Extending the p-plot: Heuristics for multiple testing

In the problem of large-scale multiple testing the p-plot is a graphically based competitor to the notoriously weak Bonferroni method. The p-plot is l ess stringent and more revealing in that it gives a gauge of how many hypot heses are decidedly false. The method is elucidated and extended here: the bootstrap reveals bias and sampling error in the usual point estimates, a b ootstrap-based confidence interval for the gauge is given, as well as two a cceptably powerful blanket tests of significance. Guidelines far use are gi ven, and interpretational pitfalls pointed out, in the discussion of a case study linking premortem neuropsychological and postmortem neuropathologic data in an HIV cohort study.