Biology, images, analysis, design...
Use/Abuse Principles How To Related
"It has long been an axiom of mine that the little things are infinitely the most important" (Sherlock Holmes)

Search this site



Just a note

For instance if your estimator were positively biased, and you found 0.6 of your bootstrap statistics (*) exceed your sample statistic (), then the estimated bias of your bootstrap statistics is (b=) 0.253 standard normal deviates - compared to

In which case is, also, biased to a similar extent - compared to its true value ()

All of which would imply that, because they are quantiles of *, those percentile confidence limits need to be corrected by twice that bias (b+b = 2b).