Methods: Adaptive testing allows survey questions to be administered selectively, thereby reducing the number of questions required of the participant. After the graded response model was fit to a sample, scores were estimated based on both the full-item bank and a simulation of Computerized Adaptive Testing (CAT).
Results: Comparisons of these 2 sets of score estimates with each other and of their correlations with external outcomes of job performance, absenteeism, and hospital admissions demonstrate that the CAT well-being scores maintain accuracy and validity. The simulation indicates that the average survey taker can expect a reduction in number of items administered during the CAT process of almost 50%.
Conclusions: An increase in efficiency of this extent is of considerable value because of the time savings during the administration of the survey and the potential improvement of user experience, which in turn can help secure the success of a total population-based well-being improvement program.