BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20261009T104839EDT-8057KVOZVD@132.216.98.100
DTSTAMP:20261009T144839Z
DESCRIPTION:Biostatistics Research At The Quebec Public Health Institute: I
 n Search Of An Unbiased Life Expectancy Estimator For Regional Populations
 .\n\nErnest Lo holds a PhD in physics from Princeton University and a Mast
 ers in biostatistics from McGill. He has worked in diverse fields includin
 g theoretical ecology\, neuroimaging and bioinformatics. Ernest is current
 ly a biostatistician and research scientist at the Quebec Public Health In
 stitute\, as well as Adjunct Professor in the department of Epidemiology\,
  Biostatistics and Occupational Health at McGill. His mandates include hea
 lth forecasting\, estimation of social inequalities in health\, and the im
 provement of statistical methods used in public health.\n\n	Life expectancy
  (LE) is a key indicator of population health whose estimated values have 
 enormous impact for both the public and for policy makers. Although LE is 
 routinely calculated by health agencies worldwide\, little is known as to 
 whether or not LE is in fact an unbiased estimator. Regional level estimat
 es of life expectancy within Quebec have shown evidence of severe upward b
 ias\, leading to implausibly high values\, when the standard\, actuarial m
 ethod is used. A geometrical argument can be used to demonstrate that this
  bias is produced by inaccuracy in the closure model\, or the way mortalit
 y or survival is modeled over the last\, open age interval. An alternative
  class of closure models uses extrapolation to estimate mortality over the
  oldest age interval\; these include the Gompertz\, Hsieh and Kannisto app
 roaches. In contrast\, a ‘relational’ approach\, termed the Brass method\,
  transforms a reference survival curve to that of each population being es
 timated. Each of these methods is described and their performance\, with r
 espect to bias and variance\, is assessed over empirical datasets and usin
 g of Monte Carlo simulation. Themes that will be addressed include: 1) str
 ategies to evaluate bias in the absence of gold standard knowledge of the 
 ‘true’ LE for a given population\, 2) sensitivity of bias and variance to 
 key parameters implicit within each LE model\, 3) the relation between alt
 ernative models of LE and different approaches of ‘borrowing strength’. Th
 is work represents the first detailed comparison of the bias and variance 
 of different population-level LE estimators. In addition to the statistica
 l import of the findings\, it is hoped that the results will lead to impro
 ved LE estimation by public health agencies and thus to improved public he
 alth planning and policies.\n\n\n\n
DTSTART:20180130T203000Z
DTEND:20180130T213000Z
LOCATION:Room 24\, Purvis Hall\, CA\, QC\, Montreal\, H3A 1A2\, 1020 avenue
  des Pins Ouest
SUMMARY:Ernest Lo\, PhD\, McGill University
URL:https://www.mcgill.ca/mathstat/channels/event/ernest-lo-phd-mcgill-univ
 ersity-284247
END:VEVENT
END:VCALENDAR