cuped

A Python package for the statistical analysis of A/B tests

因果推理&AB实验相关论文小书库

Causalis - State-of-the-art robust causal inference for experiments and observational data in python

Theory and implementatuon of various A/B experiments

AB testing, stattests, poisson bootstrap, cuped, linearization

A/B testing statistics, design, increasing sensitivity, multiple experiments comparison, traffic splitting and full A/B testing pipeline in Python

Воспроизводимые эксперименты по снижению дисперсии оценки эффекта: plain diff, CUPED, VWE и их комбинация.

896 tests / 42 scripts validating Zetyra calculators (GSD, CUPED, Bayesian, SSR incl. Single-Arm, RAR, Master Protocol). Replicates 8 published trials (Salk, DAPA-HF, PACIFIC, MONALEESA-7, I-SPY 2, STAMPEDE, REMAP-CAP, NCT03377023) + Leyrat 2024.

A/B testing engine with always-valid sequential inference (mSPRT) — peek continuously without inflating false positives. CUPED variance reduction, SRM detection, guardrails. FastAPI + React.

A/B testing engine: frequentist + Bayesian + CUPED variance reduction + peeking-safe sequential testing

Тыкаюсь в темах интенсива A/B-week от ШАДа

A Python package for the full A/B test lifecycle, from power analysis to sequential monitoring and variance reduction

End-to-end A/B experimentation toolkit: experiment readouts, MDE & power calculations, CUPED variance reduction, and decision-focused reporting in a Big Tech economist style.

An end-to-end A/B testing program review: 6 experiments, 2 ships, and the decision-quality framework behind them

Experimentation framework for synthetic accounting data with seven statistical designs, reproducible assignments, causal analysis, guardrails, power checks, and decision reporting.

Hands-on sports product experimentation lab for SRM, guardrails, novelty, Simpson's paradox and CUPED

Local-first experimentation and causal decision platform for A/B testing, CUPED, trust checks, segment-aware rollout policy, and simulation-driven validation.

A/B testing framework with power analysis, SRM diagnostics, CUPED variance reduction, and BH-corrected segment analysis

Anytime-valid A/B test analyzer that holds the false-positive rate under 1.5% while you peek at the dashboard continuously, where naive fixed-horizon testing leaks to 23% at 15 looks. mSPRT with confidence sequences, CUPED variance reduction (50% on the demo, SE 0.223 to 0.135), a peeking guard, and a reproducible A/A simulation.

End-to-end A/B testing framework — power analysis, SRM checks, CUPED variance reduction, BH-corrected segment breakouts, and an auto-generated ship/no-ship decision doc. Built on a 60k-user synthetic checkout experiment.