# [R] glm fit

Richardson, Patrick Patrick.Richardson at vai.org
Fri May 8 13:58:11 CEST 2009

```Interesting. Now the fifth homework question you have posted here. As was stated before (by several members) this is not a homework forum.

Patrick

-----Original Message-----
From: r-help-bounces at r-project.org [mailto:r-help-bounces at r-project.org] On Behalf Of mathallan
Sent: Friday, May 08, 2009 5:50 AM
To: r-help at r-project.org
Subject: [R] glm fit

Hi, I try to ask here, because I hope someone will help me understand this
problem-

I have fittet a glm in R with the results

> glm1 <-
> summary(glm1)

Call:
glm(formula = log(claims) ~ log(sum) * as.factor(grp), family =

Deviance Residuals:
Min       1Q   Median       3Q      Max
-6.6836  -1.3626  -0.2576   1.2038   8.2480

Coefficients:
Estimate Std. Error      t value   Pr(>|t|)
(Intercept)                     3.525657   0.436102   8.084 8.18e-16 ***
log(sum)                        0.334288   0.025668  13.024  < 2e-16 ***
as.factor(grp)2               0.434262   0.976240   0.445   0.6565
as.factor(grp)3               3.666490   1.436471   2.552   0.0107 *
as.factor(grp)4               0.040782   1.024730   0.040   0.9683
log(sum):as.factor(grp)2  0.007719   0.061914   0.125   0.9008
log(sum):as.factor(grp)3 -0.209986   0.091578  -2.293   0.0219 *
log(sum):as.factor(grp)4  0.059342   0.067320   0.881   0.3781
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

(Dispersion parameter for gaussian family taken to be 3.693731)

Null deviance: 15839  on 4035  degrees of freedom
Residual deviance: 14878  on 4028  degrees of freedom
AIC: 16737

Number of Fisher Scoring iterations: 2

But i'm not sure what I get out of the summary. What does it tell me?

How should the formula for Y look like, out from the summary? Is it
something like

Y=0.334288*X_sum+0.434262*X_2+  ??

And when I get a expression for Y, what does it tell me? Is it an expected
expression?

--
View this message in context: http://www.nabble.com/glm-fit-tp23443121p23443121.html
Sent from the R help mailing list archive at Nabble.com.

______________________________________________
R-help at r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help