BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:How should we teach (frequentist) statistics? Coverage and interva
l estimation
DTSTART:20220628T155500Z
DTEND:20220628T161500Z
DTSTAMP:20240226T104900Z
UID:indico-contribution-264@conferences.enbis.org
DESCRIPTION:Speakers: Mark Schaffer (Heriot-Watt University)\n\nThe use of
"Null hypothesis significance testing" and $p$-values in empirical work h
as come in for widespread criticism from many directions in recent years.
Nearly all this commentary has\, understandably\, focused on research prac
tice\, and less attention has been devoted to how we should teach economet
rics (my home discipline) and applied statistics generally. I suggest that
it is possible to teach students how to practice frequentist statistics s
ensibly if the core concepts they are taught at the start are coverage and
interval estimation. Teaching interval estimation rather than point estim
ation as the main objective automatically emphasises uncertainty. The key
concept of coverage can be taught by analogy with the well-known children'
s game Pin-the-Tail-on-the-Donkey. In "Pin-the-Ring-on-the-Donkey"\, the p
oint estimator of the donkey's tail is replaced by a ring\, and coverage p
robability is the probability that the ring will contain the correct locat
ion for the donkey's tail. The simplest version of the game is analogous t
o a prediction interval in a time-series setting\, where taking off the bl
indfold and seeing if the tail is in the ring to corresponds to waiting a
period to see if the realised outcome lies in the interval. The "Mystery-P
in-the-Ring-on-the-Donkey" version of the game is analogous to a confidenc
e interval for a parameter: when we play the game\, the image of donkey is
removed before we take off the blindfold\, so we never find out if we won
. The analogy can also be used to illustrate the difference between CIs an
d realised CIs and other subtleties.\n\nhttps://conferences.enbis.org/even
t/18/contributions/264/
LOCATION:EL5
RELATED-TO:indico-event-18@conferences.enbis.org
URL:https://conferences.enbis.org/event/18/contributions/264/
END:VEVENT
END:VCALENDAR