Transcript Interwar Metrics
Interwar Metrics
Session 7
Econometrics
• • • New economic discipline which arose in the 1930s Explicit aim to turn economics into a science Science: quantification = mathematical expression of economic ideas which should be measured by economic statistics
Ragnar Frisch 1926
“Intermediate between mathematics, statistics, and economics, we find a new discipline which, for the lack of a better name, may be called econometrics. Econometrics has as its aim to subject abstract laws of theoretical political or “pure” economics to experimental and numerical verification, and thus to turn pure economics, as far as possible, into a science in the strict sense of the word.” 1895 – 1973 Nobel Prize 1969
Econometric Society 1930 The first organizational meeting of the Society was held in Cleveland, Ohio, on December 29, 1930.
The first scientific meetings of the Society were held in September, 1931, at the University of Lausanne, Switzerland, and in December, 1931, in Washington D.C.
Constitution
“The Econometric Society is an international society for the advancement of economic theory in its relation to statistics and mathematics. The Society shall operate as a completely disinterested, scientific organization without political, social, financial, or nationalistic bias. Its main object shall be to promote studies that aim at a unification of the theoretical-quantitative and the empirical quantitative approach to economic problems and that are penetrated by constructive and rigorous thinking similar to what has come to dominate in the natural sciences.”
Robert Merton (1942)
• • • • Communalism – the common ownership of scientific discoveries, according to which scientists give up intellectual property in exchange for recognition and esteem.
Universalism – according to which claims to truth are evaluated in terms of universal or impersonal criteria, and not on the basis of race, class, gender, religion, or nationality.
Disinterestedness – according to which scientists are rewarded for acting in ways that outwardly appear to be selfless.
Organized skepticism – all ideas must be tested and are subject to rigorous, structured community scrutiny.
Cowles Commission
ALFRED COWLES, 3rd (1891–1984) Founder and President (September 1932 – September 1934) “Can Stock Market Forecasters Forecast?” Econometrica, 1(3).
Colorado Springs 1932-1939 (3rd floor)
Frisch’s Editorial
Experience has shown that each of these three view-points, that of statistics, economic theory, and mathematics, is a necessary, but not by itself a sufficient, condition for a real understanding of the quantitative relations in modern economic life. It is the unification of all three that is powerful. And it is this unification that constitutes econometrics. (p. 2)
Econometrics (textbook)
1. First, the model must be specified in explicit functional – often linear – form.
2. The second step is to decide on the appropriate data definitions, and to assemble the relevant data series for those variables included in the model. 3. The third step is to form a bridge between theory and data through the use of statistical methods. The bridge consists of various sets of statistics, which help to determine the validity of the theoretical model.
Harvard A-B-C Barometer
A Speculation ; B Business ; C Money
Karl G. Karsten – Quadrature Theory
𝑡
𝐵
𝑖 𝑖=1
= 𝐴
𝑡+3 0 𝑡
𝐵 𝜏 = 𝐴(𝑡 + 3)
𝑡
(
1 4 𝐴 𝑖 + 3 4 𝐵 𝑖
) = 𝐶
𝑡 𝑖=1 0 𝑡 1 4
𝐴 𝜏 +
3 4
𝐵 𝜏 𝑑𝜏 = 𝐶(𝑡)
Quadrature Theory
In the calculus such relations are familiar in the form of integrals and derivatives, and although these functions are purely mathematical, they are useful to describe the behavior of related forces in the physical sciences. It is the quadrature theory that economic data or statistics betray the same relationships when similarly treated, and that when this is the case, the economic forces or phenomena measured by statistics may be said to be in quadrature and a real relation is strongly suggested.
Bullock, Persons & Crum
“Causal relations have, indeed, received increasing attention from us; but no theory of causation or of time relation between cause and effect ever entered into the construction of the index.” “how foreign to actual experience are fixed mechanical, or exact mathematical, relationships in the economic world.”
Evgeny Evgenievich Slutsky
• • 1880-1948 Ukrainian mathematical statistician, economist and political economist.
The Summation of Random Causes as the Source of Cyclic Processes 1927
Propagation and Impulse
y
2 ( 2 2 )
y
0
y
(
t
)
P
(
t
)
P
(
t
t
0 )
y
0
Q
(
t
t
0 )
y
0
C P e
t
sin(
t
)
Q
(
t
)
k n
1
Q
(
t
t k
)
e k C Q e
t
sin
t y
(
t
)
k n
1
Q
(
t
t k
)
e k
Mechanism
P(t) and Q(t) explained by economic mechanism Represented by 3 equations:
y
mx
x
x
z t
c
0
D
y t
(
rx
d
sz
)
Jan Tinbergen
1936, Vereeniging voor de Staathuishoudkunde en de Statistiek (Dutch Economic and Statistical Society) 1st macro-econometric model: Dutch economy 1939, League of Nations 2nd macro-econometric model: US economy 1903 – 1994 Nobel prize 1969
A New Practice
Jan Tinbergen Quantitative Fragen der Kunjunkturpolitik 1935 Model 1. the presentation of a simplified business cycle ‘mechanism’, 2. an analysis of its various ‘influencing coefficients’, with a view to discovering those which might be modified by policy, and 3. an analysis of the conditions which would have to be satisfied in order to achieve the aims set by various types of policy.
20
Prof. Tinbergen’s Method
Keynes – Tinbergen Debate
John Maynard Keynes Jan Tinbergen
Keynes – Tinbergen debate
• • Tinbergen, Jan (1939). Statistical Testing of
Business-Cycle Theories. Vol. I A Method and
its Application to Investment Activity.
Keynes, John Maynard (1939). Professor Tinbergen’s method. The Economic Journal.
Keynes’ Critique
Measurement – Not Testing
“Am I right in thinking that the method of multiple correlation analysis essentially depends on the economist having furnished, not merely a list of the significant causes, which is correct so far as it goes, but a complete list? For example, suppose three factors are taken into account, it is not enough that these should be in fact veræ causæ ; there must be no other significant factor. If there is a further factor, not taken account of, then the method is not able to discover the relative quantitative importance of the first three. If so, this means that the method is only applicable where the economist is able to provide beforehand a correct and indubitably complete analysis of the significant factors.”
Keynes’s Critique:
• • • • • • Solely a method for measurement. It contributed nothing in terms of either discovery or testing.
If the economic theorist does not provide the modeler with a complete set of causal factors, then the measurement of the other causal factors will be biased.
Some significant factors in any economy are not capable of measurement, or may be interdependent.
Assumed linearity of the relations between these factors.
The determination of time-lags and trends was too often based on trial and error, and too little informed by theory.
Would the relations found also hold for the future?
John Maynard Keynes 1939
Critique: only a method of measurement, no discovery, neither testing Studied the unpublished writings of Newton: more than half related to alchemy: transmutation, philosopher’s stone, elixir of life
Alchemy
“Newton was not the first of the age of reason. He was the last of the magicians, the last of the Babylonians and Sumerians ….”
Statistical Alchemy
“No one could be more frank, more painstaking, more free from subjective bias or parti pris than Professor Tinbergen. There is no one, therefore, so far as human qualities go, whom it would be safer to trust with black magic. That there is anyone I would trust with it at the present stage or that this brand of statistical alchemy is ripe to become a branch of science, I am not yet persuaded. But Newton, Boyle and Locke all played with Alchemy. So let him continue.”
Milton Friedman
• • • • 1912 – 2006 Nobel Prize 1976 Chicago School of Economics NBER
Review of Tinbergen’s Volume II
Tinbergen’s results cannot be judged by ordinary tests of statistical significance. The reason is that the variables […] have been selected after an extensive process of trial and error because they yield high coefficients of correlation. Tinbergen is seldom satisfied with a correlation less than .98. But these attractive correlation coefficients create no presumption that the relationships they describe will hold in the future. The multiple regression equations which them are simply tautological reformulations of selected economic data. (p. 659)
Quoting Mitchell 1927
“The proposition may be ventured that a competent statistician, with sufficient clerical assistance and time at his command, can take almost any pair of time series for a given period and work with them into forms which will yield coefficients of correlation exceeding which their formula may be applied.” .9. […] So work of the sort […] must be judged, not by the coefficients of correlation obtained within the periods for which they have manipulated the data, but by the coefficients which they get in earlier or later periods to Arguing against Irving Fisher and Karl Karsten
Comment on Cowles Commission
• • The Commission moved to Chicago in 1939 and was affiliated with the University of Chicago until 1955.
Competition, see Rockefeller report
1948 Rockefeller report
“we someday hope to have a general theory of economic fluctuations … a general model must be based on precise tested knowledge of the behavior of component segments of the economy, on a reasonably exact and comprehensive knowledge of the phenomena generalized. In the absence of such knowledge, there will be such a wide variety of general models capable of explaining the limited number of observed phenomena that it will not be possible to choose rationally among them … it will take decades of careful monographic work in constructing foundations before we shall be ready to put up the kind of superstructure that the Cowles commission hope to create full blown … The Cowles commission staff itself includes … able people who have an almost religious belief in the unique correctness of their approach … Almost without exception, the people listed are primarily mathematicians or statisticians rather than economists and have had no occasion to do careful scientific quantitative work on a limited segment of the economy …’’