Lesson 6 of 6 · 13 min
Bootstrap resampling
Bootstrapping treats the observed sample as if it were the population and resamples it, with replacement, to build distributions and to run simulations from real data.
In short
- Resampling repeatedly draws samples from the observed data; the bootstrap is the most popular resampling method.
- Each bootstrap resample has the same size n as the original sample and is drawn with replacement: some observations repeat, others are left out.
- The statistic computed on each resample builds a bootstrap sampling distribution, used for inference without an analytical formula such as a z- or t-statistic.
- In a simulation, the bootstrap draws random values from the empirical (historical) distribution instead of a specified distribution. Every other step matches Monte Carlo.
- The time grid must match the periodicity of the observed data.
- Strength: simple, with no assumed distribution. Weakness: only statistical estimates, and only as good as the sample.
Unlock this lesson free for 7 days
Create a free account to get 7 days of full access — every lesson, video, flashcard, mock and the question bank. No card needed.