R help - Oct 2005 - GLM

Hello R-users,

I am a relatively new user of R and I have a question regarding glm. I want 
to run the function GLM on multiple individuals separately and then get 
means for summary statistics such as AIC and coef. Is there a way to do this 
in R without separately going through each individual and subsetting the 
dataset, getting the summary statistics and averaging them? For example, in 
the dataset below I would like to run the function:
>glm(Type~Dwater+Habitat, data=example, family=binomial())
on each individual separately and then get the average for the coef's Dwater
and Habitat for the 3 individuals.
>example
   Individual Type Dwater Habitat
1           1    0     40       0
2           1    1     80       1
3           1    0     30       0
4           1    1     90       0
5           2    0     15       1
6           2    1     95       1
7           2    0     20       0
8           2    1     75       1
9           3    0     15       0
10          3    1     60       1
11          3    0     10       1
12          3    1     95       0

Thanks,

Jeff.

Dear Jeff,

One way to do this is with by():

summaries <- by(example, Individual, function(data){ 
    mod <- glm(Type~Dwater+Habitat, data=data, family=binomial)
    list(AIC=AIC(mod), coef=coef(mod))
    })
    
sapply(summaries, function(x) x$coef)
rowMeans(sapply(summaries, function(x) x$coef))
sapply(summaries, function(x) x$AIC)

I hope this helps,
 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 Jeff Row
> Sent: Monday, October 31, 2005 12:01 PM
> To: r-help at stat.math.ethz.ch
> Subject: [R] GLM
> 
> Hello R-users,
> 
> I am a relatively new user of R and I have a question 
> regarding glm. I want to run the function GLM on multiple 
> individuals separately and then get means for summary 
> statistics such as AIC and coef. Is there a way to do this in 
> R without separately going through each individual and 
> subsetting the dataset, getting the summary statistics and 
> averaging them? For example, in the dataset below I would 
> like to run the function:
> 
> >glm(Type~Dwater+Habitat, data=example, family=binomial())
> 
> on each individual separately and then get the average for 
> the coef's Dwater and Habitat for the 3 individuals.
> 
> >example
>    Individual Type Dwater Habitat
> 1           1    0     40       0
> 2           1    1     80       1
> 3           1    0     30       0
> 4           1    1     90       0
> 5           2    0     15       1
> 6           2    1     95       1
> 7           2    0     20       0
> 8           2    1     75       1
> 9           3    0     15       0
> 10          3    1     60       1
> 11          3    0     10       1
> 12          3    1     95       0
> 
> Thanks,
> 
> Jeff.
> 
> ______________________________________________
> 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