The prevalence of temporomandibular disorder (TMD) among elderly people with Parkinson's disease (PD) is relatively high, but a population-based study of the relationship between PD and TMD is still lacking. This study, therefore, sought to investigate the association between TMD and PD by using data for one million randomly sampled beneficiaries of Taiwan's National Health Insurance program, including 6,185 PD patients who were matched through propensity score matching with 18,555 non-PD patients. Both the PD and non-PD cohorts were followed until death, any diagnosis of TMD, or December 31, 2013, whichever occurred first. Each diagnosis of TMD was made by a qualified physician according to the International Classification of Diseases, 9th Revision, Clinical Modification (ICD-9-CM), using the diagnosis codes 524.60, 524.62, 524.63, and 524.69 while excluding tooth abscess, wisdom tooth eruption, herpes zoster and postherpetic neuralgia, mastoiditis, otitis externa, otitis media, parotitis, sialadenitis, and trigeminal neuralgia. We used Cox proportional hazard regression models to calculate the relative risk of TMD and found a 2.11-fold (95% CI: 1.35-3.30) increased risk of TMD overall in the PD group compared with the non-PD group. Stratified by follow-up period, there was a 4.25-fold (95% CI: 1.51-11.93) increased risk in the PD group in the first year after the initial PD diagnosis and a 3.88-fold (95% CI: 1.33-11.28) increased risk in the second year. Over the long-term (>5 years), PD was significantly associated with an increased risk of TMD. These findings suggest that it is important to closely monitor the temporomandibular joint health of PD patients.