BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Modeling networks when data is missing or sampled - Handcock\, M (
 UCLA)
DTSTART:20100624T084500Z
DTEND:20100624T093000Z
UID:TALK25329@talks.cam.ac.uk
CONTACT:Mustapha Amrani
DESCRIPTION:Network models are widely used to represent relational informa
 tion among interacting units and the structural implications of these rela
 tions. Recently\, social network studies have focused a great deal of atte
 ntion on random graph models of networks whose nodes represent individual 
 social actors and whose edges represent a specified relationship between t
 he actors.\n\nMost inference for social network models assumes that the pr
 esence or absence of all possible links is observed\, that the information
  is completely reliable\, and that there are no measurement (e.g. recordin
 g) errors. This is clearly not true in practice\, as much network data is 
 collected though sample surveys. In addition even if a census of a populat
 ion is attempted\, individuals and links between individuals are missed (i
 .e.\, do not appear in the recorded data).\n\nIn this paper we develop the
  conceptual and computational theory for inference based on sampled networ
 k information. We first review forms of network sampling designs used in p
 ractice. We consider inference from the likelihood framework\, and develop
  a typology of network data that reflects their treatment within this fram
 e. We then develop inference for social network models based on informatio
 n from adaptive network designs.\n\nWe motivate and illustrate these ideas
  by analyzing the effect of link-tracing sampling designs on a collaborati
 on network.\n\nThis is joint work with Krista J. Gile\, Nuffield College\,
  Oxford.\n
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR