We tested for inflationary bias introduced through retrospective pretests by analyzing traditional pretest, retrospective pretest, and posttest evaluation data collected on a first-line supervisory leadership training program, involving 196 supervisors and their subordinates, across 17 organizational settings. Retrospective pretest ratings by both trained (supervisors) and untrained (subordinates) respondents were significantly lower than traditional pretest ratings, resulting in substantially inflated training effect sizes when posttests were compared with retrospective pretests rather than with traditional pretests. Further analysis revealed evidence of both respondents' application of an implicit theory of change (i.e., assumption that posttraining scores should generally be higher than pretraining scores) and a tendency to rate their own improvement as greater than that of others. Implications for program evaluation are discussed. (Contains 2 tables.)