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: From: Ankit Sakhuja <[email protected]>


From   Maarten Buis <[email protected]>
To   [email protected]
Subject   Re: st: From: Ankit Sakhuja <[email protected]>
Date   Fri, 24 Jan 2014 10:46:13 +0100

If you are interested in the odds ratios, than you could look at:

M.L. Buis (2012) "Stata tip 106: With or without reference", The Stata
Journal, 12(1), pp. 162-164.

Here is an example using -logit-:

*------------------ begin example ------------------
sysuse nlsw88, clear

gen byte black = race == 2 if race < 3
label variable black "race"
label define black 0 "white" ///
                   1 "black"
label value black black

gen byte goodjob = occupation < 3 if occupation < .
label variable goodjob `"respondent has a "good" job"'
label define goodjob 1 "profesional or managerial" ///
                     0 "other"
label value goodjob goodjob

logit union ibn.goodjob i.goodjob#i.collgrad i.black i.south, or
*------------------- end example -------------------
* (For more on examples I sent to the Statalist see:
* http://www.maartenbuis.nl/example_faq )

So, the odds ratio of collegegrad for those with a good job is 1.4 and
the odds ratio for those that don't have a good job is 2.4.

Hope this helps,
Maarten


On Fri, Jan 24, 2014 at 4:52 AM,  <[email protected]> wrote:
> Dear Members,
>
> I am trying to understand the effect of interaction between two
> categorical variables in a model:
>
> Logistic DIED i.agegroup i.sex i.race i.procedure i.procedure#i.sex
>
> I can visualize the interaction effect using margins and margins plot as below:
>
> margins procedure#sex
> ------------------------------------------------------------------------------
>              |            Delta-method
>              |     Margin   Std. Err.      z    P>|z|     [95% Conf. Interval]
> -------------+----------------------------------------------------------------
>     procedure#sex |
>         0 0  |   .0960571   .0013119    73.22   0.000     .0934859    .0986284
>         0 1  |   .1568595   .0082394    19.04   0.000     .1407106    .1730084
>         1 0  |   .0462026   .0008488    54.43   0.000      .044539    .0478663
>         1 1  |   .1160865   .0086644    13.40   0.000     .0991046    .1330684
> ------------------------------------------------------------------------------
> marginsplot
>
> However, I am not sure how to interpret the above table accurately
> (from my understanding it shows the % probability of mortality for
> each scenario) and how to find the odds ratios for mortality for the 2
> scenarios as below (I can find these ORs by stratifying the population
> into males and females & then running 2 separate regression but I am
> not sure if there is a way to get those using the interaction term in
> the full model):
> Males undergoing procedure in comparison to Males not undergoing procedure
> Females undergoing procedure in comparison to Females not undergoing procedure
>
> I would really appreciate your help.
> Thanks
> Ankit
> *
> *   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/



-- 
---------------------------------
Maarten L. Buis
WZB
Reichpietschufer 50
10785 Berlin
Germany

http://www.maartenbuis.nl
---------------------------------
*
*   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