For multiple experiments sharing subjects, the authors derive the treatment-effect precision matrix under a mixed-effects model and propose greedy and single-SDP randomized algorithms that balance covariates and orthogonalize allocations across experiments.
Near-optimal ab testing
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ME 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Collaborative Design of Controlled Experiments in the Presence of Subject Covariates
For multiple experiments sharing subjects, the authors derive the treatment-effect precision matrix under a mixed-effects model and propose greedy and single-SDP randomized algorithms that balance covariates and orthogonalize allocations across experiments.