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.

# RE: st: AW: difference in odds ratio

 From "Martin Weiss" To Subject RE: st: AW: difference in odds ratio Date Tue, 2 Mar 2010 20:23:21 +0100

```<>

Works just fine for me:

*******
webuse union, clear
clogit union age grade not_smsa if black, group(idcode)
est sto A
clogit union age grade not_smsa if !black, group(idcode)
est sto B
suest A B
test [A_union=B_union], cons
lincom [A_union]:age-[B_union]:age
lincom [A_union]:not_smsa-[B_union]:not_smsa
*******

HTH
Martin

-----Original Message-----
From: owner-statalist@hsphsun2.harvard.edu
[mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Shehzad Ali
Sent: Dienstag, 2. März 2010 19:11
To: statalist@hsphsun2.harvard.edu
Subject: Re: st: AW: difference in odds ratio

Thanks, Martin. For some strange reason, I experience the following problem:

clogit chosen x1 x2 x3 x4 if sex==1, group(choice_set)
est stor A
clogit chosen x1 x2 x3 x4 if sex==0, group(choice_set)
est stor B
suest A B
test [A=B], cons

Interestingly, -suest- displays the results as equations 'A_chosen' and
'B_chosen'. I then tried using -test [A_chosen=B_chosen]- but the results
look strange, i.e. differences for all pairs of coefficients are zero, which
they shouldnt be.

I wonder what I am doing wrong here? Also, is it possible to get the
confidence interval of the difference between each set of coefficients from
the two models?

Thank you,

----- Original Message ----
> From: Martin Weiss <martin.weiss1@gmx.de>
> To: statalist@hsphsun2.harvard.edu
> Sent: Tue, March 2, 2010 10:42:13 AM
> Subject: st: AW: difference in odds ratio
>
>
> <>
>
>
>
> *************
> h suest
> *************
>
>
>
> HTH
> Martin
>
>
> -----Ursprüngliche Nachricht-----
> Von: owner-statalist@hsphsun2.harvard.edu
> [mailto:owner-statalist@hsphsun2.harvard.edu] Im Auftrag von Shehzad Ali
> Gesendet: Dienstag, 2. März 2010 11:32
> An: Stata List
> Betreff: st: difference in odds ratio
>
> Hi listers,
>
> I have run two separate logistic regression models for two age groups
> (dependent and independent variables are the same in the two regressions).
I
> want to find out whether the odds ratios for the two groups are
> statistically significantly different from each other, i.e. I am
interested
> in OR(A) - OR(B) and the confidence interval around the difference.
>
> Could anyone suggest the best way to get the confidence interval and
p-value
> of the difference in odds ratios?
>
> Many thanks,
>
>
>
>
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/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/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/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/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/
```