The Moderating Effects of Social Support and Stress on Physical Activity in African American Women

Background African American women participate in less physical activity (PA), have higher rates of chronic disease, and report higher perceived stress relative to other race and sex demographic groups. Purpose Based on the stress-buffering hypothesis, this study tested the hypothesis that social support would buffer the negative effects of perceived stress on moderate-to-vigorous PA (MVPA) under high, but not low, perceived stress. Methods Participants were 143 African American women (mean [M] age = 43.94, standard deviation [SD] = 8.62; M body mass index = 37.94, SD = 8.11) enrolled in the Families Improving Together (FIT) for Weight Loss Trial. Average daily minutes of MVPA were obtained via 7 day accelerometer estimates at baseline and 8 and 16 weeks. Results A multilevel growth model demonstrated a significant three-way interaction between stress, social support, and time (B = -0.31, standard error [SE] = 0.14, p = .03). Simple slopes analyses revealed that, at baseline, among participants with high social support (+1 SD), stress was positively associated with greater MVPA (B = 0.49, SE = 0.18, p = .008), whereas among participants with low social support (-1 SD), stress was not significantly associated with MVPA (B = -0.04, SE = 0.14, p = .81). However, at 8 and 16 weeks, stress was not significantly associated with MVPA for either high or low support groups. Conclusions Findings highlight the importance of integrating constructs of stress and social support into future physical activity intervention programs for African American women and the need to evaluate changes in stress and social support longitudinally.