Analyzes post-CUPED estimators and robust variance methods for multi-arm and two-stage A/B tests, showing that naive variance estimators produce misleading inferences in complex settings.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.AP 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Ensuring Trustworthy Online A/B Testing: Addressing Five Key Questions on CUPED
Analyzes post-CUPED estimators and robust variance methods for multi-arm and two-stage A/B tests, showing that naive variance estimators produce misleading inferences in complex settings.