p-value peeking and estimating extrema
This addresses a pervasive issue in statistical hypothesis testing for researchers and practitioners, but appears incremental as it builds on existing methods for handling peeking.
The paper tackled the problem of biased p-values due to data peeking in statistical hypothesis testing by developing mechanisms to estimate running extrema of test statistics, which address the effect of peeking in general scenarios.
A pervasive issue in statistical hypothesis testing is that the reported $p$-values are biased downward by data "peeking" -- the practice of reporting only progressively extreme values of the test statistic as more data samples are collected. We develop principled mechanisms to estimate such running extrema of test statistics, which directly address the effect of peeking in some general scenarios.