摘要：The aim of this study is to analyze longitudinally, based on four measurements at intervals of eight years, the annual effect of age group and birth cohort on regular exercise in the Swedish population from 1980–1981 to 2004–2005. We followed a randomly drawn subsample of individuals aged 16–63 years, interviewed by professional interviewers, from the Swedish Annual Level of Living Survey. We applied a mixed model with a random intercept and a random slope in order to analyze the annual effects. The prevalence of regular exercise increased annually by 0.3 % among men and 0.7 % among women. For every one-unit increase in BMI, the odds of regular physical activity decreased by 6 % among men and 5 % among women. While the female birth cohorts all increased over time the male birth cohorts showed a different pattern, as only the three oldest birth cohorts (1926–1933, 1934–1941, 1942–1949) showed an increase in regular exercise. The three youngest birth cohorts (1958–1965, 1966–1973, 1974–1981) instead showed a decreased prevalence of regular exercise. There was an inverse relationship between regular exercise and age, although the differences between age groups tended to decrease over time. Differences related to educational level increased over time as the prevalence of exercise among those with higher educational attainment increased more than among those with lower educational attainment. The most dramatic relative increase in exercise over time (almost two-fold) was found among those who were obese or who reported a poor health status. The prevalence of regular exercise increased in all studied sub-groups. However, the increased difference related to education level is worrying. To reduce the risk for ill health in these groups, there is a need for targeted interventions.
关键词：Exercise ; Physical activity ; Lifestyle ; Longitudinal studies ; Cohort effect ; Mixed models ; Public health
