[R] Question on gee library

[Jun Yan]

On Sun, 29 Sep 2002, Jun Takeda wrote:
> I understand the method generalized estimating equation
> only accept missing values as Missing Completely At Random  (MCAR). 
> I would like to know more about the gee function in the gee library. 
> 
> Does the function gee in gee library accept NA?
> How does the function gee treat NA?

The following is from the function gee,

    if (!is.null(m$na.action) && m$na.action != "na.omit") {
        print("Warning: Only na.omit is implemented for gee")
        print("         continuing with na.action=na.omit")
        m$na.action <- as.name("na.omit")
    }

If the responses (and the covariates) are MCAR, na.omit removes the
observations with NA in either response or covariates, and the resulting
gee fit is valid for MCAR.


Jun Yan

Department of Statistics          Office: CSSC 4252
university of Wisconsin-Madison   Tel: (608)262-7478 
1210 W. Dayton St.                Email: jyan at stat.wisc.edu
Madison, WI 53706                 URL: http://www.stat.wisc.edu/~jyan





-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._