BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Drupal: Date iCal//NONSGML kigkonsult.se iCalcreator 2.16.12//
METHOD:PUBLISH
X-WR-CALNAME;VALUE=TEXT:Ical
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:STANDARD
DTSTART:20221106T020000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20220313T020000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:calendar.1628131.field_date.0@www.iq.harvard.edu
DTSTAMP:20230201T040137Z
DESCRIPTION:\n Today's speaker: Tracy Ke (Harvard Department of Statistics)\
, 'Learning Research Areas and Author Research Interests from Bibtex and C
itations'\n\n\n\n Abstract\n\n\n\n \;\n\n\n\n Given the scientific publi
cations in a field\, we are interested in using bibtex and citation data t
o estimate (a) the primary research areas in this field\, (b) the research
interests of individual authors (which may evolve with time)\, and (c) th
e citation impacts of different research topics in this field. We answer q
uestions (a)-(b) by studying the co-citation networks of authors. We model
them by a dynamic mixed-membership model\, where each primary area is a “
community”\, and the author research interests are described by the time-v
arying “mixed membership vectors”. We propose a spectral algorithm for est
imating these membership vectors. We answer question (c) by joint modeling
citations and paper abstracts. We propose the Hofmann-Stigler model\, whi
ch imposes K “topic vectors” in text abstracts\, K “export scores” to mode
l the citation impact of these topics\, and a “topic weight vector” for ea
ch paper. We propose a spectral algorithm for parameter estimation\, which
output can be used to rank topics.\n\n\n\n We implemented our methods in a
data set about publications in statistics. It covers over 83K papers in 3
6 journals in statistics spanning 41 years. We discovered a “Statistics Tr
iangle” that is connected to Bradley Efron’s Statistics Philosophy Triangl
e (Efron’s triangle is subjective\, but our triangle is from data). We als
o discovered the trend of moving towards the popular sub-area of “High-dim
ensional Data Analysis” of quite a few high-profile authors. We also found
that the research topic “Mathematical Statistics” is ranked 1st in terms
of the citation impact.\n\n\n\n This is joint work with Pengsheng Ji\, Jias
hun Jin and Wanshan Li. The talk is partially based on the paper “Co-citat
ion and Co-authorship Networks of Statisticians” (Journal of Business &
\; Economic Statistics\, to appear).\n\n\n\n \;\n\n\n\n\n The Applied S
tatistics Workshop (Gov 3009) meets all academic year\, Wednesdays\, 12pm-
1:30pm\, in CGIS K354. This workshop is a forum for advanced graduate stud
ents\, faculty\, and visiting scholars to present and discuss methodologic
al or empirical work in progress in an interdisciplinary setting. The work
shop features a tour of Harvard's statistical innovations and applications
with weekly stops in different fields and disciplines and includes occasi
onal presentations by invited speakers.\n\n\n\n More information is availab
le at the Gov 3009 website: \;https://projects.iq.harvard.edu/applied.
stats.workshop-gov3009\n\n
DTSTART;TZID=America/New_York:20220126T120000
DTEND;TZID=America/New_York:20220126T133000
LAST-MODIFIED:20220126T151200Z
LOCATION:Virtual via Zoom
SUMMARY:Tracy Ke (Workshop in Applied Statistics)
URL;TYPE=URI:https://www.iq.harvard.edu/event/tracy-ke-workshop-applied-sta
tistics-0
END:VEVENT
END:VCALENDAR