Abstract

During the years 84-97, a long debate occurred in France about models for the evolution of inequalities related to the percentages of a given educational level. First we try to synthesize the main contributions, then we consider models based on a latent variable called: "educational income". The frequencies at a given level of education are used to estimate the means of this variable for the social categories concerned. This passage from a local property of a distribution to a more central property can be interpreted as a measurement scale. The scales comparing percentages, already suggested in the debate, are often not very compatible with this point of view. It is not the case of the currently most used one: the logistic scale. Under this light, it is not an ideal model however.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call