Data Analysis

This generates Python statistical analysis code and runs it through a structured 4-round review process to catch mathematical errors, data handling issues, and missing uncertainty measures. It's built for academic research where you need proper test selection, effect sizes, confidence intervals, and p-values that reviewers won't tear apart. The workflow enforces good practices like named sections in your code, appropriate test selection based on data type, and never reporting a point estimate without uncertainty. Comes with helper scripts for statistical summaries and p-value formatting. The multi-round review is the real value here, it systematically checks things you'd otherwise catch only after running the analysis and realizing your t-test assumptions were violated.