Jakob Nielsen & Thomas K. Landauer (1993)
Proceedings of the SIGCHI conference on Human factors in computing systems - CHI '93, 206-213.
DOI: https://doi.org/10.1145/169059.169166
Abstract. Derives the widely cited result that approximately five evaluators or participants are sufficient to discover most usability problems in a given interface, modelling problem discovery as a Poisson process with per-participant detection probability of about 31 percent.
Tags: usability-testing sample-size