Automated simultaneous assembly of multi-stage testing for the uniform CPA examination

Some solutions used in the assembly of the computerized Uniform Certified Public Accountancy (CPA) licensing examination are offered as practical alternatives for operational programs producing large numbers of forms. The Uniform CPA examination will be offered as an adaptive multi-stage test (MST) beginning in April of 2004. Examples of automated assembly using mixed integer programming solutions in Optimization Programming Language software (OPL Studio 3.6.1© ILOG Inc.) illustrate MST design features and implementation strategies that can be generalized to other automated assembly problems. A compromise between the best possible combination of test content, and sustainability and security over time is afforded by linear programming techniques that make use of mixed integer optimization algorithms. This method of formulating relative optimization functions to ensure a variety of constraints are always met for testlets of differing difficulties is also analyzed to evaluate the exposure of testlets and panels that is associated with the MST design. Technical information is also shared to assist other practitioners and researchers to emphasize feasibility and efficiency in their test construction problems. Some practical consequences from the selection of statistical targets on testlet exposure are illustrated. These results are described with respect to the fundamental principles of automated continuous test assembly and administration based on MST where testlet or item exposure projections and inventory rotation are critical concerns. 2Some solutions used in the assembly of the computerized Uniform Certified Public Accountancy (CPA) licensing examination are offered as practical alternatives for operational programs producing large numbers of forms. The Uniform CPA examination will be offered as an adaptive multi-stage test (MST) beginning in April of 2004. Examples of automated assembly using mixed integer programming solutions in Optimization Programming Language software (OPL Studio 3.6.1© ILOG Inc.) illustrate MST design features and implementation strategies that can be generalized to other automated assembly problems. A compromise between the best possible combination of test content, and sustainability and security over time is afforded by linear programming techniques that make use of mixed integer optimization algorithms. This method of formulating relative optimization functions to ensure a variety of constraints are always met for testlets of differing difficulties is also analyzed to evaluate the exposure of testlets and panels that is associated with the MST design. Technical information is also shared to assist other practitioners and researchers to emphasize feasibility and efficiency in their test construction problems. Some practical consequences from the selection of statistical targets on testlet exposure are illustrated. These results are described with respect to the fundamental principles of automated continuous test assembly and administration based on MST where testlet or item exposure projections and inventory rotation are critical concerns.