R help - Sep 2010 - Odds ratio from Logistic model in R

Hi, I am new to R. Anyone can explain the following from R-help or
anyone can direct me how to calculate odds ratio from logistic model in
R. Thank you very much. Guoya

 

 

Stefano <stecalza at tiscalinet.it
<https://stat.ethz.ch/mailman/listinfo/r-help> >
writes:
>Hi all.
> 
>A simple question.
>Is there a function to compute the Odds Ratio and its confidence
intervall, from 
>a logistic model (glm(.......,family=binomial....). I've written my
own, but 
>certainly someone did a better job.
 
I show a simple function to do this in my introductory notes available
from:
 
        http://www.myatt.demon.co.uk
 
basically it is:
 
        lreg.or <- function(model)
          {
          lreg.coeffs <- coef(summary(salex.lreg))
          lci <- exp(lreg.coeffs[ ,1] - 1.96 * lreg.coeffs[ ,2])
          or <- exp(lreg.coeffs[ ,1])
          uci <- exp(lreg.coeffs[ ,1] + 1.96 * lreg.coeffs[ ,2])
          lreg.or <- cbind(lci, or, uci)        
          lreg.or
          }
 

 


	[[alternative HTML version deleted]]

The output of logisitic procdure only gives you the log(odds-ratio) and the
associated standard error of the log(odds-ratio). You need to exponentiate
the log(odds-ratio) to get your odds ratio. The code tells you how to obtain
the odds ratio from log(odds-ratio).
-- 
View this message in context:
http://r.789695.n4.nabble.com/Odds-ratio-from-Logistic-model-in-R-tp2630277p2651963.html
Sent from the R help mailing list archive at Nabble.com.

Hi Guoya,

Is this what you are after?

# fit logistic model
my.glm <- glm(vs ~ mpg, data = mtcars, family = binomial(link =
"logit"))

# look at a summary
summary(my.glm)

# view the coefficients as odds ratios
exp(coef(my.glm))

Hope that helps,

Josh

On Fri, Sep 24, 2010 at 10:50 AM, Li, Guoya <Guoya_Li at bshsi.org>
wrote:
> Hi, I am new to R. Anyone can explain the following from R-help or
> anyone can direct me how to calculate odds ratio from logistic model in
> R. Thank you very much. Guoya
>
>
>
>
>
> Stefano <stecalza at tiscalinet.it
> <https://stat.ethz.ch/mailman/listinfo/r-help> > writes:
>>Hi all.
>>
>>A simple question.
>>Is there a function to compute the Odds Ratio and its confidence
> intervall, from
>>a logistic model (glm(.......,family=binomial....). I've written my
> own, but
>>certainly someone did a better job.
>
> I show a simple function to do this in my introductory notes available
> from:
>
> ? ? ? ?http://www.myatt.demon.co.uk
>
> basically it is:
>
> ? ? ? ?lreg.or <- function(model)
> ? ? ? ? ?{
> ? ? ? ? ?lreg.coeffs <- coef(summary(salex.lreg))
> ? ? ? ? ?lci <- exp(lreg.coeffs[ ,1] - 1.96 * lreg.coeffs[ ,2])
> ? ? ? ? ?or <- exp(lreg.coeffs[ ,1])
> ? ? ? ? ?uci <- exp(lreg.coeffs[ ,1] + 1.96 * lreg.coeffs[ ,2])
> ? ? ? ? ?lreg.or <- cbind(lci, or, uci)
> ? ? ? ? ?lreg.or
> ? ? ? ? ?}
>
>
>
>
>
> ? ? ? ?[[alternative HTML version deleted]]
>
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>


-- 
Joshua Wiley
Ph.D. Student, Health Psychology
University of California, Los Angeles
http://www.joshuawiley.com/

Hi Guoya,

One more option, using Joshua's example, would be:

# install.packages('epicalc')
require(epicalc)
logistic.display(my.glm)

HTH,
Jorge


On Fri, Sep 24, 2010 at 1:50 PM, Li, Guoya <> wrote:
> Hi, I am new to R. Anyone can explain the following from R-help or
> anyone can direct me how to calculate odds ratio from logistic model in
> R. Thank you very much. Guoya
>
>
>
>
>
> Stefano <stecalza at tiscalinet.it
> <https://stat.ethz.ch/mailman/listinfo/r-help> > writes:
> >Hi all.
> >
> >A simple question.
> >Is there a function to compute the Odds Ratio and its confidence
> intervall, from
> >a logistic model (glm(.......,family=binomial....). I've written my
> own, but
> >certainly someone did a better job.
>
> I show a simple function to do this in my introductory notes available
> from:
>
>        http://www.myatt.demon.co.uk
>
> basically it is:
>
>        lreg.or <- function(model)
>          {
>          lreg.coeffs <- coef(summary(salex.lreg))
>          lci <- exp(lreg.coeffs[ ,1] - 1.96 * lreg.coeffs[ ,2])
>          or <- exp(lreg.coeffs[ ,1])
>          uci <- exp(lreg.coeffs[ ,1] + 1.96 * lreg.coeffs[ ,2])
>          lreg.or <- cbind(lci, or, uci)
>          lreg.or
>          }
>
>
>
>
>
>        [[alternative HTML version deleted]]
>
> ______________________________________________
> R-help@r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
> http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>
	[[alternative HTML version deleted]]