Museums have historically performed audience research using face-to-face interviews with randomly selected visitors who are intercepted by museum representatives. Although this data collection method can yield robust data about visitor experiences and interests, it requires training and human resources which are often a burden to museum administrators. Computerized surveys may be a less costly alternative to face-to-face interviews. This study compares survey results obtained from three administration modes: self-selected visitors responding to a computerized questionnaire, randomly intercepted visitors responding to the same computerized questionnaire and randomly intercepted visitors responding to a face-to-face interview. Self-selected respondents were significantly younger than randomly intercepted respondents as well as significantly more likely to have had previous exposure to the museum. Interviews were most likely to elicit answers to open-ended questions. Although fewer respondents to the computerized questionnaire provided answers to the open-ended questions, they provided the most well-developed answers.