abtest-scientist

What problem does it solve?

Guides teams to design rigorous experiments and causal analyses to obtain reliable, actionable results and avoid underpowered or biased conclusions.

Core Features & Use Cases

• Sample size and power calculations for two-arm and multi-arm experiments, with guidance for both frequentist and Bayesian analyses.
• Implementation of multiple testing corrections (Bonferroni, Benjamini-Hochberg) to control false discoveries.
• Causal inference methods such as Difference-in-Differences, synthetic control, and regression discontinuity for observational data.
• Decision support on practical significance versus statistical significance for product decisions.

Quick Start

Run a sample size calculation for a two-arm experiment and report the required sample size, power, and detectable effect in plain language.