Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: RE: RE: Using command svy glm to obtain risk ratios


From   Steve Samuels <[email protected]>
To   [email protected]
Subject   Re: st: RE: RE: Using command svy glm to obtain risk ratios
Date   Tue, 18 Feb 2014 13:47:45 -0500


I think you've discovered a bug, and I've reported it to Technical Support. In the meantime,
the following give exponentiated coefficients.


*************CODE BEGINS*************
webuse nhanes2, clear
svy jackknife slope = ///
 exp(_b[weight]) constant=exp(_b[_cons]) : ///
 glm highbp weight, fam(binom) link(logit)

svy jackknife: logistic highbp weight

**************CODE ENDS**********


On Feb 18, 2014, at 10:16 AM, "Agunwamba, Amenah A., Ph.D." <[email protected]> wrote:

Hi Steve,
Thanks so much for your comments and your reference. I will take a look - I used the sample code using the online NHANES code, and it worked. However, while I just tweaked my code to include my own variables, I was still unable to obtain RRs.

I had tried to put my code in previous messages, but it kept getting bounced, so I gave up...Let me try again.
I am using data from the adult California Health Interview Survey (CHIS). I am modeling a continuous predictor (composite) against a dichotomous outcome (fastf2 ). My code is as follows:

. svy : glm fastf2 composite, fam(bin) link(logit) eform

***RESULTS BELOW****

(running glm on estimation sample)

Jackknife replications (80)
----+--- 1 ---+--- 2 ---+--- 3 ---+--- 4 ---+--- 5 
..................................................    50
..............................

Survey: Generalized linear models

Number of strata   =         1                  Number of obs      =     38592
                                               Population size    =  26287357
                                               Replications       =        80
                                               Design df          =        79

------------------------------------------------------------------------------
            |              Jknife *
     fastf2 |      Coef.   Std. Err.      t    P>|t|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
  composite |  -.1805861   .0180401   -10.01   0.000    -.2164941   -.1446782
      _cons |  -.5332004   .0196523   -27.13   0.000    -.5723172   -.4940835
------------------------------------------------------------------------------

Hope this goes through!

~AAA


*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/


*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index