Statalist The Stata Listserver


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: Re: another aflogit issue


From   Marc Campo <mcam54@yahoo.com>
To   Marc Campo <mcam54@yahoo.com>, statalist@hsphsun2.harvard.edu
Subject   st: Re: another aflogit issue
Date   Tue, 31 Oct 2006 13:07:53 -0800 (PST)

Here is what I am doing:

.logistic incident_lowback age gender hours_week
second_job job_strain

aflogit job_strain

The regression runs fine but no AF!!

I have also tried this one:

.logistic incident_wrist age gender hours_week
second_job xfer position manual_total

.aflogit manual_total, ref(manual_total=3)

I removed the underscores and preserved the data.  No
help.  One possible clue....I primarily work in SPSS. 
The dataset was transferred using stat transfer.  
Those two variables are ones that I had to calculate
in SPSS as opposed to entering directly in SPSS.  

I could try renaming without underscores in SPSS and
retransferring............
--- Marc Campo <mcam54@yahoo.com> wrote:

> I keep running LR and then typing in aflogit for
> particular variables specifying a reference level. 
> For some variables, no problem.  For others, it says
> variable not found or abbreviation is incorrect.  I
> am
> typing in the right names.
> 
> the variable xfer runs.  the variables job_strain
> and
> manual_total do not.  Anyone know why?
> 
> thanks,
> Marc
> 
> --- Marc Campo <mcam54@yahoo.com> wrote:
> 
> > I am looking at a series of ordinal indep
> variables
> > individually while adjusting for background
> factors
> > with logistic regression.  I am entering these
> > varaibles as continuous as opposed to dummy
> coding. 
> >  
> > 
> > I want to use AFLOGIT for attributable fractions. 
> I
> > am not sure how this works with a continuous indep
> > variable however.  My vars are coded from 1-4 or
> > 1-5. 
> > 1 in each case is the lowest category.  The AF
> > instructions state to make the reference cat your
> > non
> > exposure category, so I have used 1.  Is the
> result
> > the AF for all other categories vs. 1 in that
> case? 
> > 
> > That's not what I want.  But with so few
> categories,
> > I
> > can't just take the middle value either. If it
> isn't
> > just 1 vs. all others, then my results should be
> > fine.
> > 
> > Any help is appreciated.
> > 
> 
> 

*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index