\documentclass[12pt]{article}
\begin{document}
\noindent{\bf George Handley KNIBBS} \\
b. 13 June 1858 - d. 30 March 1929
\vspace{.5 cm}
\noindent{\bf Summary.} First government statistician after Federation
in Australia, Knibbs contributed significantly to vital statistics.
\vspace{.5 cm}
The Colonial Period in Australia extended from the time of European
settlement in 1788 until Federation in 1901. Early vital statistics
were provided in annual "Blue books" without analysis. Later, major
thrusts in the development of official statistics came from the
colonies of NSW, Victoria and Tasmania through the work of T.A. Coghlan,
H.H. Hayter and R.M. Johnson, respectively. However, rivalry between
the colonies and debate over protectionism in trade and population
issues constrained progress.
With Federation of the colonies in 1901 the Australian Commonwealth
Constitution gave the Federal Parliament authority over census and
statistics. However, it was not until 1906 that the Commonwealth
Bureau of Census and Statistics was created with George Handley Knibbs
as its Head.
Knibbs, who was born in Sydney,
was an unlikely appointment as the first Commonwealth
Statistician; he had no background in statistics or economics and
had been trained as a surveyor. He was Lecturer in Surveying at
the University of Sydney from 1890 to 1903. In 1904 he was Acting
Professor of Physics at the University of Sydney and in 1905 he became
Director-General of Technical Education for NSW.
Prior to his appointment
as Commonwealth Statistician Knibbs had, however, published on a wide range
of topics - fluid mechanics, observational
accuracy and surveying, effects of rainfall distribution on
agriculture, water conservation and irrigation and city planning,
albeit avoiding all considerations of randomness. These give the
impression of competence as a mathematician, and a comprehensive
knowledge of the international literature, but an obsessive
amount of detail is sometimes provided.
The remainder of Knibbs' publications, some seventy in number,
postdate his appointment as Commonwealth Statistician and all
deal with statistical topics with the exception of two books
of poetry published in 1913.
Knibbs interpreted his brief broadly as Commonwealth Sstaistician,
to be ``a professional expert in statecraft, assisting the administrative
statesmen with his counsel and advice", as well as to undertake the
task of unification and coordination of statistical effort, and
he set to work with zeal.
Following a trip through Europe in 1909 to examine various statistical
bureaux, and attend international congresses (including the ISI Session
in Paris), Knibbs prepared a report on social insurance in which he outlined
schemes operating elsewhere and made recommendations for Australia.
In this work he took pains to elaborate an organic theory of the state
and he justified public health measures on the grounds of national
development. It should be noted that Social Darwinism, the supposed
implications of evolutionary theory for social policy, was widely promoted
at the time, with argument over whether the society or the individual
was the developing organism. William Morris Hughes, Prime Minister
during World War 1, employed evolutionary theory to justify state
activity.
In Knibbs' work on social insurance he was led naturally to examine
causes of unemployment but he suffered from lack of public
co-operation both for this and for his work on the cost of living.
His interest in the cost of living did lead to theoretical work
on index numbers which, although well regarded in its time, was
of ephemeral interest. However, it did lead to the production of the
first Australian price indices based on clearly defined principles
and his advocacy was important in the wide international acceptance
of the fixed weights aggregative formula.
Knibbs' expectations were also high in terms of the possibilities for
a detailed nosological classification and he maintained a continuing
interest in this topic. His suggestions, which would have placed considerable
demands on the medical profession, not unexpectedly achieved limited success.
A prime task for Knibbs upon assuming office was to commence the
production of the Commonwealth {\it Year Book} and the first of these,
which drew heavily on principles already adopted by Hayter in
Victoria and Coghlan in NSW, appeared in 1908.
The {\it Year Books} were well received. Melbourne's {\it Argus} newspaper
referred to it as ``a monument to Knibbs' energy, clear-sightedness
and enthusiasm" while {\it The Times} (of London) in a leading
article described it as ``The most wonderful book of its kind in
the world...the creation of a genius...the Commonwealth Statistician,
and there is no other publication in the Empire to compare with it."
However, such praise for this kind of endeavour does not seem to
have been altogether exceptional.
Knibbs was responsible for the first Commonwealth Census conducted
in 1911 and this involved major organizational effort. The final
Census Report appeared in three volumes, comprising the Statistician's
Report (Volume 1) which provided a commentary on the detailed tables
of results making up Volumes 2 and 3. The most notable component of
Volume 1 was its Appendix A, Knibbs' ``The Mathematical Theory of
Population, of its Character and Fluctuations and of the Factors
which Influence Them" which was subsequently printed separately
(Knibbs (1917)).
This exhaustive treatise of 406 pages begins, after an introduction,
with seven chapters devoted to methodology and then eleven further
chapters giving a detailed discussion of the Australian population.
In the methodological component Knibbs emphasized population distributions
and the curves which represent them, and especially noteworthy is his
discussion of smoothing.
Knibbs received almost universal praise for this treatise. Arne Fisher
considered that it would ``stand as one of the leading works on
mathematical statistics of the twentieth century" and ``it is equal
to the French classics on the calculus of probability by Laplace and
Poisson...". More qualified approval, however, was provided by Yule (q.v.),
Elderton and R.A. Fisher (q.v.), who praised the work for its broad scope
but found fault with various aspects of its theoretical content.
Yule and Elderton both took some exception to Knibbs fitting of his
own ``flexible curve" of the form $y=A{x}^m{exp(nx^p)}$ and to his
rather cursory treatment of Pearson's system of frequency curves,
while R.A. Fisher noted the complete absence of any discussion of
goodness of fit. Knibbs had described the Pearson curves as having
a limited range of shapes available and he sought to encompass
as many as possible in a singler formula. However, his procedure
for fitting these curves was less than straightforward. The work
was widely referenced in the population literature of the time,
but principally for its encyclopaedic nature and extensive
tabulations rather than for particular items of methodological
content.
Knibbs became a staunch advocate of what he termed ``The New
Malthusianism" and in his book {\it The Shadow of the World's Future}
(1928) argued that if present growth continued the world would reach
its maximum population in less than two hundred and fifty years.
Knibbs also provided eugenic arguments for selective migration.
He had earlier been active in the eugenics movement, and in 1921
was elected Vice-President of the 2nd International Eugenics
Congress held at New York.
Knibbs resigned his position as Commonwealth Statistician in 1921
to become Director of the newly constituted Commonwealth Institute
of Science and Industry (the forerunner of CSIRO). He was knighted
in 1923. He was a man of strong opinions, forthright and
public spirited, and was very much motivated by the special problems
of his country and his times. He was a forceful advocate but his expectations
were often unreasonably high and were not fully met. Nevertheless,
his achievements as Commonwealth Statistician were widely applauded
internationally and were a model for others. He died in Sydney in
1929.
\vspace{.5cm}
\noindent{\bf Bibliography}
\noindent Bambrick, S. (1983). Knibbs, Sir George Handley (1858-1229).
{\it Australian Dictionary of Biography}, Melbourne Univ. Press,
Melbourne, Vol.9, 620-621.
\noindent Heyde, C.C. (1988). Official statistics in the late colonial
period leading on to the work of the first Commonwealth Statistician,
G.H. Knibbs. {\it Australian Journal
of Statistics}, {\bf 30(B)}, 23-43.
\noindent Knibbs, G.H. (1917). The Mathematical Theory of Population, of
its Character and Fluctuations and of the Factors which Influence Them.
Appendix A, Vol. 1, {\it Census of the Commonwealth of Australia},
Aust. Govt. Printer, Melbourne.
\vspace{1 cm}
\hfill{C.C. Heyde}
\end{document}