R help - Jul 2010 - How to get the standard error from GEE(Generalized Estimation Equations) output

I am having some difficulties to locate the standard error from GEE output.


-----------sample output using list (geemodel)------------------------
 Link:                      Identity
 Variance to Mean Relation: Gaussian
 Correlation Structure:     Exchangeable
Call:
gee(formula = days.sick1 ~ bmi + age + gender + surveyround2 +
    surveyround3, id = childid, data = dat, family = gaussian,
    corstr = "exchangeable")
Number of observations :  1110
Maximum cluster size   :  3

Coefficients:
 (Intercept)          bmi          age       gender
 -1.12830236  -0.05216691  -0.01230798   0.14646632

Estimated Scale Parameter:  2.620455
Number of Iterations:  2

	[[alternative HTML version deleted]]

Hi there,

You forgot to give us some detail, but here is my guess:

install.packages('gee')

require(gee)


# fitting the model as in the help file under ?gee

data(warpbreaks)

fit <- gee(breaks ~ tension, id = wool, data = warpbreaks, corstr
"exchangeable")


 # extracting what you need

summary(fit)

str(summary(fit))

summary(fit)$coefficients

# Naive SE
summary(fit)$coefficients[,2]

# Robust SE
summary(fit)$coefficients[,3]

See ?str.

HTH,
Jorge

On Thu, Jul 29, 2010 at 1:17 PM, ZZY ZYBOYS <> wrote:
> I am having some difficulties to locate the standard error from GEE output.
>
>
> -----------sample output using list (geemodel)------------------------
>  Link:                      Identity
>  Variance to Mean Relation: Gaussian
>  Correlation Structure:     Exchangeable
> Call:
> gee(formula = days.sick1 ~ bmi + age + gender + surveyround2 +
>    surveyround3, id = childid, data = dat, family = gaussian,
>    corstr = "exchangeable")
> Number of observations :  1110
> Maximum cluster size   :  3
>
> Coefficients:
>  (Intercept)          bmi          age       gender
>  -1.12830236  -0.05216691  -0.01230798   0.14646632
>
> Estimated Scale Parameter:  2.620455
> Number of Iterations:  2
>
>        [[alternative HTML version deleted]]
>
> ______________________________________________
> R-help@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.
>
	[[alternative HTML version deleted]]