Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: RE: crude odds ratio (crude?)


From   Richard Herrell <rherre2@uic.edu>
To   "'statalist@hsphsun2.harvard.edu'" <statalist@hsphsun2.harvard.edu>
Subject   Re: st: RE: crude odds ratio (crude?)
Date   Wed, 9 Oct 2002 08:35:34 -0500 (CDT)


The crude odds ratio is the unadjusted odds ratio.  ORs may be adjusted
for confounding factors using either stratification methods (Mantel
Haenszel ORs) or logistic regression.  The calculation from a 2 x 2 table
(ad/bd) is the ML estimate of the crude OR and should be identical to the
OR from a logistic model with a single dichotomous IV.  The Mantel
Haenszel methods are available in Stata also (see the epitab section of
the reference).  


=============================================
Richard Herrell, Ph.D.
Section on Developmental Genetic Epidemiology
Mood and Anxiety Disorders Program
National Institute of Mental Health
National Institutes of Health
15K North Drive, Rm. 208 (MSC 2670)
Bethesda, MD 20892-2670
Office:  301/496-3459
Fax:     301/402-6100
email:   richard.herrell@nih.gov
 




On Wed, 9 Oct 2002, FEIVESON, ALAN H. (AL) (JSC-SD) (NASA) wrote:

> This is a guess - but the term "crude" odds ratio might mean the odds ratio
> estimated solely from the values of y (without regard to the x's).
> 
>  i.e. "crude"odds =  (no. of y's = 1)/(no. of y's = 0)
> 
> Al Feiveson
> 
> 
> -----Original Message-----
> From: Jocelyne Séguin [mailto:jocelyne@dsuper.net]
> Sent: Wednesday, October 09, 2002 7:11 AM
> To: statalist@hsphsun2.harvard.edu
> Subject: st: crude odds ratio (crude?)
> 
> 
> I have to perform logistic regressions.
> For references, I use:
> Stata (manual and software)
> Applied Logistic Regression (Hosmer & Lemeshow)
> 
> I'm reading some articles where logistic regressions are used:  crude
> odds
> ratio are reported.  Here, crude seems to be a technical word.  Crude
> odds
> ratio is not in the index of Applied Logistic Regression.  From Stata, a
> net
> search with crude as a key word (crude, crude odds ratio) produced not
> matches.
> 
> Suppose that y , x1, x2, x3, x4, x5 are variables coded 0-1.
> Here, y is the dependent variable,
> and x1, ..., x5 are the independent variables.
> I have two questions.
> 
> When crude odds ratio of x1 are reported,
> does it come from the syntax
> logistic y x1 ?
> 
> When odds ratio of x1 adjusted for x2, x3 and x4, are reported
> does it come from the syntax
> logistic y x1 x2 x3 x4 ?
> 
> Thank you.
> 
> 
> 
> 
> *
> *   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/
> *
> *   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/
> 

*
*   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