# Unable to recover simulated parameters

**URL:** <https://discourse.mc-stan.org/t/unable-to-recover-simulated-parameters/3147>\
**Category:** Modeling\
**Tags:** specification\
**Created:** [January 31, 2018, 5:47am UTC](https://discourse.mc-stan.org/t/unable-to-recover-simulated-parameters/3147 "2018-01-31T05:47:03Z")\
**Posts on this page:** 1\
**Showing post:** 11

<div class="post-metadata">

**Author:** ![Bob\_Carpenter](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.mc-stan.org/bob_carpenter/32/9230_2.png) [@Bob\_Carpenter](https://discourse.mc-stan.org/u/Bob_Carpenter)\
**Post date:** [February 11, 2018, 6:08pm UTC](https://discourse.mc-stan.org/t/unable-to-recover-simulated-parameters/3147/11 "2018-02-11T18:08:56Z")

</div>

> [@ganeshkrishnan](#):
>
> If you just want c, why bother with a + b?

It’s usually more involved than this. I don’t know why everyone wants to do this. Andrew’s theory is that people in engineering are trained to look at a lot of problems as data transforms rather than generatively.

Here’s the latest example, which was literally the last message to which I responded before this one:

> [@Simple model Parse Errors](http://discourse.mc-stan.org/t/simple-model-parse-errors/3249/9):
>
> Thanks for the tip. I will read the Stan manual to see if I can follow the examples about using censoring for my problem. I have a more general question about modeling processes of the following type. Assume z1 ~ Normal(mu1, sigma1) z2 ~ Normal(mu2, sigma2) x = f(z1, z2) where f is a deterministic function. If I observe x and am trying to infer E[z1, z2 | x], how do I go about modeling this in Stan? Looks like I’ll have to put x in the data section, but when I try doing that but declare x =…

Presumably the function `f` they’re using is more complicated than addition, but it presents exactly the same problem.

> [@ganeshkrishnan](#):
>
> Could you point me to the Chapter/section in the regression book that they are doing this?

In the IRT section they fiddle around with a bunch of this stuff because the model’s not identified. Just to be clear, you _do not_ and _cannot_ do what they do in BUGS in Stan—I show that and explain why in the manual chapter on problematic posteriors. I’m not even convinced what Gelman and Hill are doing works in BUGS—they never validated it and the guarantees for Gibbs all go out the window with improper posteriors as you don’t even have a density from which to sample!

---

_[View the full topic](https://discourse.mc-stan.org/t/unable-to-recover-simulated-parameters/3147)._