= Bootstrap-t confidence interval
{title2=$[\widehat\theta-q_{.975}\widehat s,\widehat\theta-q_{.025}\widehat s]$}
= Studentized bootstrap confidence interval
{synonym}
For each <bootstrap sample>, form $T^*=(\widehat\theta^*-\widehat\theta)/\widehat s^*$, using that sample's estimated <standard error>, possibly from a nested bootstrap. If $q_p$ are conditional quantiles of $T^*$ and $\widehat s$ is the original estimated standard error, invert the studentized inequalities to obtain the displayed interval. The quantile order is reversed by subtraction. Its coverage is approximate and requires a nondegenerate statistic and suitable bootstrap regularity.
Back to article page
