BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20251104T070843EST-6930uu0f42@132.216.98.100
DTSTAMP:20251104T120843Z
DESCRIPTION:The Law of Large Populations: The return of the long-ignored N 
 and how it can affect our 2020 vision\n\nFor over a century now\, we stati
 sticians have successfully convinced ourselves and almost everyone else\, 
 that in statistical inference the size of the population N can be ignored\
 , especially when it is large.  Instead\, we focused on the size of the sa
 mple\, n\, the key driving force for both the Law of Large Numbers and the
  Central Limit Theorem. We were thus taught that the statistical error (st
 andard error) goes down with n typically at the rate of 1/√n.   However\, 
 all these rely on the presumption that our data have perfect quality\, in 
 the sense of being equivalent to a probabilistic sample.  A largely overlo
 oked statistical identity\, a potential counterpart to the Euler identity 
 in mathematics\, reveals a Law of Large Populations (LLP)\, a law that we 
 should be all afraid of. That is\, once we lose control over data quality\
 , the systematic error (bias) in the usual estimators\, relative to the be
 nchmarking standard error from simple random sampling\, goes up with N at 
 the rate of √N.   The coefficient in front of √N can be viewed as a data d
 efect index\, which is the simple Pearson correlation between the reportin
 g/recording indicator and the value reported/recorded.  Because of the mul
 tiplier√N\, a seemingly tiny correlation\, say\, 0.005\, can have detrimen
 tal effect on the quality of inference.  Without understanding of this LLP
 \,  “big data” can do more harm than good because of the drastically infla
 ted precision assessment hence a gross overconfidence\, setting us up to b
 e caught by surprise when the reality unfolds\, as we all experienced duri
 ng the 2016 US presidential election. Data from Cooperative Congressional 
 Election Study (CCES\, conducted by Stephen Ansolabehere\, Douglas River a
 nd others\, and analyzed by Shiro Kuriwaki)\,   are used to estimate the d
 ata defect index for the 2016 US election\, with the aim to gain a clearer
  vision for the 2020 election and beyond.\n
DTSTART:20180216T203000Z
DTEND:20180216T213000Z
LOCATION:Room 217\, Maass Chemistry Building\, CA\, QC\, Montreal\, H3A 0B8
 \, 801 rue Sherbrooke Ouest
SUMMARY:Xiao-Li Meng\, Harvard University\, 
URL:/mathstat/channels/event/xiao-li-meng-harvard-univ
 ersity-285076
END:VEVENT
END:VCALENDAR