Obstructive sleep apnea syndrome (OSAS) is currently a clinically defined syndrome associating somnolence and on or two of the following symptoms: severe snoring, nocturnal respiratory arrest, repeated nocturnal awakening, non-recuperative sleep, diurnal fatigue, and altered concentration. The polysomnographic criterion is a more than 5 apnea-hypopnea episodes plus micro-awakenings related to respiratory efforts per hour of sleep. The epidemiological definition of OSAS is different because the prevalence of OSAS is estimated from the prevalence of the apnea-hyponea index (AHI) per hour of sleep and the prevalence of somnolence in the population. Epidemiological studies have produced different estimates of the prevalence of OSAS. The differences are less pronounced but still persist when comparing studies with a similar methodology, an identical sample, and sleep laboratory polysomnography recordings. These differences are related to the populations studied and also to the recording methods with different sensitivity and specificity. The difference between the prevalence P, which is the ratio between the number of patients in the study population, and the number Q, which is the ratio of the number of positive tests in the population, depends on the sensitivity and the specificity of the test used. The prevalence is also equal to the number of positive tests only if the sensitivity and specificity are both 1. The most widely used method, the thermistance method, has poor sensitivity and specificity. Prevalence is probably underestimated with this test. A rigorous consensual definition of this OSAS and abnormal ventilatory events as well as standardized diagnostic tests adapted for epidemiology studies are indispensable.