Shipping example, 1 categorical and 2 cts. covs.  
Result of printing glm output

Call:  glm(formula = cases ~ type + built, family = poisson, data = ships)

Coefficients:
(Intercept)        typeB        typeC        typeD        typeE  
   1.456470     1.795720    -1.252763    -0.904456    -0.123139  
      built  
   0.005042  

Degrees of Freedom: 33 Total (i.e. Null);  28 Residual
Null Deviance:	    614.5 
Residual Deviance: 170.5 	AIC: 280.3
Result of printing glm summary

Call:
glm(formula = cases ~ type + built, family = poisson, data = ships)

Deviance Residuals: 
    Min       1Q   Median       3Q      Max  
-4.7632  -2.1681  -0.5528   0.8157   3.9734  

Coefficients:
             Estimate Std. Error z value Pr(>|z|)    
(Intercept)  1.456470   0.704790   2.067  0.03878 *  
typeB        1.795720   0.166620  10.777  < 2e-16 ***
typeC       -1.252763   0.327327  -3.827  0.00013 ***
typeD       -0.904456   0.287459  -3.146  0.00165 ** 
typeE       -0.123139   0.234900  -0.524  0.60013    
built        0.005042   0.010331   0.488  0.62551    
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

(Dispersion parameter for poisson family taken to be 1)

    Null deviance: 614.54  on 33  degrees of freedom
Residual deviance: 170.47  on 28  degrees of freedom
AIC: 280.34

Number of Fisher Scoring iterations: 6


 Shipping example, 2 categorical covs.  

Call:
glm(formula = cases ~ type + factor(built) + offset(log(smar)), 
    family = poisson, data = ships)

Deviance Residuals: 
    Min       1Q   Median       3Q      Max  
-1.9538  -1.0525  -0.4846   0.5779   2.4183  

Coefficients:
                Estimate Std. Error z value Pr(>|z|)    
(Intercept)     -6.26892    0.21241 -29.513  < 2e-16 ***
typeB           -0.55861    0.17767  -3.144  0.00167 ** 
typeC           -0.68388    0.32908  -2.078  0.03769 *  
typeD           -0.07032    0.29071  -0.242  0.80887    
typeE            0.30425    0.23581   1.290  0.19698    
factor(built)65  0.75347    0.14855   5.072 3.94e-07 ***
factor(built)70  0.96530    0.16369   5.897 3.70e-09 ***
factor(built)75  0.70828    0.22153   3.197  0.00139 ** 
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

(Dispersion parameter for poisson family taken to be 1)

    Null deviance: 146.328  on 33  degrees of freedom
Residual deviance:  49.355  on 26  degrees of freedom
AIC: 163.22

Number of Fisher Scoring iterations: 5


 Shipping example, 3 categorical covs.  

Call:
glm(formula = cases ~ type + factor(built) + factor(period) + 
    offset(log(smar)), family = poisson, data = ships)

Deviance Residuals: 
    Min       1Q   Median       3Q      Max  
-1.6768  -0.8293  -0.4370   0.5058   2.7912  

Coefficients:
                 Estimate Std. Error z value Pr(>|z|)    
(Intercept)      -6.40590    0.21744 -29.460  < 2e-16 ***
typeB            -0.54334    0.17759  -3.060  0.00222 ** 
typeC            -0.68740    0.32904  -2.089  0.03670 *  
typeD            -0.07596    0.29058  -0.261  0.79377    
typeE             0.32558    0.23588   1.380  0.16750    
factor(built)65   0.69714    0.14964   4.659 3.18e-06 ***
factor(built)70   0.81843    0.16977   4.821 1.43e-06 ***
factor(built)75   0.45343    0.23317   1.945  0.05182 .  
factor(period)75  0.38447    0.11827   3.251  0.00115 ** 
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

(Dispersion parameter for poisson family taken to be 1)

    Null deviance: 146.328  on 33  degrees of freedom
Residual deviance:  38.695  on 25  degrees of freedom
AIC: 154.56

Number of Fisher Scoring iterations: 5


 Result with interaction.  Note infinite ets.  

Call:
glm(formula = cases ~ type * factor(built) + offset(log(smar)), 
    family = poisson, data = ships)

Deviance Residuals: 
     Min        1Q    Median        3Q       Max  
-1.85473  -0.37532  -0.00007   0.28147   2.17190  

Coefficients:
                        Estimate Std. Error z value Pr(>|z|)
(Intercept)             -23.7962  6467.9270  -0.004    0.997
typeB                    16.9799  6467.9270   0.003    0.998
typeC                    17.0329  6467.9271   0.003    0.998
typeD                    -0.5960  9075.0372   0.000    1.000
typeE                     0.6870 11432.1994   0.000    1.000
factor(built)65          18.0505  6467.9271   0.003    0.998
factor(built)70          18.4845  6467.9270   0.003    0.998
factor(built)75          18.4781  6467.9270   0.003    0.998
typeB:factor(built)65   -17.3238  6467.9271  -0.003    0.998
typeC:factor(built)65   -18.5713  6467.9272  -0.003    0.998
typeD:factor(built)65   -18.4210 11220.0344  -0.002    0.999
typeE:factor(built)65     0.5863 11432.1994   0.000    1.000
typeB:factor(built)70   -17.5544  6467.9270  -0.003    0.998
typeC:factor(built)70   -17.5542  6467.9271  -0.003    0.998
typeD:factor(built)70     1.1222  9075.0372   0.000    1.000
typeE:factor(built)70    -0.6491 11432.1994   0.000    1.000
typeB:factor(built)75   -17.6417  6467.9271  -0.003    0.998
typeC:factor(built)75   -17.3279  6467.9272  -0.003    0.998
typeD:factor(built)75    -0.3256  9075.0372   0.000    1.000
typeE:factor(built)75    -1.6641 11432.1994   0.000    1.000

(Dispersion parameter for poisson family taken to be 1)

    Null deviance: 146.328  on 33  degrees of freedom
Residual deviance:  25.208  on 14  degrees of freedom
AIC: 163.07

Number of Fisher Scoring iterations: 17


 Death penalty data  

 Two parameterizations for Model ignoring race of victem  

Call:
glm(formula = we ~ rdc + lc + rdc * lc, family = poisson, data = nonprim)

Deviance Residuals: 
      1        2        3        4        9       10       11  
 0.8199   2.7092  -0.9057  -4.3589  -2.7579   6.5252   2.4898  
     12  
-9.2709  

Coefficients:
                        Estimate Std. Error z value Pr(>|z|)    
(Intercept)               2.1401     0.2425   8.824   <2e-16 ***
rdcWhite defend.          0.1112     0.3338   0.333    0.739    
lcLive                    2.1707     0.2560   8.479   <2e-16 ***
rdcWhite defend.:lcLive  -0.1664     0.3539  -0.470    0.638    
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

(Dispersion parameter for poisson family taken to be 1)

    Null deviance: 395.92  on 7  degrees of freedom
Residual deviance: 170.16  on 4  degrees of freedom
AIC: 213.85

Number of Fisher Scoring iterations: 5


 Simultaneously estimate all three common odds ratios  

Call:
glm(formula = we ~ rdc * lc + lc * rvc + rdc * rvc, family = poisson, 
    data = nonprim)

Deviance Residuals: 
       1         2         3         4         9        10  
-0.09723   0.07514   0.13543  -0.80702   0.04525  -0.02832  
      11        12  
-0.03303   0.10988  

Coefficients:
                                 Estimate Std. Error z value
(Intercept)                        1.7360     0.4092   4.242
rdcWhite defend.                  -2.8579     0.5195  -5.502
lcLive                             2.8421     0.4203   6.761
rvcWhite victim                    0.6911     0.4947   1.397
rdcWhite defend.:lcLive            0.4402     0.4009   1.098
lcLive:rvcWhite victim            -1.3242     0.5193  -2.550
rdcWhite defend.:rvcWhite victim   3.3580     0.3820   8.791
                                 Pr(>|z|)    
(Intercept)                      2.21e-05 ***
rdcWhite defend.                 3.76e-08 ***
lcLive                           1.37e-11 ***
rvcWhite victim                    0.1624    
rdcWhite defend.:lcLive            0.2722    
lcLive:rvcWhite victim             0.0108 *  
rdcWhite defend.:rvcWhite victim  < 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: 395.91531  on 7  degrees of freedom
Residual deviance:   0.70074  on 1  degrees of freedom
AIC: 50.382

Number of Fisher Scoring iterations: 4


 Traditional estimates for comparison.  

	Mantel-Haenszel chi-squared test with continuity correction

data:  xtabs(we ~ rdc + lc + rvc, data = nonprim)
Mantel-Haenszel X-squared = 0.79633, df = 1, p-value =
0.3722
alternative hypothesis: true common odds ratio is not equal to 1
95 percent confidence interval:
 0.7096435 3.4914549
sample estimates:
common odds ratio 
         1.574067 


 Poisson regression for Resp. Cancer Deaths  
                  Estimate Std. Error    z value      Pr(>|z|)
(Intercept)     -8.3354313 0.30066091 -27.723694 3.617907e-169
factor(period)2  0.5415218 0.21510528   2.517473  1.181999e-02
factor(period)3  0.7124689 0.21414554   3.327031  8.777650e-04
factor(period)4  0.6925791 0.23017823   3.008882  2.622112e-03
factor(hire)2   -0.4828380 0.15266151  -3.162801  1.562590e-03
factor(ageg)2    1.3816528 0.24675608   5.599265  2.152619e-08
factor(ageg)3    2.1692010 0.24439792   8.875693  6.949909e-19
factor(ageg)4    2.3088425 0.26987482   8.555235  1.176290e-17
exp              0.3174323 0.05371368   5.909710  3.427098e-09

 Poisson regression for Circulatory Deaths  
                   Estimate Std. Error     z value      Pr(>|z|)
(Intercept)     -6.07404150 0.12414604 -48.9265836  0.000000e+00
factor(period)2  0.18866370 0.09564960   1.9724463  4.855868e-02
factor(period)3  0.22527782 0.09462166   2.3808271  1.727382e-02
factor(period)4  0.13500748 0.10074529   1.3400873  1.802170e-01
factor(hire)2    0.02073941 0.07135351   0.2906572  7.713135e-01
factor(ageg)2    1.05337430 0.09959307  10.5767835  3.818421e-26
factor(ageg)3    1.80339197 0.09899671  18.2166864  3.805112e-74
factor(ageg)4    2.67187802 0.10394313  25.7051921 1.022650e-145
exp              0.04452792 0.02952771   1.5080043  1.315534e-01

 Logistic regression for proportional mortality  
                  Estimate Std. Error   z value     Pr(>|z|)
(Intercept)     -2.3070781 0.33692841 -6.847384 7.521281e-12
factor(period)2  0.3379935 0.23939707  1.411853 1.579932e-01
factor(period)3  0.4523566 0.23630087  1.914325 5.557867e-02
factor(period)4  0.5553701 0.25439285  2.183120 2.902696e-02
factor(hire)2   -0.4479115 0.16940110 -2.644088 8.191124e-03
factor(ageg)2    0.3242341 0.26783869  1.210557 2.260651e-01
factor(ageg)3    0.3881245 0.26576181  1.460422 1.441740e-01
factor(ageg)4   -0.2910999 0.29026972 -1.002860 3.159284e-01
exp              0.2736544 0.06292414  4.348957 1.367868e-05

 Logistic regression for prostate date, ungrouped  

 Logistic regression for prostate date, grouped  
              Estimate Std. Error    z value     Pr(>|z|)
(Intercept) -1.5869651  0.3658393 -4.3378749 0.0000143867
frx2         0.2712883  0.4991369  0.5435148 0.5867754225
frx3         1.0273493  0.4608794  2.2291066 0.0258068132
frx4         0.4383423  0.4849243  0.9039398 0.3660273124
              Estimate Std. Error    z value     Pr(>|z|)
(Intercept) -1.5869651  0.3658392 -4.3378762 1.438661e-05
frx2         0.2712883  0.4991369  0.5435148 5.867754e-01
frx3         1.0273493  0.4608793  2.2291070 2.580679e-02
frx4         0.4383423  0.4849243  0.9039397 3.660274e-01

 Probit regression  
                 Estimate Std. Error    z value     Pr(>|z|)
(Intercept)    -0.9549111  0.2039531 -4.6820137 2.840704e-06
as.factor(rx)2  0.1538166  0.2826380  0.5442177 5.862917e-01
as.factor(rx)3  0.6061554  0.2673043  2.2676604 2.334991e-02
as.factor(rx)4  0.2509893  0.2765946  0.9074269 3.641811e-01

 Death penalty log. reg. w/o interactions to give MH.  
              Estimate Std. Error   z value     Pr(>|z|)
(Intercept)  2.8421051  0.4203344  6.761533 1.365391e-11
rvfBlack    -1.3242128  0.5193427 -2.549786 1.077891e-02
rdfBlack     0.4402222  0.4008880  1.098118 2.721531e-01

 Death penalty data with interactions  
                    Estimate   Std. Error     z value     Pr(>|z|)
(Intercept)         2.782952    0.4206851  6.61528439 3.708381e-11
rvfBlack           -1.229603    0.5358319 -2.29475533 2.174715e-02
rdfBlack           14.242955 1006.6074820  0.01414946 9.887107e-01
rvfBlack:rdfBlack -13.857940 1006.6075666 -0.01376697 9.890159e-01
Analysis of Deviance Table

Model: binomial, link: logit

Response: surv

Terms added sequentially (first to last)


        Df Deviance Resid. Df Resid. Dev
NULL                        6     226.51
rvf      1   6.2497         5     220.26
rdf      1   1.1812         4     219.08
rvf:rdf  1   0.7007         3     218.38