Purpose: A Turkish translation of the Public Opinion Survey of Human Attributes-Stuttering (POSHA-S) was used to compare probability versus convenience sampling to measure public attitudes toward stuttering. Method: A convenience sample of adults in Eskişehir, Turkey was compared with two replicates of a school-based, probability cluster sampling scheme. Results: The two replicates of the probability sampling scheme yielded similar demographic samples, both of which were different from the convenience sample. Components of subscores on the POSHA-S were significantly different in more than half of the comparisons between convenience and probability samples, indicating important differences in public attitudes. Conclusions. If POSHA-S users intend to generalize to specific geographic areas, results of this study indicate that probability sampling is a better research strategy than convenience sampling. Educational objectives: The reader will be able to: (1) discuss the difference between convenience sampling and probability sampling; (2) describe a school-based probability sampling scheme; and (3) describe differences in POSHA- S results from convenience sampling versus probability sampling. © 2011 Elsevier Inc.