Improved User Interface. The user interface is simpler and several ancillary features such as validation tests are now built-in instead of requiring stand-alone work outside of the linkage application. Details about the new interface and other changes are covered in Version 8.1 Help Pages.

Improved Data Simulation. Version 8.1 allows more accurate simulation of real data. First, more parameters are collected describing real data. These parameters are used instead of typical or average values to make simulated data closer to real data. Second, zip code populations are used to assign simulated locations so that more populous zips are more likely than less populous zips.

Improved Name and Address Standardization. Name and Address Standardization methods have been improved in Version 8.1 by adding many new rules. The new methods were developed and validated using a large number of actual names and addresses.

Improved Linkage Model. The statistical linkage model has been improved in several ways. Probabilities that data values are correct but different are now handled as match parameters, not data source parameters. Comparisons with tolerances are handled accurately in probability calculations without requiring ad hoc adjustments via X factors. Agree and disagree X factors that correct for dependent comparison outcomes are re-estimated as part of each Markov Chain Monte Carlo iteration rather than being fixed at prior estimates. Goodness of fit tables are prepared automatically if your project links simulated data.

Improved Triple Match. The user interface for triple matching has been revised to make it easier to set up match specifications. The triple linkage model is more robust because it incorporates dual match probabilities directly rather than estimating m and u probabilities for all possible triple comparison outcomes. Goodness of fit tables are prepared automatically if your project links simulated data.

Improved Auto Pilot. The Auto Pilot has been strengthened as a demonstration and training tool. Simulated data tables are prepared at the beginning of each Auto Pilot run so that you can see the process from beginning to end. Auto Pilot steps are logged so that you can review them in a standard report as a model for your own projects.

Improved Project Reporting. A Bayesian Model Check report has been added to the list of project reports. The Model Check report tabulates prior, observed, and posterior values of most parameters in the linkage model. If your project links simulated data, goodness of fit tables are prepared automatically.

More Rational Design. CODES2000 now uses only four Access databases: CODES2000 contains all of the Access forms comprising the user interface. STMT Data contains all data tables used for managing linkage projects. User Library contains all user developed custom Visual Basic functions. STMT Library contains Access Visual Basic objects that are part of an improved object oriented design. CODES2000 now supports linkage projects done in Microsoft SQL Server as well as Microsoft Access.