Attention and focus on variables that predict loneliness in the elderly are an introduction to the successful treatment of loneliness and reduction of its consequences and serious problems resulted. In this regard, the purpose of this study was to examine the role of mental well-being, psychological capital, and spiritual intelligence in predicting the sense of loneliness of the elderly. It was a descriptive correlational study. The statistical population consisted of all elderly citizens over 65 years old living in Dezful, Iran; multi stage cluster sampling method was used to select 368 samples from 6 chosen neighborhoods in Dezful. Required data was collected using Russell's loneliness questionnaire, Case and Maghremo's mental well-being questionnaire, Luthan's psychological capital questionnaire, and Abdullah Zadeh et al. 's spiritual intelligence survey. Data were analyzed by Pearson correlation method and multiple stepwise regression analysis using SPSS-21 software version 19. The results of statistical methods showed significant negative correlations between mental well-being, psychological capital and spiritual intelligence with loneliness in the elderly (P≤ 0. 01). Multiple regression results showed that 54% of the variance of loneliness could be predicted by research variables. According to the results, it could be said that the elderly may feel less lonely if they experience higher levels of subjective well-being, psychological capital, and spiritual intelligence. These findings contain important therapeutic applications regarding the importance of these variables in reducing the sense of loneliness of the elderly.