Heroic periods

This article complements Stigler’s book of 1986, The History of Statistics : The Measurement of Uncertainty before 1900. We focus on the gap between the early work on the method of least squares, c. 1805-1815, and the discovery and development of regression and correlation, c. 1885-1900. Some possible reasons for this “long pause” between two “heroic periods” are suggested. N.B.