The Living Thing / Notebooks :


Resampling your own data to estimate how good your estimator is, frequentist-style. Gets tricky for dependent data, and various other things.

For a handy crib sheet for bootstrap failure modes, see Thomas Lumley, When the bootstrap doesn’t work

Bootstrap bias correction

As opp variance estimation. When does this work? Need to understand that better.

Boostrap for dependent data

e.g., as presaged, time series.

“Wild bootstrap”

What is this even?


General refs