[R] FW: Levels and GLM

From: Kuhn, Max <Max.Kuhn_at_pfizer.com>
Date: Sat 08 Jul 2006 - 06:17:06 EST

 

One correction... since you are fitting a logistic model, it is technically correct to say the "mean value of the linear predictor," instead of "mean response".

20 lashes for me.

Max

-----Original Message-----
From: Kuhn, Max
Sent: Friday, July 07, 2006 4:11 PM
To: 'r-help@stat.math.ethz.ch'
Subject: [R] Levels and GLM

jdrapp,

By default, R fits full rank models. If you are coming from SAS, you're probably used to less than full rank model parameterizations.

>From Section 11.1.1 of "An Introduction to R" at

http://cran.r-project.org/doc/manuals/R-intro.html#Contrasts

there is this:

 "What about a k-level factor A? The answer differs for unordered and  ordered factors. For unordered factors k - 1 columns are generated  for the indicators of the second, ..., kth levels of the factor.  (Thus the implicit parameterization is to contrast the response at  each level with that at the first.)"

So level "M" is the "reference cell". Assuming that data.logistic$Overall is continuous, the intercept is the estimate of the mean response when maj = "M" and data.logistic$Overall = 0. The estimate for majN is the difference between the reference cell (estimated
by the intercept) and the mean response when maj = "N" and data.logistic$Overall = 0.

You should check out ?model.matrix and ?contrasts.

Max

> I am using the as.factor command to use with glm. When I use the
command
>
> >maj <- as.factor(data.logistic$Majors)
> >maj
>
> I receive the following output:
> [1] M M N M M M M N N M M M N M M M M M M M M M M M N M N N M M N M
> M N M M M M M
> [40] N M N M M N M M M N M N M N M N N N M N M M M M M M N M N M M M
> M M N N M M M
> [79] M M M N N M M N M N M M M M M M M M M M M M M M M N M M M M M N
> M M M M M N M
> [118] M M M N M N N M M M M M M M M N M N M M M M M N M M M M N M M M
> N N M M M N M
> [157] M M M M M M M M M M M M M N M M N N M M N M M M M M M M M M M M
> M M N M N M M
> [196] M N M M M M M M M M N M M M M M M M M N M M M M M M M M M M M M
> M M N M M N N
> [235] M M M M M N M M M M M M N N M M N M M M M M M M M M M M M M M M
> M N M M M M N
> [274] N M M M M M M N M M M M M M M M M M N N M N M M M M M M M M M M
> N M N N M M M
> [313] M M M M M M M N M M M M M N M M M M M M M M M M M M M M M N M M
> M M M M M N M
> [352] M N M N M M N M M M M N M M M M M M M M M M N M M N N
> Levels: M N
>
> When I enter:
>
> > logistic.glm <- glm(data.logistic$X100.Yard.Average ~
data.logistic$Overall + maj, family=binomial)
> > logistic.glm
>
> I receive the following output:
>
> Call: glm(formula = data.logistic$X100.Yard.Average ~
> data.logistic$Overall + maj, family = binomial)
>
> Coefficients:
> (Intercept) data.logistic$Overall majN
> 2.38819 -0.02718 -0.18385
>
> Degrees of Freedom: 377 Total (i.e. Null); 375 Residual
> Null Deviance: 514.5
> Residual Deviance: 410.7 AIC: 416.7
>
> My question: Why is there no output for majM? Any help would be
> greatly appreciated



LEGAL NOTICE\ Unless expressly stated otherwise, this messag...{{dropped}}

R-help@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 Received on Sat Jul 08 06:20:07 2006

Archive maintained by Robert King, hosted by the discipline of statistics at the University of Newcastle, Australia.
Archive generated by hypermail 2.1.8, at Sat 08 Jul 2006 - 10:15:32 EST.

Mailing list information is available at https://stat.ethz.ch/mailman/listinfo/r-help. Please read the posting guide before posting to the list.