Glossary
Bootstrap
A method that estimates how much a statistic varies by resampling the data itself, with replacement, many times.
To bootstrap a statistic, draw n observations with replacement from a sample of n, compute the statistic, and repeat thousands of times. The spread of the results is its standard error; their 2.5th and 97.5th percentiles give a 95% interval.
The plain version assumes independence. For time series with dependence, the block bootstrap resamples runs of consecutive observations.
Example: for 20 daily returns with a standard deviation of 1.404%, the exact bootstrap standard error of the mean is 1.404% x sqrt(19 / 20) / sqrt(20), which is 0.306%.