Most studies using Mare’s (1980, 1981) seminal model of educational transitions find that the effect of family background decreases across transitions. Recently, Cameron and Heckman (1998, 2001) have argued that the “waning coefficients” in the Mare model are driven by selection on unobserved variables. This paper, first, explains theoretically how selection on unobserved variables leads to waning coefficients and, second, illustrates empirically how selection leads to biased estimates of the effect of family background on educational transitions. Our empirical analysis using data from the United States, United Kingdom, Denmark, and the Netherlands shows that when we take selection into account the effect of family background variables on educational transitions is largely constant across transitions. We also discuss several difficulties in estimating educational transition models which deal effectively with selection.

Download PDF → Eksternt link →


Titel: Selection bias in educational transition models: theory and empirical evidence
Forfatter: Anders Holm & Mads Meier Jæger
Institution: Det Nationale Forskningscenter for Velfærd
Udgivelse: The Working Paper Series of The Danish National Centre for Social Research, 2008 (11)
Genre: Arbejdspapir
Omfang: 39
Årstal: 2008