What is a sample ratio mismatch (SRM) alert?
hardAnswer
- Actual traffic split (e.g., 51/49) differs significantly from designed (50/50).
- Chi-square test detects.
- Root causes: (1) buggy randomization / hashing.
- (2) selection bias (bot filtering asymmetric).
- (3) redirect skew (mobile vs desktop).
- (4) load imbalance (one variant fails silently, users bounce back).
- SRM invalidates the whole test — never analyze without fixing first.
- Standard automated check in any experimentation platform.
Check yourself — multiple choice
- Random
- Actual split differs from designed (chi-square test); causes: buggy random / bot filter / redirect / silent fail bounce; invalidates test — fix before analyzing; automated check
- Not real
- Just noise
SRM: split ratio bug; invalidates test; automated chi-square check.
#experimentation
Practise MLOps & Data Quality
215 interview questions in this topic.