R version 3.2.3 (2015-12-10) -- "Wooden Christmas-Tree"
Copyright (C) 2015 The R Foundation for Statistical Computing
Platform: x86_64-pc-linux-gnu (64-bit)

R is free software and comes with ABSOLUTELY NO WARRANTY.
You are welcome to redistribute it under certain conditions.
Type 'license()' or 'licence()' for distribution details.

  Natural language support but running in an English locale

R is a collaborative project with many contributors.
Type 'contributors()' for more information and
'citation()' on how to cite R or R packages in publications.

Type 'demo()' for some demos, 'help()' for on-line help, or
'help.start()' for an HTML browser interface to help.
Type 'q()' to quit R.

> 
> # we do example 9.2.4 in Agresti
> 
> udata <- read.table("http://www.stat.umn.edu/geyer/5421/data/table-9.3.txt",
+     header = TRUE)
> udata
    a   c   m count
1 Yes Yes Yes   911
2 Yes Yes  No   538
3 Yes  No Yes    44
4 Yes  No  No   456
5  No Yes Yes     3
6  No Yes  No    43
7  No  No Yes     2
8  No  No  No   279
> 
> gout <- glm(count ~ a * c * m, data = udata, family = poisson)
> summary(gout)

Call:
glm(formula = count ~ a * c * m, family = poisson, data = udata)

Deviance Residuals: 
[1]  0  0  0  0  0  0  0  0

Coefficients:
               Estimate Std. Error z value Pr(>|z|)    
(Intercept)     5.63121    0.05987  94.060  < 2e-16 ***
aYes            0.49128    0.07601   6.464 1.02e-10 ***
cYes           -1.87001    0.16383 -11.414  < 2e-16 ***
mYes           -4.93806    0.70964  -6.959 3.44e-12 ***
aYes:cYes       2.03538    0.17576  11.580  < 2e-16 ***
aYes:mYes       2.59976    0.72698   3.576 0.000349 ***
cYes:mYes       2.27548    0.92746   2.453 0.014149 *  
aYes:cYes:mYes  0.58951    0.94236   0.626 0.531600    
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

(Dispersion parameter for poisson family taken to be 1)

    Null deviance:  2.8515e+03  on 7  degrees of freedom
Residual deviance: -1.2590e-13  on 0  degrees of freedom
AIC: 65.043

Number of Fisher Scoring iterations: 3

> 
> stout <- step(gout)
Start:  AIC=65.04
count ~ a * c * m

        Df Deviance    AIC
- a:c:m  1  0.37399 63.417
<none>      0.00000 65.043

Step:  AIC=63.42
count ~ a + c + m + a:c + a:m + c:m

       Df Deviance    AIC
<none>        0.37  63.42
- a:m   1    92.02 153.06
- a:c   1   187.75 248.80
- c:m   1   497.37 558.41
> summary(stout)

Call:
glm(formula = count ~ a + c + m + a:c + a:m + c:m, family = poisson, 
    data = udata)

Deviance Residuals: 
       1         2         3         4         5         6         7         8  
 0.02044  -0.02658  -0.09256   0.02890  -0.33428   0.09452   0.49134  -0.03690  

Coefficients:
            Estimate Std. Error z value Pr(>|z|)    
(Intercept)  5.63342    0.05970  94.361  < 2e-16 ***
aYes         0.48772    0.07577   6.437 1.22e-10 ***
cYes        -1.88667    0.16270 -11.596  < 2e-16 ***
mYes        -5.30904    0.47520 -11.172  < 2e-16 ***
aYes:cYes    2.05453    0.17406  11.803  < 2e-16 ***
aYes:mYes    2.98601    0.46468   6.426 1.31e-10 ***
cYes:mYes    2.84789    0.16384  17.382  < 2e-16 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

(Dispersion parameter for poisson family taken to be 1)

    Null deviance: 2851.46098  on 7  degrees of freedom
Residual deviance:    0.37399  on 1  degrees of freedom
AIC: 63.417

Number of Fisher Scoring iterations: 4

> 
> 
> proc.time()
   user  system elapsed 
  0.141   0.011   0.266