The statistics of dying

I have often commented in the past that the supposed scientific revolution is described in popular presentations as the astronomical revolution and the modernisation of physics with sometimes a bit of medicine tacked on to make it seem broader whereas in fact in the period between about 1400 and 1700 CE a very wide spectrum of academic disciplines went through a period of renewal or were created for the first time driven by the socio-economic and political pressures of the age. Today’s birthday boy John Graunt, born on the 24th April 1620, is credited with creating a completely new discipline, that bane of all sociology students, statistical demography.

Graunt was the son of a draper who earned his living as a haberdasher; he was active in politics and became interested in demography producing the first statistical analysis of life expectancies and rates of death based on an analysis of the London Bills of Mortality, weekly announcements of the deaths in London. He published the results of his work, in which he was probably assisted by his close friend William Petty, in his Natural and Political Observations mentioned in a following index, and made upon the Bills of Mortality With reference to the Government, Religion, Trade, Growth, Ayre, diseases, and the several Changes of the said City in 1662. His book also included the first sensible and probably accurate estimate of the population of London, 384 000. As always in the history of science Graunt’s work did not appear out of thin air but built upon earlier writings on probability by Cardano, Pascal and Fermat amongst others as well as the statistical work of Richard Witt and James Howell.

Graunt’s pioneering work was developed by Petty in his Political Arithmetic, published posthumously in 1690, and Edmund Halley in his An estimation of the degrees of mortality of mankind published in the Philosophical Transactions of the Royal Society in 1693. In Holland the Cartesian mathematicians Jan De Witt and Johann Hudde both made significant contribution to the science of statistical demography in the same period.

In his private life Graunt suffered twice through the Great Fire of London. He lost all of his property and with it his wealth in the fire and having recently converted from the Puritanism of his youth to Catholicism he was accused of having laid the fire, charges of which he was finally cleared. Amongst statisticians and historians of statistics he is regarded as the ‘Columbus’ of demography and the distinguished epidemiologist Kenneth J. Rothman writing in Lancet said of Graunt, “With [Graunt’s book on the Bills of Mortality] he added more to human knowledge than most of us can reasonably aspire to in a full career.”


Filed under History of science

3 responses to “The statistics of dying

  1. Pingback: The statistics of dying | Whewell's Ghost

  2. Mike Flynn

    And in his analysis he showed that he understood what today quality practitioners call “the Pareto Principle”; viz., the common fact that in any enumeration of a problem, the vast bulk of the problem is concentrated in a few categories. He pointed out in one analysis that roughly half of all deaths fell into a mere three categories: Chrisomes & Infants, Consumption, and Fever and that modest progress on these three counted for more than utter success on the many smaller categories. He also understood the problem of operational definitions. Fever, he wrote, might include a wide range of actually distinct diseases, as the name simply means “first he got hot, then he died.” The categorization of death causes were made independently by a wide and largely untrained body of neighborhood “death-watchers,” and these did not always do so in consistent and repeatable ways. Finally, he understood what today we call “process” when he noted that Chrisomes/Infants, Abortive/Stillborn, and Childbed were all metrics pertaining to the same process, that of pregnancy and birth. I’ve often used one of his analyses in training classes for statistical process control.

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s