You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
As raised in #115, #107, and elsewhere, users increasingly modify the jags_code generated by mcp but get stuck when introducing new variables. We should make it easier to do this. Maybe it will fit neatly into the custom families (#101) planned for v0.5,
Add fields with "extra_data_params" to the custom family. Perhaps allow defining out-of-model inferred parameters using prior = list(new_param = "dnorm(...)") as a way to signal that it should be sampled.
Include "extra_data_params" in jags_data
Sample extra_inferred_params and show them in summary() and plot_pars() etc.
Perhaps provide an API to let users modify fit$.internal$formula_r instead of the full jags_code so that it can be used for plot(), fitted(), pp_check(), etc.
The text was updated successfully, but these errors were encountered:
As raised in #115, #107, and elsewhere, users increasingly modify the
jags_code
generated bymcp
but get stuck when introducing new variables. We should make it easier to do this. Maybe it will fit neatly into the custom families (#101) planned for v0.5,prior = list(new_param = "dnorm(...)")
as a way to signal that it should be sampled.jags_data
extra_inferred_params
and show them insummary()
andplot_pars()
etc.fit$.internal$formula_r
instead of the fulljags_code
so that it can be used forplot()
,fitted()
,pp_check()
, etc.The text was updated successfully, but these errors were encountered: