Cowles Commision Foundation Methods

The Cowles Commission Foundation and the Cowles Commission Method

Haavelmo's probabilistic approach was accepted by researchers in the Cowles Commission for Research in Economics, which was founded in 1932 by Alfred Cowles III, a wealthy investment adviser. Cowles assembled a group of very bright economists, including Irving Fisher, Harold Hotelling (1895-1973), and Ragnar Frisch, and set them to work on applying mathematical and statistical methods to the study of economic issues. The Cowles Commission was initially housed in Colorado Springs; in 1937 it moved to Chicago, where it remained until it moved to its current home, Yale, in the 1950s.

Much of what is now considered standard econometric work was done by the Cowles Commission. This work included estimating whether the ordinary least squares estimator would be biased downward (which it was found to be by as much as 25 percent); developing the Monte Carlo approach to small data sets; and working on issues of asymptotic convergence and unbiasedness of estima­tors.

During this time, it should be remembered, computational difficulties were enormous, because the computer as we currently know it did not exist. One did not simply type into the computer "Find OLS estimate" or "Find maximum likelihood estimate" to determine a result. One performed the work manually. The Cowles Commission followed Haavelmo in assuming that the best approach to econometrics was the probabilistic approach, in which the structural equations had an assumed distribution of error terms. This probabilistic approach became known as the Cowles Commission method. One of the most famous econometric models coming from the Cowles Commission was the Klein-Goldberger macro-econometric model (an improvement of earlier Klein models), which was the first empirical representation of the broad Keynesian system. It contained 63 variables, many of which were endogenous, and 43 predetermined. Of those 43 predetermined variables, 19 were exogenous and 24 were lagged.