# Error with AR(2) exogenous process

**URL:** <https://forum.dynare.org/t/error-with-ar-2-exogenous-process/3242>\
**Category:** Dynare help (legacy posts)\
**Created:** [24 June 2013 12:09 UTC](https://forum.dynare.org/t/error-with-ar-2-exogenous-process/3242 "2013-06-24T12:09:25Z")\
**Posts on this page:** 5\
**Page:** 1

<div class="post-metadata">

**Author:** ![lombard](https://forum.dynare.org/letter_avatar_proxy/v4/letter/l/ecb155/32.png) [@lombard](https://forum.dynare.org/u/lombard)\
**Post date:** [24 June 2013 12:09 UTC](https://forum.dynare.org/t/error-with-ar-2-exogenous-process/3242/1 "2013-06-24T12:09:25Z")

</div>

Hi,

I couldn’t find anything on this subject.

I’ve written the technology process as

```auto
a=rho_a*a(-1)+rho_a2*a_m1(-1)+e_a; 
a_m1=a(-1);
```

where

```auto
rho_a=1.9;
rho_a2=(1-rho_a_A)-.001;
```

The eigenvalues of this AR(2) block are

> [@](#):
>
> 0.9887  
> 0.9113

Yet Dynare returns

> [@](#):
>
> There are 38 eigenvalue(s) larger than 1 in modulus  
> for 37 forward-looking variable(s)
> 
> The rank conditions ISN’T verified!

While having a standard AR(1) process generates a saddle-path solution.

Am I missing something? Is this a known issue?

Thanks

Gianni

PS: I’m using version 4.4-unstable

---

<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:** [24 June 2013 13:39 UTC](https://forum.dynare.org/t/error-with-ar-2-exogenous-process/3242/2 "2013-06-24T13:39:45Z")

</div>

Sorry, but I cannot replicate the issue. What exactly is rho\_a\_A in your definition of rho\_a2? Is it supposed to be rho\_a? Could you run the attached file on your machine and see whether it runs?  
[lombard.mod](https://forum.dynare.org/uploads/default/original/2X/4/47c4ff12051a635119051b0efaa5f2d722ad7275.mod) (390 Bytes)

---

<div class="post-metadata">

**Author:** ![lombard](https://forum.dynare.org/letter_avatar_proxy/v4/letter/l/ecb155/32.png) [@lombard](https://forum.dynare.org/u/lombard)\
**Post date:** [24 June 2013 14:17 UTC](https://forum.dynare.org/t/error-with-ar-2-exogenous-process/3242/3 "2013-06-24T14:17:44Z")

</div>

Sorry, it was a typo. You correctly guessed it was rho\_a.

As for the possibility of reproduce the problem, it is not so simple. That is why I was checking for  
similar experiences. If you simply write the AR(2) in Dynare, it will solve. The problem, as I mentioned  
is that in a larger model you go from being able to solve to no solution.

I’ll try to post a specific example, if I find a minute to wrap things together

Cheers

Gianni

---

<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:** [24 June 2013 14:19 UTC](https://forum.dynare.org/t/error-with-ar-2-exogenous-process/3242/4 "2013-06-24T14:19:48Z")

</div>

I see. Have you checked whether adding an additional variable just decreases the numerical accuracy and the qz\_criterium now is too narrow?

---

<div class="post-metadata">

**Author:** ![chekellog1010](https://forum.dynare.org/letter_avatar_proxy/v4/letter/c/c6cbf5/32.png) [@chekellog1010](https://forum.dynare.org/u/chekellog1010)\
**Post date:** [26 June 2013 03:44 UTC](https://forum.dynare.org/t/error-with-ar-2-exogenous-process/3242/5 "2013-06-26T03:44:53Z")

</div>

> [@jpfeifer](#):
>
> Sorry, but I cannot replicate the issue. What exactly is rho\_a\_A in your definition of rho\_a2? Is it supposed to be rho\_a? Could you run the [attached](http://kostenloshandyorten.de) file on your machine and see whether it runs?
