摘要：The present study investigated the cross-sectional and longitudinal predictability of mental health using Sense of Coherence (SOC) through a linear regression model (LRM) and generalized additive model (GAM). The estimation using LRM and GAM showed that SOC predicted mental health in both cross-sectional and longitudinal data. Moreover, the model fit index and analysis of deviance showed that the GAM fitted better with both data compared to LRM. These results suggest that SOC can be used as a predictor of the current and future states of mental health as well as the continuous and gradual changes in mental health.
关键词：sense of coherence;mental health;predictability;linear regression model;generalized additive model
