# Posterior Mode of Bayesian Estimation **URL:** \ **Category:** ML/Bayesian estimation\ **Created:** [1 August 2020 04:23 UTC](https://forum.dynare.org/t/posterior-mode-of-bayesian-estimation/16350 "2020-08-01T04:23:40Z")\ **Posts on this page:** 3\ **Page:** 1
**Author:** ![Andy\_zhao](https://forum.dynare.org/letter_avatar_proxy/v4/letter/a/96bed5/32.png) [@Andy\_zhao](https://forum.dynare.org/u/Andy_zhao)\ **Post date:** [1 August 2020 04:23 UTC](https://forum.dynare.org/t/posterior-mode-of-bayesian-estimation/16350/1 "2020-08-01T04:23:40Z")
Hi all, After running Bayesian estimation using MCMC, the output of “MAT -file” gives three type of posterior mode information: (1), modname\_mode (2), modname\_mh\_mode (3), modename\_results/oo\_.posterior\_mode My questions are: (a), what are the exact difference for those three type of posterior mode (b), If I want to do Laplace approximation, which mode information should I use? Thanks in Advance! ---
**Author:** ![jpfeifer](https://forum.dynare.org/user_avatar/forum.dynare.org/jpfeifer/32/5044_2.png) [@jpfeifer](https://forum.dynare.org/u/jpfeifer)\ **Post date:** [4 August 2020 10:01 UTC](https://forum.dynare.org/t/posterior-mode-of-bayesian-estimation/16350/2 "2020-08-04T10:01:23Z")
The `modname_mode` is the mode after mode-finding. Its results are stored in the `_results.mat`-file in `oo_.posterior_mode`. The `posterior_mode`-file in contrast contains the mode obtained during the run of the Metropolis-Hastings algorithm. ---
**Author:** ![Andy\_zhao](https://forum.dynare.org/letter_avatar_proxy/v4/letter/a/96bed5/32.png) [@Andy\_zhao](https://forum.dynare.org/u/Andy_zhao)\ **Post date:** [5 August 2020 00:22 UTC](https://forum.dynare.org/t/posterior-mode-of-bayesian-estimation/16350/3 "2020-08-05T00:22:33Z")
Dear Johannes, This is very helpful! Thank you very much! Best Wishes