# Can we estimate parameter that is not related to shock?

**URL:** <https://forum.dynare.org/t/can-we-estimate-parameter-that-is-not-related-to-shock/5950>\
**Category:** Dynare help (legacy posts)\
**Created:** [27 December 2016 13:33 UTC](https://forum.dynare.org/t/can-we-estimate-parameter-that-is-not-related-to-shock/5950 "2016-12-27T13:33:38Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![shuixing](https://forum.dynare.org/letter_avatar_proxy/v4/letter/s/bc79bd/32.png) [@shuixing](https://forum.dynare.org/u/shuixing)\
**Post date:** [27 December 2016 13:33 UTC](https://forum.dynare.org/t/can-we-estimate-parameter-that-is-not-related-to-shock/5950/1 "2016-12-27T13:33:38Z")

</div>

dear professor Pfeifer;

I have a question about parameter estimation using bayesian,: can we estimate parameters those are not related to the specified shocks, i.e., if I do not specify a wage stickiness shock, nor do I have wage data, can I use bayesian estimation and other variable data to estimate the wage stickiness parameters?

best  
shuixing

---

<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:** [27 December 2016 13:39 UTC](https://forum.dynare.org/t/can-we-estimate-parameter-that-is-not-related-to-shock/5950/2 "2016-12-27T13:39:47Z")

</div>

In general, the answer is yes. To stay with your example, the value of the wage stickiness parameter will typically have implications for the probability distribution of the other observed variables. However, you should always check whether your observed data is informative for the parameters you want to estimate, i.e. you should use the

```auto

```

command

---

<div class="post-metadata">

**Author:** ![shuixing](https://forum.dynare.org/letter_avatar_proxy/v4/letter/s/bc79bd/32.png) [@shuixing](https://forum.dynare.org/u/shuixing)\
**Post date:** [28 December 2016 10:32 UTC](https://forum.dynare.org/t/can-we-estimate-parameter-that-is-not-related-to-shock/5950/3 "2016-12-28T10:32:14Z")

</div>

[quote=“jpfeifer”]In general, the answer is yes. To stay with your example, the value of the wage stickiness parameter will typically have implications for the probability distribution of the other observed variables. However, you should always check whether your observed data is informative for the parameters you want to estimate, i.e. you should use the

```auto

```

command[/quote]

I see, thanks, professor Pfeifer.