GS [G.S. Maddala] came to Chicago with a very strong statistical background (a BA in Mathematics from Andhra University and an MA in Statistics from Bombay University) and immediately impressed everyone who came into contact with him. When he showed up in my econometrics class it was clear that here was somebody from whom I could learn. A teacher is lucky when that happens. His first published paper (Econometrica, 1962) on the quarterly consumption function came out of this class. It was joint work with Robert Lucas, Neil Wallace, and myself. Not bad company.

At Chicago, we tried to convert GS to empirical work. He did a first-rate dissertation on “Productivity and Technological Change in the Bituminous Coal Industry” (Journal of Political Economy, 1965) and a pioneering study of international diffusion of new steel making techniques (Economic Journal, 1967). But whether it was the profession's cool reception to empirical work in general or the pull of his first love, almost all of his subsequent work has been in econometric methodology, where he has been both an innovator and a great expositor and synthesizer. He has worked in almost all areas of econometrics: distributed lags, generalized least squares, panel data, simultaneous equations, errors in variables, tests of significance, switching and market disequilibrium models, qualitative and limited dependent variable models, selection and self-selection biases, exact small sample distributions of estimators, outliers and bootstrap methods, Bayesian econometrics, and more.