OBJECTIVE: Although social support has been recognized as an important factor in the quality of life of head and neck cancer patients, there has been little investigation of the buffering effect of social support on these patients' social distress or of the coping skill of self-efficacy. The aim of this study was to examine how social support and self-efficacy mediate the relationship between social distress and emotional distress in head and neck cancer patients. METHODS: Two hundred twenty-five head and neck cancer patients completed our questionnaire (effective response rate, 92.2%). Of these, 129 (57.3%) had facial disfigurement. These participants responded to questions about perception of social distress, social support, self-efficacy, and emotional distress (depression and anxiety). We used structural equation modeling for statistical analysis. RESULTS: The fit indices of this model were excellent (χ2 (7) = 9.147, p = 0.242, goodness of fit index (GFI) = 0.981, adjusted goodness of fit index (AGFI) = 0.922, comparative fit index (CFI) = 0.993, root mean square error of approximation (RMSEA) = 0.049). Self-efficacy strongly buffered the negative influence of social distress on emotional distress. Social support from family members did not have a direct or indirect influence on emotional distress. Social support from friends was related to lower social distress and higher emotional distress. CONCLUSIONS: Our findings suggest that self-efficacy might confound the relationship between social support and emotional distress, and that different sources of social support might play different roles in the mediation of social distress on emotional distress.