Examples

Cytel's LogXact 5 vs. SAS's PROC LOGISTIC:
Relationship between Genetic Mutation and Colon Cancer

(Source: Dorota Gertig, David Hunter, and Donna Spiegelman (2000) -- Harvard School of Public Health)

A case-control study of colon cancer investigated the relationship between the presence/absence of a genetic mutation and the presence/absence of colon cancer.
(771 observations, 4 covariates.)

The following covariates were used: 

AGECAT = Age category of subject
EXP 
GENE: 1 = presence of genetic mutation, 0 = absence of genetic mutation
AGECAT was specified as a factor variable.

The results are presented below. Note that SAS fails to fit the logistic regression model -- only LogXact 5 can do it.

LOGXACT 5 RESULTS

=============================================================================================
Parameter Estimates
=============================================================================================
                   Point Estimate            Confidence interval and P-value for Beta
         Type  Beta        SE(Beta)    Type        95.0%     C.I.            Pvalue      SE      
                                                   Lower       Upper       2*1-sided   
=============================================================================================
AGECAT_0  MLE  -0.5534     0.2919      Asymptotic  -1.1255     0.0187      0.0580              
          CMLE -0.5530     0.2920      Monte Carlo -1.1597     0.0495      0.0742      0.0038    
                                       ( Seed=1035223637,Samples=10000 )

AGECAT_1  MLE  -0.7577     0.3188      Asymptotic  -1.3825     -0.1329     0.0175              
          CMLE -0.7529     0.3210      Monte Carlo -1.4451     -0.0960     0.0196      0.0020    
                                       ( Seed=1035223702,Samples=10000 )

AGECAT_2  MLE  -0.5734     0.2957      Asymptotic  -1.1530     0.0062      0.0525              
          CMLE -0.5714     0.2931      Monte Carlo -1.1890     0.0385      0.0702      0.0037    
                                       ( Seed=1035223764,Samples=10000 )

AGECAT_3  MLE  0.1100      0.2572      Asymptotic  -0.3941     0.6141      0.6690              
          CMLE 0.1087      0.2577      Monte Carlo -0.4367     0.6365      0.7718      0.0097    
                                       ( Seed=1035223821,Samples=10000 )

EXP       MLE  0.1072      0.1332      Asymptotic  -0.1540     0.3683      0.4213              
          CMLE 0.1073      0.1330      Monte Carlo -0.1599     0.3738      0.4682      0.0085    
                                       ( Seed=1035223872,Samples=10000 )

GENE      MLE  -1.7985     0.7516      Asymptotic  -3.2716     -0.3255     0.0167              
          CMLE -1.7819     0.7495      Monte Carlo -3.8377     -0.3201     0.0080      0.0013    
                                       ( Seed=1035223891,Samples=10000 )

GENE.EXP  MLE  1.1224      0.4763      Asymptotic  0.1888      2.0559      0.0185              
          CMLE 1.0959      0.4671      Monte Carlo 0.1265      2.2284      0.0222      0.0021    
                                       ( Seed=1035223937,Samples=10000 )
%CONST    MLE  -1.2233     0.2243      Asymptotic  -1.6629     -0.7837     0.0000              
=============================================================================================

Analysis time: 00:05:55
=============================================================================================
SAS's PROC LOGISTIC RESULTS
WARNING: There is not enough memory available for exact computations.
Try it yourself!
The links below include data files and SAS code that you can download.

LOGXACT 5--
Download LogXact data
View Instructions for LogXact 5 analysis

PROC LOGISTIC--
Download SAS code (includes data)