LAUSR

This study applies a new Bayesian univariate ordered probit model to happiness data on Australia, Canada, and the US, with immigration status and religion status reflecting individual heterogeneity in the threshold model. The empirical results show that the models that include individual heterogeneity perform better than those without individual heterogeneity do. Furthermore, the effects of heterogeneity vary between the three countries. Having a religious affiliation affects the thresholds in the US, but shows no evident effects in Canada or Australia. Furthermore, parents’ immigration status can affect the thresholds in Australia, but shows no effects in the US or Canada.