BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Continuous-time statistical models for network panel data - Tom Sn
 ijders (University of Groningen\; University of Oxford)
DTSTART:20161212T093000Z
DTEND:20161212T103000Z
UID:TALK69450@talks.cam.ac.uk
CONTACT:INI IT
DESCRIPTION:For the statistical analysis of network panel data even with a
 s little as 2 waves\, it is very fruitful to use models that assume a cont
 inuous-time Markov network process\, observed only at the moments of obser
 vation for the panel. This is analogous to the use of continuous-time mode
 ls for classical (non-network) panel data proposed by Bergstrom\, Singer\,
  and others. For network data such an approach was proposed already by Col
 eman in 1964. The advantage of this approach is that it provides a simple 
 way to represent the feedback that is inherent in network dynamics\, and t
 he model can be defined by just specifying the conditional probability of 
 a tie change\, given the current state of the network.<br><span><br>This a
 pproach is used in the Stochastic Actor-Oriented Model of Snijders (2001) 
 and in the Longitudinal Exponential Random Graph Model of Snijders & Koski
 nen (2013). The first of these is actor-oriented\, i.e.\, tie changes are 
 modelled as choices by actors\, which among their outgoing tie variables t
 o toggle\; the second is tie-oriented\, i.e.\, tie changes are modelled as
  toggles of single tie variables. Both are generalized linear models for t
 he (unobserved) continuous-time process\, with all the practical modelling
  flexibility of such models. Estimation for panel data is more involved\, 
 requiring a simulation approach. Estimators have been developed along seve
 ral lines\, including Method of Moments\, Generalized Method of Moments\, 
 Maximum Likelihood\, and Bayesian\, and are available in the R package RSi
 ena. This package is widely applied in empirical social network studies in
  the social sciences.</span>  <span>&nbsp\;&nbsp\;&nbsp\;&nbsp\;&nbsp\;&nb
 sp\;&nbsp\;&nbsp\;&nbsp\;&nbsp\;&nbsp\; <br>This presentation treats the b
 asic definition of the model and some of its extensions\, e.g.\, co-evolut
 ion of multivariate networks. Some open problems\, from a mathematical and
  from an applied perspective\, will be mentioned.</span>  &nbsp\;&nbsp\;&n
 bsp\;&nbsp\;&nbsp\;&nbsp\;&nbsp\;&nbsp\;&nbsp\;&nbsp\;&nbsp\;   <br><br><i
 >References</i>  <i>&nbsp\;</i>  <ul><li>Ruth M. Ripley\, Tom A.B. Snijder
 s\, Zs&oacute\;fia Boda\, Andr&aacute\;s V&ouml\;r&ouml\;s\, and Paulina P
 reciado\,  <span><span>2016. <i>Manual for SIENA version 4.0</i>. Oxford: 
 University of Oxford\, Department of Statistics\; Nuffield College. </span
 ><a target="_blank" rel="nofollow" href="http://www.stats.ox.ac.uk/siena/"
 >http://www.stats.ox.ac.uk/siena/</a></span>  &nbsp\;&nbsp\;</li><li><span
 >Tom A.B. Snijders\, 2001. The statistical evaluation of social network dy
 namics. <i>Sociological Methodology</i>\, 31\, 361-395.</span></li><li><sp
 an>Tom A.B. Snijders and Johan Koskinen\, 2013. "Longitudinal Models". Cha
 pter 11 (pp. 130-140) in D. Lusher\, J. Koskinen\, and G. Robins\, <i>Expo
 nential Random Graph Models for Social Networks</i>\,</span>  Cambridge: C
 ambridge University Press.  &nbsp\;</li><li>T<span>om A.B. Snijders\, Gerh
 ard G. van de Bunt\, G. G.\, and Christian E.G. Steglich\, 2010. <span>Int
 roduction to actor-based models for network dynamics. <i>Social Networks</
 i>\, 32\, 44&ndash\;60.</span></span>  &nbsp\;  </li></ul><br><br><br><br>
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR