MCAR, MAR, MNAR — what are these and why do they matter?
mediumAnswer
- Missing Completely At Random (MCAR): missingness independent of everything — dropping rows is unbiased.
- Missing At Random (MAR): missingness depends only on observed features — imputation with these features is unbiased.
- Missing Not At Random (MNAR): missingness depends on the unobserved value itself (e.g., high earners refuse to disclose income) — imputation from observed features is biased; you need external information or explicit modeling.
- Test empirically: does missingness correlate with observed features?
Check yourself — multiple choice
- They're all synonyms
- MCAR: random; MAR: depends on observed features (imputable); MNAR: depends on the missing value itself (biased)
- MNAR is easier to handle than MCAR
- Only MCAR affects predictions
MCAR = random; MAR = observed-dependent (imputable); MNAR = missing-dependent (biased without external info).
#missing-data#data-quality
Practise Supervised Learning
215 interview questions in this topic.
Related questions
- How do you handle class imbalance in a dataset?
- What is target leakage and how do you prevent it?
- How do decision trees handle missing values?
- How does gradient boosting handle missing values without imputation?
- You use stratified k-fold on a dataset with duplicate customer records — why is it wrong?
- How do you prevent leakage in target encoding?