The historical construction of correlation as a conceptual and operative instrument for empirical research

This article is meant to reconstruct—from the standpoint of sociology and history of science—the development of the concept and the operative instruments of statistical correlation. The starting point is the discussion of some key mathematical aspects of the Error Theory, including a detailed analysis of the various positions regarding its contributions, if any, to the theory of correlation. Then proceeds to examine how the concept (and its relative instruments) emerged in its modern sense, by the late Nineteenth century, thanks to the work of Francis Galton. Finally, it considers the numerous contributions that rendered possible the formalisation and generalisation of both Galton’s concept and methodological tools, in particular those of Karl Pearson, but also those of Walter Weldon, Francis Ysidro Edgeworth, George Udny Yule and Charles Spearman.

“Co-relation or correlation of structure” is a phrase much used in biology, and not least in that branch of it which refers to heredity, and the idea is even more frequently present than the phrase; but I am not aware of any previous attempt to define it clearly, to trace its mode of action in detail, or to show how to measure its degree. Francis Galton (1888, 135)