Richard Loree Anderson
Richard Loree Anderson was an American econometrician. He was a Professor of Statistics at North Carolina State University from 1941 to 1966. In 1967, he took up chairmanship of the newly established Department of Statistics at the University of Kentucky, a position he held until 1979. In 1951 he was elected as a Fellow of the American Statistical Association. While a professor at the University of Kentucky, he consulted with a number of drug companies on clinical trials. Even before, he had been consulting several computer programming companies including IMSL, BMDP, and SAS.
Anderson was good friends with William Gemmell Cochran before the latter died in 1980. The two had first met at Iowa State University in 1938.
Research
In 1942, Anderson found the probability density function of the serial correlation coefficient when the variables are independent and identically distributed and follow the normal distribution. Anderson recalled that he preliminarily calculated this based on characteristic functions and presented it in the winter of 1940, but he thought it would be intractable for N > 9. The next day, he received a note from Cochran asking him to try out Cochran's theorem, which turned out to be the answer.In 1962, Anderson, W. T. Wells, and John W. Cell calculated the probability density function for the product of two noncentral chi-squared variables using the Mellin transform.
In 1980, Anderson, Walter W. Stroup, and James W. Evans devised an algorithm to compute maximum likelihood estimates for the completely random balanced incomplete block design.
In 1985, Anderson, Sastry G. Pantula, and Larry A. Nelson, proposed an estimator for the covariance matrix for a mixed linear model, where the model describes an experiment conducted over several sites for several years. The model takes the form, where i indexes sites, j indexes "blocks" at each site, and k indexes treatments.
In 1996, Anderson, Pao-Sheng Shen, and P. L. Cornelius used simulations to study nested mating designs. They concluded that asymptotic variances severely underestimate the actual variance in the simulation.