Evidence-appraisal glossary
Alpha-Spending Function
A rule that decides how much of a study's total false-positive budget (its alpha) may be spent at each interim look at the data. It lets a trial peek early without inflating the overall chance of a spurious result.
Also called: alpha spending, error-spending function.
Every time researchers test accumulating data, they risk a false positive, so repeated looks would erode the protection a single fixed alpha provides. An alpha-spending function parcels out small pieces of the total alpha across planned analyses, keeping the study-wide error rate at the intended level. Conservative shapes, such as O'Brien-Fleming style boundaries, spend very little early and reserve most alpha for the final look, so stopping early demands very strong evidence. It is the engine behind most group-sequential designs.
This is a plain-language methodology definition for reading research. It is general education, not medical advice.