What is alpha-spending in sequential testing?

hard

Answer

$Divide the total α (0.05) across scheduled interim looks so cumulative false-positive rate stays capped.$
$Pocock: uniform per look (conservative).$
$O'Brien-Fleming: tiny α early, most saved for the final look (encourages waiting).$
$Haybittle-Peto: small α at interims, α - 0.001 at final.$
$All maintain family-wise error at 0.05 across multiple looks — enables ethical stopping in clinical trials.$

Check yourself — multiple choice

Random
Split total α across interim looks (Pocock uniform / O'Brien-Fleming saved late / Haybittle-Peto) → cap cumulative FPR at 0.05
Same as Bonferroni
Not real

α-spending: split α across interim looks; Pocock / OBF / HP schedules.

#hypothesis-testing#ab-testing#multiple-testing

215 interview questions in this topic.