BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//ox.ac.uk//NONSGML oxford.event//EN
X-WR-TIMEZONE:Europe/London
BEGIN:VTIMEZONE
TZID:Europe/London
X-LIC-LOCATION:Europe/London
BEGIN:DAYLIGHT
DTSTART:19700329T010000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:BST
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:19701025T020000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:GMT
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
SUMMARY:Metrics and Models: Lai Wei
DTSTART;TZID=Europe/London:20260528T140000
DTEND;TZID=Europe/London:20260528T150000
DTSTAMP:20260526T105338Z
UID:8d8f7f09-af56-f111-a825-6045bd12f634
CREATED:20260523T135521Z
DESCRIPTION:Talk Title: Using AI Predictions to Augment Rather Than Replac
 ing Surveys\n\nAbstract: Precision in household surveys is increasingly co
 stly to buy with additional interviews\, yet many statistics that inform h
 ealth\, labor\, and social policy still require narrow confidence interval
 s to be useful. Our question is whether we can obtain some of that precisi
 on “for free” by exploiting information already available at populatio
 n scale. Prediction‑Powered Inference (PPI) provides principled framewor
 k to achieve this: obtain a predictor using either existing data or extern
 al information (LLM)\, predict it on a very large auxiliary file\, and the
 n calibrate the prediction‑based estimate with a gold‑standard correct
 ion computed on the survey labels. As a demonstration\, we apply PPI to Na
 tional Health Interview Survey (NHIS) and General Social Survey (GSS)\, ha
 rmonized with the American Community Survey (ACS)\, covering a broad range
  of outcomes that include political opinion\, socio-economic conditions\, 
 and health conditions and behaviours. We show that the combination of auxi
 liary population-level information and external prediction algorithms can 
 increase the effective sample size of survey data.\n\nBio: Lai Wei is an A
 ssistant Professor of Sociology and HKU-100 Scholar at the University of H
 ong Kong. Prior to his post he obtained his PhD in sociology from Princeto
 n University. He studies social stratification and quantitative methodolog
 y. His past works have been published in Sociological Methods & Research\,
  Journal of Royal Statistical Society\, Journal of Health and Social Behav
 iour\, among other outlets.
LAST-MODIFIED:20260523T140057Z
END:VEVENT
END:VCALENDAR