Search

Abstract: Founder of the Brussels Observatory, Adolphe Quetelet (1796–1874) is especially well known for his theory of the average man. Like the average position of a star obtained through a large quantity of observed data, the average man was, according to Quetelet, subject to fixed causal laws. Published in 1835, his book On Man: Essay of Social Physics is one of the founding works of sociology and mathematical statistics. The sources of the analogy between astronomy and social physics have been debated by historians. To shed light on this question and the conditions of application of mathematics in the 19th century, we publish for the first time a manuscript that is kept in Quetelet's papers at the Royal Academy of Belgium, and give an English translation of it. [Copyright &y& Elsevier]

This paper discusses two basic issues related to the assessment of the goodness-of-fit of sociological models to behavioral data: How simplifying assumptions contained in models should be evaluated and whether analysis of data should be carried out at the individual group or aggregate level. The discussion is conducted in the context of the fit of a model of participation rates by Fisek, Berger, and Norman (1991) to data collected by Smith-Lovin, Skvoretz, and Hudson (1986) in a Bales-type situation. The conclusions are that simplifying assumptions should be evaluated from the point of view of robustness of model to violations of such assumptions, and that the assessment of the adequacy of minimal actor models should be in terms of aggregated data. The fit of the model and data under consideration is assessed to be adequate. [ABSTRACT FROM AUTHOR]