What imputation methods should you consider?
mediumAnswer
- (1) Drop rows: fine if MCAR and few missing.
- (2) Mean/median/mode imputation: baseline, distorts variance.
- (3) KNN imputation: uses similar rows' values.
- (4) Iterative (MICE) imputation: regress each missing column on the others, iterate.
- (5) Model-based (missForest, DL).
- (6) Multiple imputation: create m imputed datasets, fit model on each, combine (Rubin's rules) — captures imputation uncertainty.
- For high-stakes analysis, prefer MICE or multiple imputation.
Check yourself — multiple choice
- Drop everything
- Drop / mean-median / KNN / MICE / model-based / multiple imputation — prefer MICE or MI for high-stakes
- Only mean
- Impossible
Imputation: drop / mean / KNN / MICE / model / MI; MI captures uncertainty.
#eda
Practise Statistics Fundamentals
215 interview questions in this topic.