Log data density is -Inf
Posted: Sat Aug 06, 2016 8:31 amHi,
I had difficulty in doing Bayesian estimation.
Log data density before mcmc, that is, value at mode, was reseanable.
But, after mcmc, Log data density ends up being -Inf, and also accptance ratios of each chain are almost 100%.
What causes this problem and How can I fix it?
Thanks in advance
I had difficulty in doing Bayesian estimation.
Log data density before mcmc, that is, value at mode, was reseanable.
But, after mcmc, Log data density ends up being -Inf, and also accptance ratios of each chain are almost 100%.
What causes this problem and How can I fix it?
Thanks in advance