Education and Fertility: An investigation into Italian families

In this paper we analyse the correlation between the level of education and the number of children in Italy. We select 10,720 Italian families from the 2004-2007 European Union Statistics on Income and Living Conditions (EU-SILC) dataset. Our dependent variable is represented by the number of children ever born to each respondent. Since the number of children ever born is a count variable, Poisson regression is the suitable statistical procedure used to conduct the empirical analysis. First, we estimate the correlation between the female’s education and her number of children, and then we use also partner’s education to take into account the family dimension. Furthermore, in the context of fertility, zero observations might be due either to the choice not to have children or to impossibility to become a mother. For this reason, we adopt also a more appropriate tool, that is a Zero-Inflated Poisson regression. From the empirical results, we may observe a significant negative correlation between the level of education and the number of children