BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Tracking people over time in 19th century Canada: Challenges\, Bia
 s and Results - Luiza Antonie (University of Guelph)
DTSTART:20160913T110000Z
DTEND:20160913T113000Z
UID:TALK67329@talks.cam.ac.uk
CONTACT:INI IT
DESCRIPTION:<span>Co-author: Kris Inwood (University of Guelph) <br></span
 > <span><br>Linking multiple databases to create longitudinal data is an i
 mportant  research problem with multiple applications. Longitudinal data a
 llows analysts  to perform studies that would be unfeasible otherwise. In 
 this talk\, I discuss a  system we designed to link historical census data
 bases in order to create  longitudinal data that allow tracking people ove
 r time. Data imprecision in  historical census data and the lack of unique
  personal identifiers make this  task a challenging one. We design and emp
 loy a record linkage system that  incorporates a supervised learning modul
 e for classifying pairs of records as  matches and non-matches. In additio
 n\, we disambiguate ambiguous links by taking  into account the family con
 text. We report results on linking four Canadian  census collections\, fro
 m 1871 to 1901\, and identify and discuss the impact on  precision and bia
 s when family context is employed. We show that our system  performs large
  scale linkage producing high quality links and generat ing  sufficient lo
 ngitudinal data to allow meaningful social science studies.&nbsp\;</span>
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR