Re: Is there a way to adjust for...

Posted by lori.andersen on Jan 21, 2012; 6:04pm
URL: http://spssx-discussion.165.s1.nabble.com/Is-there-a-way-to-adjust-for-tp5163060p5163065.html

Enter the predictors in separate levels such as age and gender in level 1, then other predictors in a subsequent level.  Then you can look at the effect of the other predictors beyond the other two, in effect "controlling" for them.

On Sat, Jan 21, 2012 at 1:00 PM, ishaybarat [via SPSSX Discussion] <[hidden email]> wrote:

Is there a way to adjust for...

I study a population of 900 hip fracture elderly. This type of patient has extreme high mortality (10% at 30 days and 30% at 1 year). The strongest predictors for death are age and gender. These two overshadow any other possible predictor (like co-morbidity, complications etc).
Is there a way to adjust for these two predictors without the need of stratifying the data according to age and gender?

I used the SPSS logistic regression were the dependent variable is dead/alive and the rest are covariates. Method is Enter.

Thanks

 
 

*¸..• ´¨)) -:¦:-        *
    ¸.•´ .
  (( -:¦:- * Ishay *  -:¦:-
    ´•..          ..•´
               ((¸¸.•´* -:¦:-  

---

If you reply to this email, your message will be added to the discussion below:

http://spssx-discussion.1045642.n5.nabble.com/Is-there-a-way-to-adjust-for-tp5163060p5163060.html

To start a new topic under SPSSX Discussion, email [hidden email]
To unsubscribe from SPSSX Discussion, click here.
NAML