I got it. Thanks for your patient answer.
I have learned prior and posterior predictive checks. Is it hard to use in a custom likelihood function?
BTW, I uploaded my code and a document which may describes my model and priors better. I’d really appreciate it if you could take a look.
I use pymc 5.10.0 in windows.
To run my code. You should install a chemistry library through:
conda install -c conda-forge cantera
And I have another error the same as posted in Can you try setting cores=1 in pm.sample?
I install pymc with conda in a new env. I donnot know how to handle it. so I set pm.sample(cores=1).
sofc_demo_explanation.pdf (737.9 KB)
sofc_demo.py (9.0 KB)