[R-sig-ME] Questions on Mixed Model analysis

[Ben Bolker]

On Tue, Nov 22, 2016 at 1:38 PM, Cleber Iack <profiack at gmail.com> wrote:
> Dear,
>
> I would like if it was possible that the Lord would help me in a review,
> lest it incur in error.
>
> If it were a Simple Logistic regression, I  in school "A" could calculate
> the Odds Ratio for example in relation to the "P1", I would exp
> (-0.44448621), but since I'm using a generalized linar mixed model with
> Reply Binaria, I can analyze the same way this exit?
>
> If I'm wrong, could you give me an example of these data down the analysis
> of any school cited in relation to any predictor variable
>
> Thank you
>
> Cleber
>
>> ranef(mt7)
> $escola
>       (Intercept)          P1                P2              P3
>  P4
> A     1.6902746  -0.4448621  -0.6658758 -3.4604301  -3.3696828
> B   -1.2843136   1.0089079   0.3088816  0.1211393   1.6589110
> C  -0.5780668  -0.9977792   0.5655049  2.1674668   0.1728413
> D   0.1886338   0.4412192  -0.2184985  1.5010123   1.7992507"

   The random effects represent deviations from the population-level
value of the parameter.  So the odds ratio represents the deviation
from the population average.  If you want the overall odds ratio
(deviation of school A from even odds in the P1 parameter), try coef()


>
> Number of obs: 79811, groups:  escola, 4
> Fixed Effects:
>     (Intercept)              cem       anoscMedio       anoscMuito
>  anoscFinalizado
>        -2.44242         -0.22111         -0.53089         -1.80689
> -2.45414
>            cugm              cri              cam              hpm
>     caim
>         0.06979         -0.55041          0.20136          0.17523
> -0.12234
>             cpm             qutm              ism                     P1
>                P2
>         0.21953         -0.06551          0.07528         -0.64913
> -1.50175
>      P3                        P4
>        -2.19105         -1.88287
>
>         [[alternative HTML version deleted]]
>
> _______________________________________________
> R-sig-mixed-models at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models