8 Methodology of Empirical Econometric Modeling
of simultaneity, identification, exogeneity, and partial effects (see Wright, 1915,
1929; Working, 1927; Tinbergen, 1930,inter alia).
Equally importantly, many “strange” empirical correlations had been found that
stimulated the unraveling of both spurious, and later nonsense, regressions in
works such as Yule (1897), Hooker (1901), and especially the famous explanation
in Yule (1926), leading first to a distinction between short-run and long-term rela-
tionships, then unit roots, and eventually cointegration, as in Granger (1981),
and dozens of later contributions surveyed in Hendry and Juselius (2000, 2001).
Despite obvious progress – Stigler (1962) begins his article about Moore by “If one
seeks distinctive traits of modern economics, traits which are not shared to any
important degree with the Marshallian or earlier periods, he will find only one:
the development of statistical estimation of economic relationships” – trouble lay
ahead.
The attack by Robbins (1932) on the empirical studies of Schultz (1928) – por-
trayed as the feckless Dr. Blank studying the demand for herring (rather than
sugar) – was the first of several critiques which sought to deny any substantive
role for econometrics in economics.^1 Tinbergen’s attempts to build empirical mod-
els of investment activity brought down the wrath of John Maynard Keynes (see
Tinbergen, 1939, 1940; Keynes, 1939, 1940), who insisted that the economist had
to be “in the saddle” with the econometrician as the “patient ass,” and sarcastically
demanded that Tinbergen satisfy:
an experiment on his part. It will be remembered that the seventy translators
of the Septuagint were shut up in seventy separate rooms with the Hebrew text
and brought out with them, when they emerged, seventy identical translations.
Would the same miracle be vouchsafed if seventy multiple correlators were shut
up with the same statistical material? And anyhow, I suppose, if each had a
different economist perched on hisa priori, that would make a difference to the
outcome.We will return in section 1.4 both to that issue, which may well now be possible,
and to Keynes’ general claims – one might like to ponder whether 70 economic
theorists asked to tackle the same puzzle would derive precisely the same model?
As ever, other more constructive outcomes followed from that debate, especially
the memorandum by Frisch (1938), and it certainly did not discourage Haavelmo
(1944).
1.3.2 War and post-war
“I’ll tell you all my ideas about Looking-glass House. First, there’s the room
you can see through the glass – that’s just the same as our drawing-room,
only the things go the other way.” (Quote from Alice in Lewis Carroll,
1899)Despite Koopmans (1937) being a key precursor to the establishment of modern
econometrics in Haavelmo (1944), the attack by Koopmans (1947) on Burns and