Dear all,

Assume that you run a model with the "bayes" prefix. For the sake of the argument, let us assume this very simple example.

Code:
sysuse auto
bayes: reg mpg
The results are:

HTML Code:
Burn-in ...
Simulation ...

Model summary
------------------------------------------------------------------------------
Likelihood:
  mpg ~ regress({mpg:_cons},{sigma2})

Priors:
  {mpg:_cons} ~ normal(0,10000)
     {sigma2} ~ igamma(.01,.01)
------------------------------------------------------------------------------

Bayesian linear regression                       MCMC iterations  =     12,500
Random-walk Metropolis-Hastings sampling         Burn-in          =      2,500
                                                 MCMC sample size =     10,000
                                                 Number of obs    =         74
                                                 Acceptance rate  =      .4189
                                                 Efficiency:  min =      .1705
                                                              avg =      .1924
Log marginal likelihood = -244.88981                          max =      .2144
 
------------------------------------------------------------------------------
             |                                                Equal-tailed
             |      Mean   Std. Dev.     MCSE     Median  [95% Cred. Interval]
-------------+----------------------------------------------------------------
mpg          |
       _cons |  21.30411   .6781437   .014646   21.32258   19.96519   22.60581
-------------+----------------------------------------------------------------
      sigma2 |  34.45136   5.848324   .141647   33.74739   24.79315    47.5186
------------------------------------------------------------------------------
Note: Default priors are used for model parameters.
When I try to get marginal effects I get:

HTML Code:
. margins, dydx(*) atmeans post
last estimates not found
r(301);
Is there a way to retrieve marginal effects after Bayesian analysis in Stata?