“…In addition, and more positively, various cases can also be cited in which the chief statistical accomplishment has been to identify and characterize important social regularities that were hitherto unappreciated, or incorrectly understood, by in e¡ect separating out these regularities from their particular contexts. For example, loglinear modelling has been applied to demonstrate how temporal constancy and a large degree of cross-national commonality in relative rates of social mobility^or patterns of social £uidityĉ an underlie historically and geographically speci¢c and often widely £uctuating absolute rates Featherman, Jones, and Hauser, 1975;Goldthorpe, 1987;Erikson and Goldthorpe, 1992). Likewise, sequential logit modelling, as pioneered by Mare (1981), has been used in order to show up more or less constant class di¡erentials in educational attainment during eras in which educational provision has steadily expanded and in which the`e¡ects' of class origins on educational attainment overall would thus appear to decline^that is, simply on account of increased rates of participation (see e.g.…”