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, is already up and running.

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

Re: st: logistic regression predictors

From   Maarten buis <>
Subject   Re: st: logistic regression predictors
Date   Sun, 18 Jul 2010 04:57:41 -0700 (PDT)

--- On Sun, 18/7/10, lilian tesmann wrote:
> I am trying to predict mortality rates in a specific
> population of clients.
> I encountered two problems and would be really grateful for
> any insights or suggestions.
> (1) We have one predictor – a health condition, which is
> present in only 5% of population but over70% of people with
> that condition die. Not surprisingly OR is very large (from
> 25 to 50). The purpose of the analysis is to obtain
> individual predictions, but they are hugely influenced by
> this health condition. Could anyone suggest how to deal with
> this problem?

I don't understand what the problem is: if you want individual
predictions then you want those predictions to  be influenced
by that health condition.
> (2) Another problem is that in this very specific clinical
> population another two health conditions, which are usually
> very significant predictors of death, have OR=0.3-0.5. The
> result it has on prediction is that according to my model,
> sicker people have a lower risk of dying. 

That result is consistent with the odds ratios (less than 1 
means a negative relation, i.e. more of x --> less of y).
Remember that odds ratios are ratios, so an odds ratio of
.3 means that the odds of death with the condition is only 
30% of the odds of death without the condition. If that 
does not make substantive sense, take a look at wether
these variables were coded the right way. I don't think 
this is a collinearity problem.

Hope this helps,

Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen


*   For searches and help try:

© Copyright 1996–2016 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index