david oseguera montiel
2011-Aug-15 18:29 UTC
[R] Get significant codes from a model output fit with GEE package
Does anyone know how could I get the significant codes from mixed model
output fitted with a GEE package?
The output I got is the following:
GEE: GENERALIZED LINEAR MODELS FOR DEPENDENT DATA
gee S-function, version 4.13 modified 98/01/27 (1998)
Model:
Link: Logit
Variance to Mean Relation: Binomial
Correlation Structure: Exchangeable
Call:
gee(formula = bru ~ +grac + locc + dekc, id = flo, data = all,
family = binomial(link = "logit"), corstr =
"exchangeable")
Summary of Residuals:
Min 1Q Median 3Q Max
-0.41935925 -0.15355800 -0.09403907 -0.03244056 0.98117731
Coefficients:
Estimate Naive S.E. Naive z Robust
S.E. Robust z
(Intercept) -0.3254043 0.1640277 -1.983837 0.1375856 -2.365105
graczero -1.6884041 0.4978737 -3.391230 0.5222118 -3.233179
loccM -1.3815591 0.2202543 -6.272563 0.2256275 -6.123185
dekclow -0.5583225 0.2487267 -2.244723 0.2293527 -2.434341
Estimated Scale Parameter: 1.025636
I much appreciate any help.
David
Dennis Murphy
2011-Aug-15 21:16 UTC
[R] Get significant codes from a model output fit with GEE package
Hi:
If you're asking about the p-values, here's a reproducible example
from the gee package:
library('gee')
m <- gee(breaks ~ tension, id=wool, data=warpbreaks,
corstr="exchangeable")
# Nosing around the summary method return object:> names(summary(m))
[1] "call" "version"
"nobs"
[4] "residual.summary" "model"
"title"
[7] "coefficients" "working.correlation"
"scale"
[10] "error"
"iterations"> summary(m)$coefficients # Found it...
Estimate Naive S.E. Naive z Robust S.E. Robust z
(Intercept) 36.38889 3.069434 11.855246 5.774705 6.301428
tensionM -10.00000 3.910008 -2.557539 7.463905 -1.339781
tensionH -14.72222 3.910008 -3.765266 3.731952
-3.944912> class(summary(m)$coefficients)
[1] "matrix"
# Assuming your significance tests are two sided,
naivePval <- 2 * pnorm(-abs(summary(m)$coefficients[,
3]))> naivePval
(Intercept) tensionM tensionH
2.021302e-32 1.054156e-02 1.663716e-04> robustPval <- 2 * pnorm(-abs(summary(m)$coefficients[, 5]))
> robustPval
(Intercept) tensionM tensionH
2.949162e-10 1.803165e-01 7.982945e-05
HTH,
Dennis
On Mon, Aug 15, 2011 at 11:29 AM, david oseguera montiel
<davidoseguera at yahoo.com.mx> wrote:> Does anyone know how could I get the significant codes from mixed model
> output fitted with a GEE package?
> The output I got is the following:
>
> ?GEE: ?GENERALIZED LINEAR MODELS FOR DEPENDENT DATA
> ?gee S-function, version 4.13 modified 98/01/27 (1998)
>
> Model:
> ?Link: ? ? ? ? ? ? ? ? ? ? ?Logit
> ?Variance to Mean Relation: Binomial
> ?Correlation Structure: ? ? Exchangeable
>
> Call:
> gee(formula = bru ~ +grac + locc + dekc, id = flo, data = all,
> ? ?family = binomial(link = "logit"), corstr =
"exchangeable")
>
> Summary of Residuals:
> ? ? ? ?Min ? ? ? ? ?1Q ? ? ?Median ? ? ? ? ?3Q ? ? ? ? Max
> -0.41935925 -0.15355800 -0.09403907 -0.03244056 ?0.98117731
>
>
> Coefficients:
> ? ? ? ? ? ? ? ? ? ? ? ? Estimate ? ?Naive S.E. ? ?Naive z ? ? ?Robust S.E.
> ?Robust z
> (Intercept) -0.3254043 ?0.1640277 -1.983837 ? 0.1375856 -2.365105
> graczero ? ?-1.6884041 ?0.4978737 -3.391230 ? 0.5222118 -3.233179
> loccM ? ? ? -1.3815591 ?0.2202543 -6.272563 ? 0.2256275 -6.123185
> dekclow ? ? -0.5583225 ?0.2487267 -2.244723 ? 0.2293527 -2.434341
>
> Estimated Scale Parameter: ?1.025636
>
> I much appreciate any help.
> David
>
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>