Combined Metropolis, RescalingStep samplers.

choderalab / bayesian-itc

Python tools for the analysis and modeling of isothermal titration calorimetry (ITC) experiments.

GNU General Public License v3.0

5 stars 10 forks source link

Closed bas-rustenburg closed 9 years ago

bas-rustenburg commented 9 years ago

Running sampling for 1000000 steps to test.

bas-rustenburg commented 9 years ago

Here is the data, fixing the bug so we're using both Metropolis and RescalingStep at once.

1,000,000 steps, 10000 burn-in, thinning period of 25:

sample-deltag sample-deltah sample-deltah_0 sample-ls sample-p0 sample-sigma sample-subtracted

jchodera commented 9 years ago

How does this compare to omitting RescalingStep?

bas-rustenburg commented 9 years ago

@jchodera see #54, I added the comparison there.

bas-rustenburg commented 9 years ago

Switched back to using Metropolis only, but leaving the fixed implementation of RescalingStep for if we change our minds.