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: Comparing groups


From   MIGUEL ANGEL GRUPO DE INVESTIGACIO ODONT SIMANCAS PALLARES <[email protected]>
To   [email protected]
Subject   Re: st: Comparing groups
Date   Thu, 17 Jan 2013 15:09:09 -0500

Maarten, thanks for the answer.

In this example i can see a little bit better the logistic regression
use for this case.
But, what does mean in the command "logit low ib0.drug", the <ib0.>? I
couldnt find any variable named in this way.
In other hand, if i request to STATA for "logistic" it would report
Odds Ratios. If less than 1 i can understand that the treatment effect
is benefical for the outcome?

Thanks for your answer,

Miguel.

On Thu, Jan 17, 2013 at 2:44 PM, Maarten Buis <[email protected]> wrote:
> On Thu, Jan 17, 2013 at 8:22 PM, MIGUEL ANGEL GRUPO DE INVESTIGACIO
> ODONT SIMANCAS PALLARES wrote:
>> But my question is adressed to know if is correct to use X2 test to
>> compare the treatment groups having in mind that the outcome is
>> dichotomus (compare two treatment estrategies when the outcome is
>> dichotomus).
>
> The Chi square test is just a test of no association in the entire
> table, so that is not what you want (I think). I would just use
> logistic regression in that case:
>
> *------------------ begin example ----------------------
> // get some data
> use http://www.stata-press.com/data/r12/lbw.dta, clear
>
> // create our 3 value "drug" variable
> // 0 plays the role of the placebo and 1 and 2 are the
> // competing "drugs"
> gen byte drug = cond(ftv==0,0,                    ///
>                 cond(ftv==1,2,3)) if ftv < .
> label define drug 0 "0 visits to doctor"          ///
>                   1 "1 visit to doctor"           ///
>                   2 "more than 1 visit to doctor"
>
> // The logit output gives you directly tests the comparisons
> // drug 1 versus placebo and drug 2 versus placebo
> // In this case both are not significant
> logit low ib0.drug, or
> *-------------------- end example -----------------------
> (For more on examples I sent to the Statalist see:
> http://www.maartenbuis.nl/example_faq )
>
> Hope this helps,
> Maarten
>
> ---------------------------------
> 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/



-- 
Cordial Saludo,

Miguel Angel Simancas. OD. MSc (C).
GITOUC - GITOUC Research Group
Departamento de Investigación - Research Department
Facultad de Odontología - Faculty of Dentistry
Universidad de Cartagena - University of Cartagena
Tel: +57 (5) 6698172. Ext: 110.

*
*   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