We appreciate the comments by Evered and colleagues regarding the statistical and methodological issues associated with our analysis of long-term cognitive outcomes after coronary artery bypass grafting (CABG). The authors raise several important points regarding the analysis of neuropsychological test results. The first is the use of group mean change vs change in each patient's performance after the preoperative testing. The authors are correct in stating that we have previously advocated the use of such individual change scores, and we also used the same methods for the current analysis, as explained in our "Methods" section: "The statistical significance of changes from baseline to 1 year, from 1 year to 5 years, and from baseline to 5 years was assessed by 1-sample t tests on the average ofthe within-subject z score differences (later score minus earlier score) for each cognitive domain [emphasis added]."
Selnes OA, Royall RM, Grega MA, Borowicz LM, McKhann GM. In reply. Arch Neurol. 2002;59(3):489–490. doi: