PARTI
IntroductionCHAPTER 1
Econometric modelling, a preliminary view
1.1 Econometrics ~ a brief historical overview
It is customary to begin a textbook by defining its subject matter. In this
case this brings us immediately up against the problem of defining
“econometrics. Such a definition, however, raises some very difficult
methodological issues which could not be discussed at this stage. The
epilogue might be a better place to give a proper definition, For the
purposes of the discussion which follows it suffices to use a working
definition which provides only broad guide-posts of its intended scope:
Econometrics is concerned with the systematic study of economic
phenomena using observed data.
This definition is much broader than certain textbook definitions
narrowing the subject matter of econometrics to the ‘measurement’ of
theoretical relationships as suggested by economic theory. It is argued in
the epilogue that the latter definition of econometrics constitutes a relic of
an outdated methodology, that of the logical positivism (see Caldwell
11982)), The methodological position underlying the definition given above
is largely hidden behind the word ‘systematic’. The term systematic is used
to describe the use of observed data in a framework where economic theory
a8 well as statistical inference play an important role, as yet undefined. The
use of observed data is what distinguishes econometrics from other forms of
studying economic phenomena.
Econometrics, defined as the study of the economy using observed data,
can be traced as far back as 1676, predating economics as a separate
discipline by a century. Sir William Petty could be credited with the first
3inary view
4 A preli
‘systematic’ attempt to study economic phenomena using data in his
Political Arithmetik. Systematic in this case is used relative to the state of the
art in statistics and economics of the time.
Petty (1676) used the pioneering results in descriptive statistics developed
by his friend John Graunt and certain rudimentary forms of economic
theorising to produce the first ‘systematic’ attempt in studying economic
phenomena using data, Petty might also be credited as the first to submit to
4 most serious temptation in econometric modelling. According to Hull,
one of his main biographers and collector of his works:
Petty sometimes appears to be seeking figures that will support a
conclusion he has already reached: Graunt uses his numerical data as a
basis for conclusions, declining to go beyond them:
(Sce Hull (1899), p. xxv.)
Econometrics, since Petty’s time, has developed alongside statistics and
economic theory borrowing and lending to both subjects. In order to
understand the development of econometrics we need to relate it to
developments in these subjects.
Graunt and Petty initiated three important developments in statistics:
i the systematic collection of (numerical) data;
(i) the mathematical theory of probability related to life-tables; and
(iii) the development of what we nowadays call descriptive statistics
(see Chapter 2) into a coherent set of techniques for analysing
numerical data.
It was rather unfortunate that the last two lines of thought developed
largely independent of each other for the next two centuries. Their slow
convergence during the second half of the nineteenth and early twentieth
centuries in the hands of Galton, Edgeworth, Pearson and Yule, inter alia,
culminated with the Fisher paradigm which was to dominate statistical
theory to this day
The development of the calculus of probability emanating from Graunt’s
work began with Halley [1656-1742] and continued with De Moivre
[1667-1754], Daniel Bernoulli [1700-82], Bayes [1702-61], Lagrange
[1736-1813], Laplace [1749-1827], Legendre [1752-1833], Gauss [1789-
1857] imter alia, In the hands of De Moivre the main line of the calculus of
probability emanating from Jacob Bernoulli [1654-1705] was joined up
with Halley's life tables to begin a remarkable development of probability
theory (see Hacking (1975), Maistrov (1974)
The most important of these developments can be summarised under the
following headings:
(i) manipulation of probabilities (addition, multiplication);