No matter how careful health education researchers plan their study designs when using survey methodologies, they will always be faced with missing data. Data can be missing for various reasons, such as lost or damaged questionnaires, respondent refusals to answer survey questions, skipped questions, illegible responses, or procedural mistakes. The purpose of this brief oral presentation is to discuss 3 judgment calls that are necessary to consider when deciding how to manage missing data in survey research. Specifically, when confronted with missing values: (1) Should the analyst use a deletion or an imputation technique? (2) Which particular missing data technique should the analyst select? (3) Which missing data technique variation is optimal? Five of the most commonly used techniques will be presented: listwise deletion, pairwise deletion, mean substitution, hot deck imputation, and multiple imputation. Finally, the sources, or types, of missing data (data that are missing at random, missing completely at random, and missing not at random) will be identified which will aid the session participant in selecting the most appropriate missing data technique for his or her own sample data. A practical health education illustration will be provided.