Up-and-Down Methods with Multi-Category Rating
Two Categories, Three Categories, Four Categories
Up-and-Down methods using three rating categories (‘Stronger’, ‘Do not know’, ‘Weaker’) or four rating categories (‘Stronger’, ‘Probably Stronger’, ‘Probably Weaker’, ‘Weaker’) are proposed by Okamoto (2019). These multi-category rating methods with Bayesian analysis estimated point of subjective equality (PSE) and just noticeable difference (JND) more accurately than the traditional up-and down method (Okamoto, 2019). Bayesian methods were applied also to data of the traditional up-and-down method. The Bayesian method brought more accurate estimates than those by traditional averaging method. Detailed explanation and associated programs are presented at the following website:
Up-and-Down method with Two Rating Categories
Up-and-Down method with Three Rating Categories
Up-and-Down method with Four Rating Categories