Although there are many advantages to using computer-based tests (CBTs) linked to computer-based instruction (CBI), there are also several difficulties. In certain instructional settings, it is difficult to conduct psychometric analyses of test results. Several measurement issues surface when CBT programs are linked to CBI. Testing guidelines state that computer-administered testing should provide at least the same degree of feedback to examinees regarding their responses as traditional testing formats. This guideline has interesting implications for CBT. Although answer changing should be allowed when the examinee feels another answer is more appropriate or the examinee pressed the wrong key, the amount of time allowed for changes is significant. In adaptive testing, item presentation is based on previous responses. Another drawback of CBT is the difficulty in scoring constructed response or short answer items--the recommended way to test recall of facts. Item contamination is an additional problem, because CBI allows students to preview items, receive feedback while items are still being presented, or retake items. The final problem is the non-equivalence of groups tested. Since examinees are rarely administered the same items on a test, it is difficult to compute item and test statistics. (GDC)