Features and Specifications

LogXact® Features

• Powerful Monte Carlo procedures enable fast exact inference even for larger data sets
• Exploration Mode tells you how long a problem will take before you commit computing resources
• Exploration Mode also allows use of customized exact algorithms to optimize computer performance for difficult problems
• See LogXact overview page for more details

Thorough Documentation

LogXact now includes a detailed online user manual carefully documenting all the binary logistic and Poisson regression methods. Both the online and optional printed manual are packed with relevant step-by-step examples of how to run each procedure. There are also examples illustrating handling of large datasets. Cytel maintains a high standard for thorough documentation and instruction.

Validation of LogXact® Results

The statistical results computed by LogXact engines are validated by rigorous and extensive quality assurance testing. Data sets have been collected from standard textbooks, published articles by both Cytel and LogXact users for testing across a wide range of possible input values.

Method 1: Comparison of exact p-values, asymptotic p-values, permutation distributions and exact parameter estimates computed by LogXact engines and corresponding values.

Method 2: Cross-validation (within LogXact) of exact p-values with Monte Carlo p-value confidence intervals using a very large Monte Carlo sample size (typically in excess of a million tables). The Monte Carlo intervals should include the exact p-value up to the confidence level of the settings.

Method 3: Comparison of asymptotic values with the results from SAS, SPSS and S-PLUS.

Method 4: Comparison of exact p-values and exact parameter estimates with results from StatXact. While the algorithms used in StatXact are quite different than those used for LogXact, certain inference in logistic regression models can be recast as StatXact tests.

StatXact statistical procedures that validate the logistic regression procedure of LogXact include:

• Wilcoxon-Mann-Whitney test
• Generalized Wilcoxon-Gehan test
• Normal scores test
• Savage scores test
• Logrank test
• Confidence interval for the odds ratio of two binomials
• Homogeneity of odds-ratios for stratified 2 x 2 tables
• Confidence interval for the common odds ratio for stratified 2 x 2 tables
• Wilcoxon-Mann-Whitney test for stratified 2 x C tables
• Normal scores test for stratified 2 x C tables
• Savage test for stratified 2 x C Tables
• Cochran-Armitage trend est for stratified 2 x C tables
• Permutation test with general scores for stratified 2 x C tables