OLS regression for A/B tests can be run on k-anonymized aggregate data (counts and sums) and return the same coefficients, enabling privacy-preserving interaction tests and CUPED adjustment.
Privacy by design: The 7 foundational principles, 2009
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.AP 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
K-Anonymous A/B Testing
OLS regression for A/B tests can be run on k-anonymized aggregate data (counts and sums) and return the same coefficients, enabling privacy-preserving interaction tests and CUPED adjustment.