BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:The Cycle of Statistical Research - Qingyuan Zhao (Statistical Lab
 oratory)
DTSTART:20200219T150000Z
DTEND:20200219T160000Z
UID:TALK136282@talks.cam.ac.uk
CONTACT:J.W.Stevens
DESCRIPTION:More than fifty years ago\, John Tukey first envisioned a fiel
 d we now call "Data Science" (he called it "Data Analysis") to replace aca
 demic statistics. George Box\, who famously said "all models are wrong"\, 
 instead called "Data Analysts [to] get themselves together and become whol
 e Statisticians before it is too late". Despite their differences\, both T
 ukey and Box relentlessly emphasised on the cycle of statistical research:
  Conjecture -> Design -> Analysis -> Conjecture -> Design -> Analysis -> .
 ... This talk argues that the problem is not whether we should call someth
 ing "Statistics" or "Data Science". The problem is that we should take a h
 olistic view of any statistical research and participate in every part of 
 the cycle. This point will be illustrated by two research problems that th
 e speaker has been working on: one is on the cholesterol hypothesis and th
 e controversial role of HDL cholesterol\; the other is on the current nove
 l coronavirus outbreak around the world.
LOCATION:MR14\, Centre for Mathematical Sciences
END:VEVENT
END:VCALENDAR