|
Résumé :
|
This work began as an attempt to apply the classical techniques of statistics and econometrics to the Deutch-Solow model of nationalism, in order to turn this model into a workable tool for predicting the political future. In the course of this effort, it became clear that the usual statistical methods do a poor job in fitting dynamic models to real-world data, if we judge these models by their ability to make good predictions across time. It also became clear that newer and better methods would not be feasible, economically, unless we could invent less expensive algorithms, too. Thus the goals of this thesis are five-fold : (1) to describe new ways of fitting models to data; (2) to define new algorithms which make these methods feasible; (3) to introduce evidence for the superiority of theses methods, both for real-world and for simulated data; (4) to discuss the applications of theses ideas, in broad terms, to social and even biological sciences; (5) to discuss the new work on nationalism which has led us in these directions.
|
