QQ plots for random effects

[Yeganeh]

Hello everyone,
I have to assume the data is heterogeneous. So I want to draw qq plot for each part of the zero-inflated model:
random effects in zero-part within men/women
random effects in Poisson-part within men/ women
If possible, Could you provide code for it, please?
I look forward to your reply.
Best,
Yeganeh

[sbxkoenk]

Hello,

I have moved this post from Visual Analytics board to statistical_procedures board.

It is "Visual" (QQ-plot) and it is "Analytics" (Zero-Inflated Poisson Regression), but that does not make it SAS Visual Analytics 🤔 .

Koen

[sbxkoenk]

Hello @Yeganeh ,

The UNIVARIATE procedure (base SAS) and the CAPABILITY procedure (SAS/QC) have a QQPLOT statement.

Can't you use that one of these?

Thanks,

Koen

[Yeganeh]

Hi Koen,
I want to make qq plot for random effects in the different groups separately. I have attached the figure.

It seems we need the (ui,vi) before making this plot. I tried to use /solution to estimating random effects but, it could not estimate random effects. I used proc univariate;
var dmft;
class sex;
qqplot /normal(mu=est sigma=est) square;
run;
This code has limitations. It can't provide qq plot for two parts of zip model.
For a detailed description of this figure, please refer to my former post (WARNING: The final Hessian matrix is full rank but has at least one negative eigenvalue)

[sbxkoenk]

Hello @Yeganeh ,

Is it possible to paste the example QQ-plot in the body of a new post in this thread?

You can copy / paste or use the "Insert Photos"-button if the plot is in a file (like *.png or *.jpg).
That way I do not have to download an attachment (something I do not like to do).

I guess I will then also find out what the pair (ui,vi) means, because that does not ring a bell right now.

Thanks,

Koen

[Yeganeh]

ui:  The random effect related with zero part

vi: The random effect related with poisson part

[sbxkoenk]

Hello,

I see the above plots come from this journal article :
Zero-inflated count models for longitudinal measurements with heterogeneous random effects
Huirong Zhu, Sheng Luo, and Stacia M. DeSantis

Correct?

Unfortunately, I do not know how to get the random effects for the different model parts (zeromodel part and Poisson part).

If nobody else helps you out here (today nor tomorrow), I will send a request to some colleagues within SAS that probably do know how to do this.
I would like to study it and dive into this, but have no time unfortunately.

I will keep an eye on this thread,

Koen

[Yeganeh]

Sorry for misclassification.