Aims: To estimate the clinically important change (CIC) on a 100-mm visual analog scale for pain intensity (VAS-PI) by relating it to the patient's global impression of change (PGIC) in patients with chronic temporomandibular disorder (TMD) pain and to assess the dependency of the CIC on their baseline pain scores. Methods: Data from a prospective cohort study with 588 patients with chronic TMD pain were analyzed. The CIC was estimated over a 3-month period, and receiver operating characteristic methods were used to assess the optimal cut-off point. The PGIC category of "much improved" served as an external criterion. Dependency of absolute and percent change on baseline VAS-PI scores was determined by linear regression analysis. Results: A VAS-PI change score of -19.5 mm and a percent change score of -37.9% were best associated with the concept of CIC. Since patients with high baseline pain required greater absolute reductions in pain to reach a clinically important improvement, percent change scores performed better in classifying improved patients. Conclusion: Providing a standard definition of the CIC adds to the interpretability of study results, ie, the estimates will aid in understanding individual patient outcomes. Keywords: chronic pain, minimal clinically important change, temporomandibular disorder