BEGIN:VCALENDAR
PRODID:-//Columba Systems Ltd//NONSGML CPNG/SpringViewer/ICal Output/3.3-
M3//EN
VERSION:2.0
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VEVENT
DTSTAMP:20230228T141633Z
DTSTART:20230315T140000Z
DTEND:20230315T150000Z
SUMMARY:Rebecca Lewis - Cox reduction and confidence sets of models (- i
n person stat seminar)
UID:{http://www.columbasystems.com/customers/uom/gpp/eventid/}akp-la0xpfa
t-ys1frw
DESCRIPTION:Rebecca Lewis\, PhD student in the Department of Mathematics
at the Imperial College London is our speaker for the Statistics seminar
series.\n\nTitle: Cox reduction and confidence sets of models\n\nAbstra
ct: In the context of sparse high-dimensional regression problems\, Cox
and Battey (2017\, 2018) emphasised the need for confidence sets of mode
ls: an enumeration of those small sets of variables that fit the data eq
uivalently well in a suitable statistical sense. This is to be contraste
d with the single model returned by penalised regression procedures\, ef
fective for prediction but potentially misleading for subject-matter und
erstanding. In this talk\, I will provide insights into Cox and Battey's
proposed construction of a model confidence set\, characterising the mo
dels that are likely to be retained in the set\, identifying features of
the covariate matrix that may reduce the procedure's efficacy and sugge
sting improvements to mitigate these.\n\nVenue:\nRoom G108 \nAlan Turing
Building \nManchester\nM13 9PL
STATUS:TENTATIVE
TRANSP:TRANSPARENT
CLASS:PUBLIC
LOCATION:Room G108 \, Alan Turing Building \, Upper Brook street\, Manche
ster\, M13 9PL
END:VEVENT
END:VCALENDAR