Statistical Test Planning with a Computer Program

Statistical test plarmiag can be carried out advantageously by expert systems which design the test plan, evaluate the results, and optimize the process in a single logically constructed sequence. An example is the program APO (Analysis Process Optimization) [30]. 

APO presents the results in tabular and graphical form and provides detailed hints for the further development and improvement of the working hypothesis. 

To develop a test plan the program only requires information on the independent variables. After input of the variables (experimental parameters) and their levels, the program calculates those points in a multidimensional space that provide the best predictions in a subsequent modeling process. The input levels of a variable determine the range of values, which should have been determined in preliminary investigations and catalyst screening. In general at least 3-5 levels per variable should be chosen. 

The maximum number of experiments is limited to 80 for nine independent variables. 

As an example of the application of the program, we shall use the previously discussed example of the selective hydrogenation of a substituded o-cyano aromatic ni-tro compound with a supported Pd catalyst (see Section 13.3.1). 

---

Selection and Testing Statistical Test Planning with a Computer Program... 

---