According to item response theory (IRT), examinee ability estimation is independent of the particular set of test items administered from a calibrated pool. Although the most popular application of this feature of IRT is computerized adaptive (CA) testing, a recently proposed alternative is self-adapted (SA) testing, in which examinees choose the difficulty level of each of their test items. Examinee performance was compared under CA and SA testing conditions for college students from an introductory statistics course. Three test forms were developed, testing mathematical knowledge necessary for the course. The final pool contained 93 items which were administered to 204 subjects. The SA test yielded significantly higher ability scores, and examinees taking the SA test reported significantly lower posttest state anxiety. Implications of the differences between the two test types for measurement practice are discussed. Three tables present study data. (Author/SLD)