STATISTICAL MODELING OF MONETARY POLICY AND ITS
EFFECTS
CHRISTOPHER A. SIMS
A BSTRACT.

The science of economics has some constraints and tensions that set it apart from other sciences. One reflection of these constraints and tensions is that, more than in most other scientific disciplines, it is easy to find economists of high reputation who disagree strongly with one another on issues of wide public interest. This may suggest that economics, unlike most other scientific disciplines, does not really make progress. Its theories and results seem to come and go, always in hot dispute, rather than improving over time so as to build an increasing body of knowledge.
There is some truth to this view; there are examples where disputes of earlier decades have been not so much resolved as replaced by new disputes.
But though economics progresses unevenly, and not even monotonically, there are some examples of real scientific progress in economics. This essay describes one — the evolution since around 1950 of our understanding of how monetary policy is determined and what its effects are. The story described here is not a simple success story. It describes an ascent to higher ground, but the ground is still shaky. Part of the purpose of the essay is to remind readers of how views strongly held in earlier decades have since been shown to be mistaken. This should encourage continuing skepticism of consensus views and motivate critics to sharpen their efforts at looking at new data, or at old data in new ways, and generating improved theories in the light of what they see.
We will be tracking two interrelated strands of intellectual effort: the methodology of modeling and inference for economic time series, and the
Date: January 3, 2012. c 2012 by Christopher A. Sims. This document is licensed under the Creative
Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License. http:// creativecommons.org/licenses/by-nc-sa/3.0/. 1

STATISTICAL MODELING OF MONETARY POLICY AND ITS EFFECTS

2

theory of policy influences on business cycle fluctuations. Keynes’s analysis of the Great Depression of the 1930’s included an attack on the Quantity Theory of money. In the 30’s, interest rates on safe assets had been at approximately zero over long spans of time, and Keynes explained why, under these circumstances, expansion of the money supply was likely to have little effect. The leading American Keynesian, Alvin Hansen included in his (1952) book A Guide to Keynes a chapter on money, in which he explained Keynes’s argument for the likely ineffectiveness of monetary expansion in a period of depressed output. Hansen concluded the chapter with, “Thus it is that modern countries place primary emphasis on fiscal policy, in whose service monetary policy is relegated to the subsidiary role of a useful but necessary handmaiden.”
Jan Tinbergen’s (1939) book was probably the first multiple-equation, statistically estimated economic time series model. His efforts drew heavy criticism. Keynes (1939), in a famous review of Tinbergen’s book, dismissed it. Keynes had many reservations about the model and the methods, but most centrally he questioned whether a statistical model like this could ever be a framework for testing a theory. Haavelmo (1943b), though he had important reservations about Tinbergen’s methods, recognized that Keynes’s position, doubting the possibility of any confrontation of theory with data via statistical models, was unsustainable. At about the same time, Haavelmo published his seminal papers explaining the necessity of a probability approach to specifying and estimating empirical economic models (1944) and laying out an internally consistent approach to specifying and estimating macroeconomic time series models (1943a).
Keynes’s irritated reaction to the tedium of grappling with the many numbers and equations in Tinbergen’s book finds counterparts to this day in the reaction of some economic theorists to careful, large-scale