How Many Focus Groups Are Enough? Building an Evidence Base for Nonprobability Sample Sizes

• Published in: Field methods Vol. 29; no. 1; pp. 3 - 22
• Main Authors: Guest, Greg, Namey, Emily, McKenna, Kevin
• Format: Journal Article
• Language: English
• Published: Los Angeles, CA SAGE Publications 01.02.2017; SAGE PUBLICATIONS, INC
• Subjects: African Americans; Coding; Data Analysis; Evidence Based Practice; Focus Groups; Group research; Health Behavior; Help Seeking; Help seeking behavior; Males; Men; Methodological approaches; Participant Characteristics; Probability; Research Design; Research Methodology; Sample Size; Sampling; Thematic Approach; North Carolina; United States > US
• ISSN: 1525-822X; 1552-3969
• DOI: 10.1177/1525822X16639015

Few empirical studies exist to guide researchers in determining the number of focus groups necessary for a research study. The analyses described here provide foundational evidence to help researchers in this regard. We conducted a thematic analysis of 40 focus groups on health-seeking behaviors of African American men in Durham, North Carolina. Our analyses revealed that more than 80% of all themes were discoverable within two to three focus groups, and 90% were discoverable within three to six focus groups. Three focus groups were also enough to identify all of the most prevalent themes within the data set. These empirically based findings suggest focus group sample sizes that differ from many of the “rule of thumb” recommendations in the existing literature. We discuss the relative generalizability of our findings to other study contexts, and we highlight some methodological questions about adequate sample sizes for focus group research.