[R-sig-ME] Weird behaviour of mcmcsamp & glmer

[Douglas Bates]

Which version of the lme4 package?

Probably what has happened is that I modify the fitted model object
during the mcmcsamp process and have forgotten to reinstall the
original version of the fixef parameters when done.

On Feb 6, 2008 10:12 AM, Bernd Weiss <bernd.weiss at uni-koeln.de> wrote:
> -----BEGIN PGP SIGNED MESSAGE-----
> Hash: SHA1
>
> library(lme4)
> m1 <- glmer(cbind(incidence, size - incidence) ~ period + (1 | herd),
> ~            family = binomial, data = cbpp)
> fixef(m1)  ## first call
> tmp <- mcmcsamp(m1, 1000)
> fixef(m1)  ## second call
>
> The fixed effects (m1) before and after the use of mcmcsamp differ
> considerably. Why?
>
> TIA,
>
> Bernd
>
> -----BEGIN PGP SIGNATURE-----
> Version: GnuPG v1.4.7 (MingW32)
> Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org
>
> iD8DBQFHqdxtUsbvfbd00+ERAgVXAKCS3oNVMK5nTo05IARZ6d+UmGotqQCgqSpQ
> vIYoubaJl20NVQRjNzmSohg=
> =8Ixm
> -----END PGP SIGNATURE-----
>
> _______________________________________________
> R-sig-mixed-models at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models
>