Quant Memo
Statistics/●●●●●

Blocking on a strong predictor to sharpen your test

Your experiment's outcome varies enormously by country: users in some regions spend far more than others. You worry that a simple coin-flip randomization might, by chance, put more high-spend regions in one arm, adding noise to the comparison.

Explain how stratification (blocking) and post-stratification / covariate adjustment reduce variance, and why they don't bias the effect.

Your answer

This one is open-ended. Work it through, then check your reasoning against the full solution.

More Statistics questions