This paper provides evidence that in the long run the trends of social capital are good predictors of the trends of subjective well-being. The indicator of social capital that we apply is the membership of individuals in groups or associations. All countries for which there exist comparable long time series on social capital are considered (14 developed and 5 developing countries). Correlations are calculated using the same bivariate analysis applied by Easterlin and Angelescu (2009) to investigate the long run relationship between subjective well-being and GDP per-capita. Finally, several robustness checks of Easterlin and Angelescu's results are performed, substantially confirming that subjective well-being and GDP per-capita are unrelated in the long term.