On this page
What this lesson covers
Bootstrapping estimates a statistic's variability without an explicit population-distribution model, while remaining dependent on the quality and range of the observed sample.
The lesson explains bootstrap standard errors, confidence intervals and adaptability across statistics. It also covers computation, sample bias, limited extrapolation and the loss of time dependence under independent resampling.
Key points
- Fat tails: A bootstrap keeps the fat tails and the skewness of the daily results, because every draw is one of the observed days.
- Bootstrapping: Bootstrapping avoids explicit distributional assumptions and uses only what the sample contains.
- Statistical robustness: Even from limited data, bootstrapping can give a reliable estimate of how much a statistic varies.
- Autocorrelated time series: Not ideal for autocorrelated time series, because random draws break the order of the data.
Common mistakes
- Expecting resampling to fix an unrepresentative sample is mistaken because resampling amplifies the flaw.
- Claiming that an independently resampled path preserves a run of turbulent days overlooks how resampling scatters those days at random.
- Expecting a bootstrap draw to fall outside the range of the observed data; no single draw can.
Try a practice question
Choose an answer, then check it to read the explanation for every option.
Continue studying in Quizara
In Quizara the lesson comes with more practice questions on the topic, explanations for every option and an AI tutor for your follow-up questions.
Written by the Quizara Editorial Team under our editorial standards.