A randomized and stratified investigation was conducted into the epidemiology of stuttering in the community across the entire life span. Persons from households in the state of New South Wales, Australia, were asked to participate in a telephone interview. Consenting persons were given a brief introduction to the research, and details were requested concerning the number and age of the persons living in the household at the time of the interview. Interviewees were then given a description of stuttering. Based on this description, they were asked if any person living in their household stuttered (prevalence). If they answered "yes," a number of corroborative questions were asked, and permission was requested to tape over the telephone the speech of the person who stutters. Confirmation of stuttering was based on (a) a positive detection of stuttering from the tape and (b) an affirmative answer to at least one of the corroborative questions supporting the diagnosis. Results showed that the prevalence of stuttering over the whole population was 0.72%, with higher prevalence rates in younger children (1.4-1.44) and lowest rates in adolescence (0.53). Male-to-female ratios ranged from 2.3:1 in younger children to 4:1 in adolescence, with a ratio of 2.3:1 across all ages. The household member being interviewed was also asked whether anyone in the household had ever stuttered. If the answer was "yes," the same corroborative questions were asked. These data, along with the prevalence data, provided an estimate of the incidence or risk of stuttering, which was found to range from 2.1% in adults (21-50 years) to 2.8% in younger children (2-5 years) and 3.4% in older children (6-10 years). Implications of these results are discussed.