[R-sig-ME] How to fix residuals

[Vincent Dorie]

Hi Sijia,

You might find the section in the GLMM FAQ helpful:
https://bbolker.github.io/mixedmodels-misc/glmmFAQ.html#setting-residual-variances-to-a-fixed-value-zero-or-other.
You can use those to fix the residual variance to 1, and then use a weights
vector if necessary to give every observation its own fixed variance.

Best,
Vince

On Fri, May 8, 2020 at 9:55 AM Mollie Brooks <mollieebrooks using gmail.com>
wrote:

> It might be possible to do that with glmmTMB using the argument `start` to
> specify the values and using `map` to force them to stay at the starting
> values. The tricky part is figuring out what parameter to fix and at what
> values. Can you give a reproducible example so we have more to work with?
>
> cheers,
> Mollie
>
> > On 7May 2020, at 7:24, Sijia Huang <huangsjcc using gmail.com> wrote:
> >
> > Hi,
> > I am using lme4 to fit cross-classified models, and I am wondering if it
> is
> > possible to fix the residual (associated with each observation) to a
> > certain value in lme4 -- analogous to the *hold* argument in SAS PROC.
> >
> > Thank you so much! Looking forward to your reply!
> >
> > Best,
> > Sijia
> >
> >       [[alternative HTML version deleted]]
> >
> > _______________________________________________
> > R-sig-mixed-models using r-project.org mailing list
> > https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models
>
> _______________________________________________
> R-sig-mixed-models using r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models
>

	[[alternative HTML version deleted]]