Resampling returns without destroying their memory
Asked at Millennium
You want to bootstrap the distribution of a strategy's maximum drawdown from a series of daily returns that exhibit autocorrelation and volatility clustering.
Explain why the ordinary i.i.d. bootstrap is wrong here, how the block bootstrap fixes it, and how to choose the block length.
Your answer
This one is open-ended. Work it through, then check your reasoning against the full solution.