An empirical investigation comparing IF-THEN rules and decision tables for programming rule-based expert systems

The author discusses which method is better for programming rule-based expert systems: IF-THEN rules or decision tables. Thirty undergraduate students served as experimental subjects in an eight week study. After four weeks, subjects wrote decision tables covering cases significantly more consistently than IF-THEN rules (p<0.01). After eight weeks, subjects wrote IF-THEN rules that were significantly more complete (p<0.05) and significantly more correct (p<0.01). The eighth week test also revealed that subjects preferred decision tables to IF-THEN rules (p<0.05), perceiving them to be easier (p<0.01). In spite of a significant preference for decision tables, subjects wrote significantly more accurate IF-THEN rules.<>