Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.


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

Re: st: Adjusted Prevalence from Logistic models


From   Phil Clayton <philclayton@internode.on.net>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Adjusted Prevalence from Logistic models
Date   Wed, 24 Oct 2012 22:55:07 +1100

For such a simple model you could also consider graphing the predicted probability of beta blocker use against age for each of the four groups defined by rural dwelling & sex.

logistic BB age i.sex i.rural
margins sex#rural, at(age=(50(5)90))
marginsplot, noci legend(pos(6) row(1)) plotopts(msymbol(none))

Obviously you can change the age range to suit your particular dataset.

Phil

On 24/10/2012, at 7:18 PM, Richard Williams <richardwilliams.ndu@gmail.com> wrote:

> At 01:18 AM 10/24/2012, Dean Eurich wrote:
>> Hi all,
>> 
>> A simple question. If I run a logistic model:
>> 
>> logistic BB age sex rural
>> 
>> I get the OR for the effect of rural (which is a flag for rural=0 or urban=1 dwelling) on the use of beta blockers (medication used to treat cardiovascular disease).
>> 
>> A reviewer has asked for us to present the adjusted prevalence for the use of BB by rural and urban status. I am not to sure how to do this.
>> 
>> I assume I could use the 'margin' command.
>> 
>> So would it be as simple as
>> 
>> margins rural, atmeans
>> 
>> (Although I realize I could do it as specific levels of sex and age as well)
>> 
>> Thanks
>> 
>> Dean
> 
> I'm not totally sure how you want to adjust. But if you want to use -margins- you should use factor variable notation, e.g.
> 
> logistic BB age i.sex i.rural
> margins rural, atmeans
> 
> In general, I am not crazy about the atmeans option, and I especially don't like it when you have a variable like sex in the model. You'll be plugging in something like .5 for sex (the average person is half male, half female?) I'd rather use the default -asobserved- or plug in specific values or ranges of values for the other variables. For some highlights of what you can do with margins, see
> 
> http://www.nd.edu/~rwilliam/stats/Margins01.pdf
> 
> As a sidelight, when you say rural=0 or urban=1, that sort of sounds to me like heads I win, tails you lose. Aren't rural=0 and urban=1 the same thing?
> 
> -------------------------------------------
> Richard Williams, Notre Dame Dept of Sociology
> OFFICE: (574)631-6668, (574)631-6463
> HOME:   (574)289-5227
> EMAIL:  Richard.A.Williams.5@ND.Edu
> WWW:    http://www.nd.edu/~rwilliam
> 
> *
> *   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 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index