The goal of this study was to use meta-analytic path analysis to evaluate a theoretical model of stress and health. A meta-analysis technique was adopted to combine and re-analyze 477 studies that investigated stress-related topics between January 1980 and December 2003 in Taiwan. Databases searched included PerioPath-Index to Chinese Periodical Literature, Electronic Theses and Dissertations System, and NSC (National Science Council) Science and Technology Information System. Variables recorded included stress, health, social support, coping strategies, and personality traits. A correlation matrix of these variables was derived from meta-analytic data and then analyzed using structural path analysis to test the fitness of the hypothesized stress-health model to the observed aggregated data. Results showed the revised hypothesized model to be a reasonable, good fit to aggregated data. Based on the theoretical stress-health model developed in this study, subjective stress was found to have a substantively important and direct effect on health, whereas objective stress required the mediating function of subjective stress to exercise an influence on health. Such variables as social support, coping strategies, and personality traits had comparatively weaker influences, either direct or indirect, on the stress-health process. This study provided a holistic view on the relationship between stress and health in the context of stress and proposed a direction for future research and practice.