Hello everyone,
My bootstrap was still at 1% after 24 hours, giving me an ETA of 37 days. My bootstrap sample size is 200, and the population size is 120. I have already used a small sample size and a small number of patients to test the bootstrap and it works.
It takes a long time to fit the model (Estimation Time 2119.92), so I expect it to take a long time, but is there a way to speed it up?
Thanks in advance,
Athanasios
There can be significant variation between the bootstrap runs so it might be that some of them are quite a bit slower than the original run. Are any warnings printed? The easiest way to speed up a bootstrap is to run it on multiple nodes as a batch job, see VSCode extension · JuliaHub. Then you can run it on many nodes. You’d have to use EnsembleDistributed in the bootstrap settings as well, see Pumas Docstrings · Pumas.
I did not get any warnings during the run. I will try these solutions and let you know, thanks