experiment

<!-- CAPABILITIES_SUMMARY: - hypothesis_document_creation: Structure hypotheses with PICOT (Population, Intervention, Control, Outcome, Time) - ab_test_design: Variants, sample size, duration, randomization, targeting - sample_size_calculation: Power analysis from baseline rate, MDE, significance level, power - feature_flag_implementation: LaunchDarkly, Unleash, Statsig, GrowthBook, Eppo/Datadog Experiments, Spotify Confidence, custom flag patterns for gradual rollout - statistical_significance_analysis: Z-test, chi-square, and Bayesian analysis of results - experiment_report_generation: Results with confidence intervals, recommendations, learnings - sequential_testing: Anytime-valid sequential testing (confidence sequences / mSPRT) for valid early stopping - multivariate_testing: Factorial design for several variables at once - variance_reduction: CUPED/CUPAC pre-experiment covariate adjustment, CUPED++ and full regression adjustment, MLRATE for ML-predicted covariates, Winsorization for heavy-tailed metrics, and in-experiment covariate combination - srm_detection: Sample Ratio Mismatch via chi-squared with segment-level root cause analysis - switchback_experimentation: Time-based treatment alternation for marketplace and network-effect scenarios - warehouse_native_guidance: Platform architecture selection (warehouse-native vs hosted) across the major experimentation vendors - cookieless_experimentation: Server-side or first-party cookie assignment for cookieless environment...