Objective: To investigate the effects of a physical therapy (PT) program in groups of people with Parkinson's disease (PD). Design: Randomized controlled trial with a crossover design. Setting: Two outpatient rehabilitation clinics in Boston and Amsterdam, respectively. Participants: Sixty-eight subjects diagnosed with typical, idiopathic PD, Hoehn and Yahr stage II or III, and stable medication use. Intervention: Group A received PT and medication therapy (MT) for the first 6 weeks, followed by MT only for the second 6 weeks. Group B received only MT for the first 6 weeks and PT and MT for the second 6 weeks. Main Outcome Measures: The Sickness Impact Profile (SIP-68), the mobility portion of the SIP-68, the Unified Parkinson's Disease Rating Scale (UPDRS), and comfortable walking speed (CWS) at baseline, 6-week, 12-week, and 3-month follow-up. Results: At 6 weeks, differences between groups were significant for the SIP mobility (P=.015; effect size [ES]=.55), for CWS (P=.012; ES=.49), for the activities of daily living (ADL) section of the UPDRS (P=.014; ES=.45), and for the total UPDRS (P=.007; ES=.56). The total SIP and the mentation and motor sections of the UPDRS did not differ significantly between groups. Significant differences were found at 3 months compared with baseline for CWS, the UPDRS ADL, and total scores. Conclusions: People with PD derive benefits in the short term from PT group treatment, in addition to their MT, for quality of life related to mobility, CWS, and ADLs; long-term benefits were found in CWS, UPDRS ADL, and total scores but varied between groups. © 2005 by American Congress of Rehabilitation Medicine and the American Academy of Physical Medicine and Rehabilitation.