I’m working with the ABC example provided on pymc.io . I’ve tried a couple of factorial changes: Changing from the default “Slice”/CompoundStep sampler to DEMetropolis or DEMetropolisZ (Works) Changing the m parameter from a Uniform prior to pm.Constant("m", c = 0.4) (Works) Changing the m paramete…

Cannot sample with DEMetropolis* when using pm.Constant

ricardoV94 June 4, 2022, 5:36am 5

Yes that is perfectly valid.

Topic		Replies	Views
TypeError when combining constant and Normal distribution in function within deterministic node v5 bug	6	777	April 18, 2022
"Fixed" prior question Questions	2	1122	December 5, 2021
Error in the sampling process, 'sd' not taken in account in Metropolis.py Questions	8	1506	September 29, 2017
Pymc3 evaluates function but doesn't update sample Questions	5	1369	November 3, 2017
Metropolis sampler do not sample (traceplot gives flat plots) Questions	11	2840	June 15, 2018