ECTJ, VOL. 34, NO. 1, PAGES 3-7 ISSN 0148-5806 I recently served as review editor on an article submitted to ECTJ by Richard Clark titled "Evidence for Confounding in Computer-Based Instruction Studies: Analyzing the Meta Analyses," (Clark, 1985). While I fussed over some aspects of the first draft, I thought Clark did a good job of highlighting some of the issues involved in comparing computer-based instruction (CBI) with "traditional" instruction (TI) (or, for that matter, comparing any instructional media and/or methods). In particular, Clark argued that the superiority of CBI over TI in comparison studies might have been either overestimated due to a failure to control