R help - May 2012 - need help in logistic regression

Hello everyone,

I tried to understand the relationship between temperature and the
death of an organism by using logistic regression.
glm(formula = Death ~ Temperature, family = binomial(link = "logit"),
data = mydata)

Coefficients:
                           Estimate Std. Error z value Pr(>|z|)
(Intercept)          -87.9161     7.7987  -11.27   <2e-16 ***
Temperature        2.9532     0.2616   11.29   <2e-16 ***
>From the above summary, I could understand that log odds of death -87.9161 +
2.9532*Temperature.  Odds=exp(log[odds]).  Probability odds/(1+odds)
Assuming my data is randomly normal distributed with (u=0, standard
deviation=0.35), and I want to run it for n=10,000, how do I get to
probability from log odds?

Regards,
Eddie

Look at
?predict.glm

mydata.glm <- glm(formula = Death ~ Temperature, family = binomial(link
"logit"),
data = mydata)

and see that predict(mydata.glm, type="response") gives the
predictions on
the probability scale.

On Mon, May 28, 2012 at 10:16 AM, eddie smith <eddieatr@gmail.com> wrote:
> Hello everyone,
>
> I tried to understand the relationship between temperature and the
> death of an organism by using logistic regression.
> glm(formula = Death ~ Temperature, family = binomial(link =
"logit"),
> data = mydata)
>
> Coefficients:
>                           Estimate Std. Error z value Pr(>|z|)
> (Intercept)          -87.9161     7.7987  -11.27   <2e-16 ***
> Temperature        2.9532     0.2616   11.29   <2e-16 ***
>
> >From the above summary, I could understand that log odds of death >
-87.9161 + 2.9532*Temperature.  Odds=exp(log[odds]).  Probability >
odds/(1+odds)
>
> Assuming my data is randomly normal distributed with (u=0, standard
> deviation=0.35), and I want to run it for n=10,000, how do I get to
> probability from log odds?
>
> Regards,
> Eddie
>
> ______________________________________________
> 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<http://www.r-project.org/posting-guide.html>
> and provide commented, minimal, self-contained, reproducible code.
>
	[[alternative HTML version deleted]]