The general aim of the present retrospective study was to examine the test mode effect, that is, the difference in performance when tests are taken on computer (CBT), or by paper and pencil (PnP). The specific purpose was to examine the degree to which extensive practice in CBT in graduate students in nurse anesthesia would raise scores on a later, high-stakes, computer-adaptive National Certification Examination (NCE). A group of students with extensive practice in CBT while in school were compared to a group of students whose tests were administered primarily on PnP ( n = 73 in each group). Groups were matched on age, grade point average (GPA), and gender. Groups were compared on NCE scores with GPA as the covariate. The adjusted mean score in the PnP group was 535 (95% CI = 526-543), which was higher than the adjusted mean score in the CBT group, 510 (95% CI = 501-519). It was concluded that controlling for academic ability, graduate students in nurse anesthesia at one university with greater exposure to CBT while in school had lower scores on the NCE than a comparison group of students with less exposure to CBT. However, this difference was least (13.9 points), and statistically insignificant, in students with GPA less than 3.50, perhaps consistent with a beneficial effect of practice in CBT in this subgroup. NCE scores were not affected by gender or age, but were positively correlated with various measures of academic ability, such as scores on course examinations, and the Self-Evaluation Examination. Student reactions to computer-based testing were generally positive. Students reported that immediate scoring and feedback was an advantage, and felt that computer-based testing was good preparation for the NCE. They were dissatisfied with the inability to review and change previous answers, the need to learn new test-taking skills, and technical problems with the testing software. The direct economic cost of the CBT activities was modest. Indirect economic benefits and costs were also discussed. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://www.proquest.com/en-US/products/dissertations/individuals.shtml.]