.96 \times\) Monte Carlo standard error bars. Note: the error bars are too small to be seen for power, due to the scale of the plots. * AIPTW and IPTW have convergence issues when there are a high number of predictors; see Table S1 in Additional file 1 for more details