Seminar

Cultural imagery and statistical models of the force of mortality, and a new (old?) way to make the link between its integral and the survival function

Wednesday, 21 March 2012
Time: 
09:30 to 10:30
MEGA, Room 515, School of Population Health, Melbourne University
Level 5, 207 Bouverie Street
Parkville
Australia

We describe selected artistic and statistical depictions of the force of mortality [hazard or mortality rate], a concept that has long pre-occupied actuaries, demographers and statisticians. We provide a more graphic form for the force of mortality function that makes the relationship between its constituents more explicit.

The "Bridge of Human Life" in Addison's (1711) allegorical essay provides a particularly vivid image, with the forces depicted as external. The model used by Gompertz (1825) appears to treat the forces as internal.

In his 1897 essay Pearson mathematically modernises "the medieval conception of the relation between Death and Chance" by decomposing the full mortality curve into five distributions along the age axis, the results of five "marksmen" aiming at the human mass crossing this bridge.

We describe Addison's imagery; comment briefly on Gompertz's law and the origin of the term 'force of mortality'; describe the background for Pearson's essay, as well as his imagery and statistical model; and give the Bridge of Life a modern form, illustrating it via statistical animation.

We use Edmonds' (1832) concept of person-time, and the Poisson distribution, to provide a new (old?) way to make the link between the integral of the hazard function and the survival function.

 

Prof. James Hanley

Professor Hanley has been involved in a wide range of research in epidemiology, and has contributed to the methodology of diagnostic test evaluation, agreement statistics, analysis of correlated data, meta-analysis and most recently the statistics of cancer screening.

After a PhD in biostatistics and an early-career post at Harvard, Jim moved to Montreal in the 1980's and since 1993 he has been professor in the Department of Epidemiology and Biostatistics in the faculty of Medicine at McGill University and a Senior Scientist in the Division of Clinical Epidemiology at the Royal Victoria Hospital. He has published and collaborated extensively, and has written several expository articles on statistical methods, statistical thinking, and statistical/epidemiological history.

For more details, see: http://www.biostat.mcgill.ca/hanley