# DSGE-VAR Likelihood Functions

**URL:** https://forum.dynare.org/t/dsge-var-likelihood-functions/6120
**Category:** DSGE-VAR
**Created:** [4 April 2017 00:31 UTC](https://forum.dynare.org/t/dsge-var-likelihood-functions/6120 "2017-04-04T00:31:53Z")
**Posts on this page:** 4
**Page:** 1

<div class="post-metadata">

### Author: ![zapadedo](https://forum.dynare.org/letter_avatar_proxy/v4/letter/z/b3f665/32.png) [@zapadedo](https://forum.dynare.org/u/zapadedo)
#### Post date: [4 April 2017 00:31 UTC](https://forum.dynare.org/t/dsge-var-likelihood-functions/6120/1 "2017-04-04T00:31:53Z")

</div>

Solved. Thanks!

---

<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: [5 April 2017 11:40 UTC](https://forum.dynare.org/t/dsge-var-likelihood-functions/6120/2 "2017-04-05T11:40:58Z")

</div>

1. You don’t get the plots because of the

```auto

```

1. The model\_comparison fails because the estimation does not properly work. You did not find a correct mode and the data is wrong. obs\_y\_h for example has a massive seasonal pattern

---

<div class="post-metadata">

### Author: ![zapadedo](https://forum.dynare.org/letter_avatar_proxy/v4/letter/z/b3f665/32.png) [@zapadedo](https://forum.dynare.org/u/zapadedo)
#### Post date: [6 April 2017 10:34 UTC](https://forum.dynare.org/t/dsge-var-likelihood-functions/6120/3 "2017-04-06T10:34:25Z")

</div>

Solved. Thanks!

---

<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: [9 April 2017 10:41 UTC](https://forum.dynare.org/t/dsge-var-likelihood-functions/6120/4 "2017-04-09T10:41:49Z")

</div>

You should be working with different priors that do not imply asymptotes (e.g. at the unit root). In the unstable version I get

`Prior distribution for parameter theta_star has unbounded density!
Prior distribution for parameter rho_a_star has unbounded density!
Prior distribution for parameter phi_e_h has unbounded density!
Prior distribution for parameter phi_e_star has unbounded density!`  
That should explain the problems with rho\_a\_star.

Regarding the DSGE-VAR, the implied covariance matrix of the VAR’s innovations, based on the artificial sample, is not positive definite. This suggests that your model is stochastically singular, i.e. the shocks you have left are not sufficient to get observables used in the VAR that are not exact linear combinations.