Background: This study examined the extent to which social cognitive theory is involved in dietary behavior changes among a sample of African Americans in Georgia. Purpose: We examined whether outcome expectations, barriers, and self-efficacy mediate changes in fruit and vegetable intake behavior. Methods: To accomplish this, we used change scores from the time of baseline (T1) to follow-up (T2). Using self-efficacy as an example, mathematically this is represented by the equation: Self-efficacy T2--Self efficacy T1 = ? Self-efficacy. A total of 1011 individuals were recruited across the 14 churches (20% of total population). Three measures of dietary intake were obtained to provide an estimate of actual intake. Participants completed a 7-item fruit and vegetable food frequency questionnaire (FFQ) measuring consumption behavior in the past month, based on the Behavioral Risk Factor Surveillance System. Regression analysis was performed using the fruit and vegetable values from the FFQs and 24-hour recall as the dependent variables. Results: Findings indicate that self-efficacy in isolation significantly predicted changes in fruit and vegetable intake (B = 0.606, P < 0.001) but accounted for a little less than 3% of the variance (R[superscript 2] = 0.027). Likewise, changes in outcome expectations for eating more fruits and vegetables (B = 0.517, P < 0.001) and changes in barriers (B = - 0.812, P < 0.001) were significant predictors. Translation to Health Education Practice: Results of this study can assist health educators to design, implement, and evaluate health education and health promotion programs related to dietary practices.