Statistical Challenges in Online Controlled Experiments: A Review of A/B Testing Methodology

Provides a canonical overview or reference point for the relevant DoOperator research area.

A modern review of statistical methodology for online controlled experiments, including sensitivity, heterogeneity, long-term effects, optional stopping, and interference.

Use when orienting a new paper, blog post, benchmark, or research plan in this area.

Do not cite the overview as evidence that a specific method works in a specific deployment setting without checking the underlying primary paper.