Theodore Wilbur Anderson was an American mathematician and statistician who has specialized in the analysis of multivariate data.
He was born in Minneapolis, Minnesota. He was on the faculty of Columbia University from 1946 until moving to Stanford University in 1967, becoming Emeritus Professor in 1988. He served as Editor of Annals of Mathematical Statistics from 1950 to 1952. He was elected President of the Institute of Mathematical Statistics in 1962.
Anderson's 1958 textbook, An Introduction to Multivariate Analysis, educated a generation of theorists and applied statisticians; it was "the classic" in the area until the book by Mardia, Kent and Bibby [1]. Anderson's book emphasizes hypothesis testing via likelihood ratio tests and the properties of power functions: Admissibility, unbiasedness and monotonicity.Anderson is also known for Anderson–Darling test of whether there is evidence that a given sample of data did not arise from a given probability distribution.
He also framed the Anderson–Bahadur algorithm along with Raghu Raj Bahadur which is used in statistics and engineering for solving binary classification problems when the underlying data have multivariate normal distributions with different covariance matrices. Wikipedia
Source: "The ET interview: Professor TW Anderson," 1986, p. 525
T. W. Anderson. The Statistical Analysis of Time Series http://books.google.com/books?hl=nl&lr=&id=rCOzXIC8ZLkC&oi=fnd&pg=PR11, (1971/2011), p. 1. Introduction; Cited in: American Sociological Association (1974), Sociological Methodology, p. 310
Source: "The ET interview: Professor TW Anderson," 1986, p. 525
