R help - Jul 2005 - logistic regression: categorical value, and multinomial

I have two questions:

1. If I want to do a binomial logit, how to handle the
categorical response variable? Data for the response
variables are not numerical, but text.

2. What if I want to do a multinomial logit, still
with categorical response variable? The variable has 5
non-numerical response levels, I have to do it with a
multinomial logit.

Any input is highly appreciated! Thanks!

Ed

> d<-data.frame(y=sample(letters[1:2],100,T),x=rnorm(100))
> head(d,10)
   y           x
1  b  0.55915620
2  b  0.87575380
3  b -0.13093156
4  b  0.75925729
5  b  0.40233427
6  b  1.34685918
7  a  1.10487752
8  a -2.27456596
9  a  1.65919787
10 b  0.05095611
> glm(y~x,data=d,family=binomial)
Call:  glm(formula = y ~ x, family = binomial, data = d) 

Coefficients:
(Intercept)            x  
     0.2771       0.5348  

Degrees of Freedom: 99 Total (i.e. Null);  98 Residual
Null Deviance:      136.1 
Residual Deviance: 129.5        AIC: 133.5 


======= 2005-07-28 00:22:55 伳侜佋佢伬伌佇伵佒佇佇伌伒伬仯伜======
>I have two questions:
>
>1. If I want to do a binomial logit, how to handle the
>categorical response variable? Data for the response
>variables are not numerical, but text.
>
>2. What if I want to do a multinomial logit, still
>with categorical response variable? The variable has 5
>non-numerical response levels, I have to do it with a
>multinomial logit.
>
>Any input is highly appreciated! Thanks!
>
>Ed
>
>______________________________________________
>R-help at stat.math.ethz.ch mailing list
>https://stat.ethz.ch/mailman/listinfo/r-help
>PLEASE do read the posting guide!
http://www.R-project.org/posting-guide.html
= = = = = = = = = = = = = = = = = = = 			


 

2005-07-28

------
Deparment of Sociology
Fudan University

Blog:http://sociology.yculblog.com

Dear Ed,

See ?glm for fitting binomial logit models, and ?multinom (in the nnet
package) for multinomial logit models. Neither function will handle a
character ("text") variable as the response, but you could easily
convert
the variable to a factor.

John

--------------------------------
John Fox
Department of Sociology
McMaster University
Hamilton, Ontario
Canada L8S 4M4
905-525-9140x23604
http://socserv.mcmaster.ca/jfox 
-------------------------------- 
> -----Original Message-----
> From: r-help-bounces at stat.math.ethz.ch 
> [mailto:r-help-bounces at stat.math.ethz.ch] On Behalf Of Haibo Huang
> Sent: Wednesday, July 27, 2005 11:23 AM
> To: r-help at stat.math.ethz.ch
> Subject: [R] logistic regression: categorical value, and multinomial
> 
> I have two questions:
> 
> 1. If I want to do a binomial logit, how to handle the 
> categorical response variable? Data for the response 
> variables are not numerical, but text.
> 
> 2. What if I want to do a multinomial logit, still with 
> categorical response variable? The variable has 5 
> non-numerical response levels, I have to do it with a 
> multinomial logit.
> 
> Any input is highly appreciated! Thanks!
> 
> Ed