Reiers?l, Geary and the idea of instrumental variables

Abstract

In the 1940s the method of instrumental variables was introduced for use in the Errors in Variables Model. According to ReierS0I, the "idea of using instrumental variables" was introduced independently by himself in 1941 and by Geary in 1943. For the modern reader the "idea" signifies the use of a particular estimator which, under certain assumptions, is consistent for the structural parameters. Geary presents something resembling this but Reiers?l does not. So what was the "idea of using instrumental variables"? The paper tries to answer this question. It sets the work of Reiers?l and Geary in the larger context of work on the EVM in the 1930s and 1940s.