"Modern statistics is much more than a toolbox, a bag of tricks, or a miscellany of isolated techniques useful in individual sciences. There is a unity to the methods of statistics. The same computer program that analyzes the data of a geophysical scientist today might be used by an economist, a chemist, a sociologist, or a political scientist tomorrow."August 1820 marks the publication of Adrien Marie Legendre's "Sur la methode des moindres quarres" otherwise known as the method of least squares. Legendre's tremendous contribution to the development of statistics was as revolutionary as calculus had been to mathematics a century earlier. Legendre's statistical method focused on deducing the most accurate results from observational measurements. He concluded that a system of equations of the form E = a +bx + cy + fz + &c., in which, a, b, c, f, &c are known coefficients, varying from one equation to the other, and x, y, z, &c are unknown quantities, to be determined by the condition that each value of E (error) is reduced either to zero or a very small number. According to Legendre, when the number of equations equals the number of unknowns, there are no problems. However, when there are more equations than unknowns, it becomes impossible to choose values for the unknowns that would eliminate all the errors. As a solution, Legendre proposed in making the sum of the squares of the errors a minimum. As a result, equilibrium is established among the errors and prevents the extremes from dominating. Legendre's method of least squares was presented so clearly that statisticians a century after found very little to improve on.
Stephen M. Stigler, The History of Statistics: The Measurement of Uncertainty before 1900.
Author: Henry Sheen(?)
References:
http://www.mnsfld.edu/~rwalker/Statistics.html
Owen, D.B., On The History of Statistics and Probability.
New York:Marcel Dekker, Inc. 1976, page(s): 9, 300, 310, 339, 439.
|
|
|
|
|
|