%0 Journal Article
%T Longitudinal Research in Social Science: Some Theoretical Challenges
%A Burch
%A Thomas K.
%J Canadian Studies in Population
%D 2001
%I Canadian Population Society
%X Every advance carries with it potential problems, and longitudinal analysisis no exception. This paper focuses on the problems related to the massive amounts of data generatedby longitudinal surveys. It is argued that a proliferation of data may be to the good, but it will notnecessarily lead to better scientific knowledge. Most demographers think the logical positivest way -that theory arises out of empirical generalizations. But massive empirical investigations have onlyled to disappointing theoretical outcomes in demography. This paper discusses one way out of thisimpasse: to adopt a different view of theory, a model-based view of sicence. Theoretical models basedon empirical generalization should become the main representational device in science. French Chaque innovation inclue des probl¨¨mes possibles, et l¡¯analyse longitudinale nefait pas exception. Nous attirons attention sur la surabondance de donn¨¦es dansles enqu¨ºtes longitudinales. Cette abondance contient des avantages mais elle ner¨¦sulte pas n¨¦cessairement en une meilleure connaissance scientifique.Beaucoup de d¨¦mographes semblent penser que la th¨¦orie sort desg¨¦n¨¦ralisations empiriques, mais l¡¯abondance de donn¨¦es en d¨¦mographie nousdonne souvent des sorties th¨¦oriques limit¨¦es. Nous proposons ici une autrefa on, en adoptant une diff¨¦rente vue de la th¨¦orie qui commence avec unescience ¨¤ base de mod¨¨les. Les mod¨¨les th¨¦oriques ¨¤ base de g¨¦n¨¦ralisationsempiriques devraient ¨ºtre la principale fa on de repr¨¦senter en science.
%K logical positivism
%K abstract modelling
%K the Semantic Model
%K middle range theory
%U http://www.canpopsoc.ca/CanPopSoc/assets/File/publications/journal/CSPv28n2p262.pdf