# DSGE-VAR: simulated data and shock decomposition

**URL:** <https://forum.dynare.org/t/dsge-var-simulated-data-and-shock-decomposition/6041>\
**Category:** DSGE-VAR\
**Created:** [18 February 2017 09:41 UTC](https://forum.dynare.org/t/dsge-var-simulated-data-and-shock-decomposition/6041 "2017-02-18T09:41:00Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![apple564](https://forum.dynare.org/letter_avatar_proxy/v4/letter/a/b2d939/32.png) [@apple564](https://forum.dynare.org/u/apple564)\
**Post date:** [18 February 2017 09:41 UTC](https://forum.dynare.org/t/dsge-var-simulated-data-and-shock-decomposition/6041/1 "2017-02-18T09:41:00Z")

</div>

We have finished our DSGE-VAR estimation and want to do shock decompositions and IRF based on DSGE-VAR instead of DSGE. Now we have two enquirers as follows,

1. Can we use the posterior mean/mode to simulate the model in a seperate dynare mod file to get the simulated data and shock decomposition data? If so, how would the DSGE-VAR weight, lamda, be reflected in this simulation?
2. This question may be linked with the above one. When we finished the DSGE-VAR estimation, inside the oo\_.PosteriorIRF there are dsge and bvardsge IRF data. How are they calculated? Can we do it manually?

---

<div class="post-metadata">

**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:** [23 February 2017 18:05 UTC](https://forum.dynare.org/t/dsge-var-simulated-data-and-shock-decomposition/6041/2 "2017-02-23T18:05:38Z")

</div>

Using the unstable version (future version 4.5), all objects you need to compute these things should be saved. See [[Comparing IRFs of DSGE and DSGE-VAR in dynare](https://forum.dynare.org/t/comparing-irfs-of-dsge-and-dsge-var-in-dynare/6049/1))