Graphics Reference
In-Depth Information
1900-1950: The Modern Dark Ages
1.2.6
Ifthe late
swere the 'golden age' of statistical graphics and thematic cartography,
the early
s can be called the 'modern dark ages' of visualization (Friendly and
Denis,
).
here were few graphical innovations, and by the mid-
s the enthusiasm for
visualization which characterized the late
s had been supplanted by the rise of
quantification and formal, oten statistical, models in the social sciences. Numbers,
parameterestimates and,especially, those with standard errorswereprecise.Pictures
were -well, just pictures:pretty or evocative, perhaps, but incapable of stating a 'fact'
to three or more decimals. Or so it seemed to many statisticians.
But it is equally fair to view this as a time of necessary dormancy, application and
popularization rather than one of innovation. In this period statistical graphics be-
came mainstream. Graphical methods entered English
textbooks (Bowley,
;
Peddle,
; Haskell,
; Karsten,
), the curriculum (Costelloe,
; Warne,
) and standard use in government (Ayres,
), commerce (Gantt charts and
Shewart's control charts) and science.
hese textbooks contained rather detailed descriptions of the graphic method,
with an appreciative and oten modern flavour. For example, Sir Arthur Bowley's
(
) Elements of Statistics devoted two chapters to graphs and diagrams and dis-
cussedfrequencyandcumulative frequencycurves(withgraphicalmethodsforfind-
ing the median and quartiles), effects of choice of scales and baselines on visual esti-
mationofdifferencesandratios,smoothingoftime-seriesgraphs,rectanglediagrams
in which three variables could be shown by height, width and area of bars, and 'his-
torical diagrams' in which two or more time series could be shown on a single chart
for comparative views of their histories.
Bowley's(
,pp.
-
)exampleofsmoothing(Fig.
.
)illustrates thecharac-
terofhisapproach.HereheplottedthetotalvalueofexportsfromBritainandIreland
over the period
-
. At issue was whether exports had become stationary in
the most recent years, and the conclusion by Sir Robert Giffen (
), based solely
on tables of averages for successive
-year periods,
that 'the only sign of stationari-
ness is an increase at a less rate in the last periods than in the earlier periods' (p.
).
To answer this, he graphed the raw data, together with curves of the moving average
over
-,
- and
-year periods. he
- and
-year moving averages show strong evi-
denceofanapproximately
-yearcycle,andhenoted,'noargumentcanstand which
does not take account of the cycle of trade, which is not eliminated until we take de-
cennial averages' (p.
). To this end, he took averages of successive
-year periods
starting
and drew a freehand curve 'keeping as close [to the points] as possible,
he first systematic attempt to survey, describe and illustrate available graphic methods for
experimental data was that of Étienne Jules Marey's (
) La Méthode Graphique.Marey
[
-
] also invented several devices for visual recording, including the sphymograph
andchronophotographytorecordthemotion ofbirdsinflight,people runningandsoforth.
Giffen, an early editor of he Statist, also wrote a statistical text published posthumously in
; it contained an entire chapter on constructing tables, but not a single graph (Klein,
, p.
).
