This paper proposes an algorithm of a computerized adaptive testing based on Item Response Theory, designed to estimate the degree of usability of e-commerce sites. Five algorithms were tested by simulation. The algorithm with the best performance was applied to real data from 361 e-commerce sites. The results showed that the algorithm could obtain good estimates for the degree of usability of e-commerce sites with the application of 13 items.
Computerized adaptive testing; Item response theory; Usability; e-commerce sites
