How many bootstrap resamples do you need, and which statistics does it handle?
mediumAnswer
- Given data ,...,, sample n observations with replacement to form X*, compute the statistic θ̂*, repeat B ≈ 1000-10000 times to build an empirical distribution of θ̂.
- Use it to compute SEs, CIs, and bias.
- Works for any statistic , no distributional assumption.
- Weaknesses: bad for extreme statistics (max), heavy tails, small n, and violated i.i.d.
Check yourself — multiple choice
- Cross-validation
- Resample n with replacement B times → empirical distribution of θ̂ → SE / CI / bias; distribution-free but bad for max / heavy tails / tiny n
- Same as t-test
- Only parametric
Bootstrap: resample with replacement; empirical θ̂ distribution; distribution-free.
#bootstrap#confidence-interval#non-parametric
Practise Statistics Fundamentals
215 interview questions in this topic.