Proportion of 5000 simulations with B = 1000 bootstrap draws for each simulation where future subjects with covariates x0 are denied treatment 1 for a significant difference within subgroups (column 3), an ITE estimator greater than c (column 4) or a probability of at least 0.5 for the ITE estimator to be greater than c (column 5) with c = log (1.2). The last row shows the results for a prediction model that is derived from 1000 subjects per treatment with x1 = x2 = 0 instead of 100 while all the other settings remain unchanged.

Table 5: Proportion of 5000 simulations with B = 1000 bootstrap draws for each simulation where future subjects with covariates $x_{0}$ are denied treatment 1 for a significant difference within subgroups (column 3), an ITE estimator greater than c (column 4) or a probability of at least 0.5 for the ITE estimator to be greater than c (column 5) with c = log (1.2). The last row shows the results for a prediction model that is derived from 1000 subjects per treatment with $x_{1}$ = $x_{2}$ = 0 instead of 100 while all the other settings remain unchanged.

$x_{01}$	$x_{02}$	$\Pr [sig diff]$	$\Pr [\hat{D} (x_{0}) \geq c]$	$\Pr [{\hat{P}}^{*} (x_{0}, c) \geq 0 .5]$
1	1	0.3184	0.8072	0.8068
1	0	0.1498	0.630	0.6304
0	1	0.0912	0.4924	0.4894
0	0	0.0692	0.3714	0.3652
0	0	0.0958	0.1864	0.1872