Curved exponential family models for social networks

By David R. Hunter. Soc. Networks, 2007

498 citations recorded by the source corpus.

Subfields: Mathematical Physics, Statistical and Nonlinear Physics

View Paper: https://www.semanticscholar.org/paper/71bd9a5e520beff2f637d0e20aa7c51c7909b5f5

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Mathematical Physics

In Statistical and Nonlinear Physics

Citations in the corpus

Specification of Exponential-Family Random Graph Models: Terms and Computational Aspects. (2008, background): “See Hunter and Handcock (2006) for a general explanation of curved exponential-family models for networks and Hunter (2007) for more about these speciﬁc terms. gwdsp(alpha, fixed = FALSE) — Geometrically weighted dyadwise shared partner distribution: This term adds one network statistic to the…”
How Do They ‘End Up Together’? A Social Network Analysis of Self-Control, Homophily, and Adolescent Relationships (2011, methodology): “Triad closure is parameterized using the geometrically weighted edgewise shared partner distribution ( Hunter 2007 and Hunter and Handcock 2006):”
Complex Dependencies in the Alliance Network (2012, background): “Hunter (2007: 12–14) points out that we can relate the edgewise shared partners statistic to the k-triangle as follows: Tk(y) = Xn 2 i = k i k EPi(y) ð5Þ for 2 k n 2.”
Advances in exponential random graph (p*) models applied to a large social network (2007, methodology): “For more information on the use of AIC for ERGM model fit, see Hunter et al. (2005). 3. Goodness of fit plotting for higher order statistics. This approach is described in detail in Hunter et al. (2005). The logic entails generating new networks according to the probability distribution implied by t”
A statnet Tutorial. (2008, methodology): “This is the GWESP (geometrically weighted edgewise shared partner) statistic; For more information on it, and the equivalent “alternating k-triangle” statistic, see Snijders et al. (2006); Robins, Snijders, Wang, Handcock, and Pattison (2007b) or Hunter (2007).”
Information Exchange in Policy Networks (2012, methodology): “The geometrically weighted edge-wise shared partner distribution (GWESP) and the geometrically weighted dyad-wise shared partner distribution (GWDSP) can be interpreted together (Hunter 2007).”
Birds of a feather, or friend of a friend? using exponential random graph models to investigate adolescent social networks* (2009, methodology): “To capture this phenomenon, Hunter (2007) and Hunter and Handcock (2006) described a statistic called the geometrically weighted edgewise shared partner distribution (GWESP), a reparameterization of a statistic of Snijders et al. (2006).”
ergm: A Package to Fit, Simulate and Diagnose Exponential-Family Models for Networks. (2008, background): “Further details on such models may be found in Hunter et al. (2008), where they are fit to real data similar to faux.”
Recent developments in exponential random graph (p*) models for social networks (2007, methodology): “As the alternative weighted degree parameterization does not include the number of edges (Hunter, 2006), this might be a reason to prefer it.”
Private analysis of graph structure (2011, background): “Because the amount of distortion increases as more statistics are released (see Lemma 2.1), these techniques are not appropriate for releasing a large number of statistics simultaneously (such as the edgewise shared partner distribution used by [6]).”
Goodness of Fit of Social Network Models (2008, unknown): “Hunter (2007) discussed this issue at length.”
The analysis of social networks (2008, methodology): “where EPk y ð Þ 1⁄4 P i\j yijI spij 1⁄4 k is the number of pairs of linked actors who share k partners, spij 1⁄4 P k yikyjk is the number of partners shared by actors i and j (Goodreau 2007; Hunter 2007) and parameter q controls the rate at which the weights assigned to configurations having k share”