Bayesian SNA (@BayesianSNA) header
Bayesian SNA (@BayesianSNA) profile picture

Bayesian SNA

@BayesianSNA

Tweets about Statistical Network Analysis from @albertocaimo

 Dublin 🇮🇪
acaimo.github.io/Bergm
Joined May 2013
  • Tweets567
  • Following405
  • Followers704
9Media
Photo by Bayesian SNA (@BayesianSNA)Photo by Bayesian SNA (@BayesianSNA)Photo by Bayesian SNA (@BayesianSNA)Photo by Bayesian SNA (@BayesianSNA)Photo by Bayesian SNA (@BayesianSNA)Photo by Bayesian SNA (@BayesianSNA)Photo by Bayesian SNA (@BayesianSNA)Photo by Bayesian SNA (@BayesianSNA)Photo by Bayesian SNA (@BayesianSNA)
'#ergm' 4.2 is out, featuring a new framework for getting help and searching for ERGM statistics, constraints, and reference distributions (including those from other packages), as well as improvements to model specification and computation. #sna @SocNetAnalysts #networkscience
19
48
L-2 Regularized maximum likelihood for β-model in large and sparse networks arxiv.org/abs/2110.11856
L-2 Regularized maximum likelihood for $β$-model in large and...

L-2 Regularized maximum likelihood for $β$-model in large and...

The $β$-model is a powerful tool for modeling large and sparse networks driven by degree heterogeneity, where many network models become infeasible due to computational challenge and network...

arxiv.org
Highly Scalable Maximum Likelihood and Conjugate Bayesian Inference for ERGMs on Graph Sets with Equivalent Vertices arxiv.org/abs/2110.13527
#Networks2021 Workshop on Bayesian Exponential Random Graph Models with Bergm - June 21, 09:00-12:00 EDT - Don't miss it out! Only a few places left!
3
3
Random graphs with node and block effects: models, goodness-of-fit tests, and applications to biological networks arxiv.org/abs/2104.03167
2
Bayesian exponential random graph models for populations of networks arxiv.org/abs/2104.05110
Bayesian exponential random graph models for populations of networks

Bayesian exponential random graph models for populations of networks

The collection of data on populations of networks is becoming increasingly common, where each data point can be seen as a realisation of a network-valued random variable. A canonical example is...

arxiv.org
5
A Stein Goodness of fit Test for Exponential Random Graph Models arxiv.org/abs/2103.00580
A Stein Goodness of fit Test for Exponential Random Graph Models

A Stein Goodness of fit Test for Exponential Random Graph Models

We propose and analyse a novel nonparametric goodness of fit testing procedure for exchangeable exponential random graph models (ERGMs) when a single network realisation is observed. The test...

arxiv.org
1
A Latent Space Model for Multilayer Network Data arxiv.org/abs/2102.09560
1
Generative Dynamics of Supreme Court Citations: Analysis with a New Statistical Network Model arxiv.org/abs/2101.07197
Bayesian SNA retweeted
Thomas Wiecki (@twiecki) profile picture
Thomas Wiecki@twiecki18 Jan 2021
Primer on Bayesian statistics published in Nature. But it's not only science that is recognizing Bayesian modeling as the powerful inference method that it is, I see the same happening in business. Exciting times! nature.com/articles/s43586-0…
Image from Thomas Wiecki (@twiecki)
Image from Thomas Wiecki (@twiecki)
Image from Thomas Wiecki (@twiecki)
5
215
18
895
In 2017, we (see below) set out to answer some questions and clear up some common misconceptions about history, inference, and applicability of ERGMs. The result is, at last, officially out in Statistical Science: dx.doi.org/10.1214/19-STS743 . #networkscience @SocNetAnalysts
Statist. Sci. Volume 35, Number 4 (2020), 627-662. Exponential-Family Models of Random Graphs: Inference in Finite, Super and Infinite Population Scenarios Michael Schweinberger, Pavel N. Krivitsky, Carter T. Butts, and Jonathan R. Stewart Truncated abstract follows.

ALT Statist. Sci. Volume 35, Number 4 (2020), 627-662. Exponential-Family Models of Random Graphs: Inference in Finite, Super and Infinite Population Scenarios Michael Schweinberger, Pavel N. Krivitsky, Carter T. Butts, and Jonathan R. Stewart Truncated abstract follows.

1
14
4
41
Bayesian SNA retweeted
Nial Friel (@NialFriel) profile picture
Nial Friel@NialFriel17 Nov 2020
The latest version of Bergm is now on CRAN. With huge thanks to @albertocaimo for leading this project. Highlight: fast estimation of the evidence (marginal likelihood) cran.r-project.org/web/packa…
Bergm: Bayesian Exponential Random Graph Models

Bergm: Bayesian Exponential Random Graph Models

Bayesian analysis for exponential random graph models using advanced computational algorithms: the approximate exchange algorithm with adaptive direction sampling (optionally adaptive, delayed-acce...

cran.r-project.org
1
4
15
Modeling partitions of individuals arxiv.org/abs/2009.13974
Modeling partitions of individuals

Modeling partitions of individuals

Despite the central role of self-assembled groups in animal and human societies, statistical tools to explain their composition are limited. We introduce a statistical framework for...

arxiv.org
Improving ERGM Starting Values Using Simulated Annealing arxiv.org/abs/2009.01202
Improving ERGM Starting Values Using Simulated Annealing

Improving ERGM Starting Values Using Simulated Annealing

Much of the theory of estimation for exponential family models, which include exponential-family random graph models (ERGMs) as a special case, is well-established and maximum likelihood estimates...

arxiv.org
2
Introducing "Robust Bayesian inference of network structure from unreliable data," a (hopefully!) pedagogical introduction to inferring networks from noisy data -- with code. w/ George T. Cantwell and MEJ Newman 📃Preprint: arxiv.org/abs/2008.03334
Image from Jean-Gabriel Young (@_jgyou)
5
85
5
254
🔥Hot off the press🔥New article in #SocialNetworks with @albertocaimo and @PaoloCampanaCAM introducing a latent space model for interdependent ego-networks applied to human smuggling data 🚔 #openaccess #sna #RStats sciencedirect.com/science/ar…
8
12
"Italian sociologists: a community of disconnected groups" Together with @vtraag @albertocaimo @squazzoni , we explored the (dis)connectivity of Italian sociological community through a quantitative analysis, a #Thread Read the full-text online here: rdcu.be/b4TA0
Image from Aliakbar Akbaritabar, @akbaritabar.bsky.social (@Akbaritabar)
2
17
2
42
Study on #coauthorship #networks of #sociologists in #Italy by @Akbaritabar @vtraag @albertocaimo revealing hidden patterns and key colleagues. Relevant for @newsAIS @sisecit link.springer.com/article/10…
1
7
12
Kernel-based Approximate Bayesian Inference for Exponential Family Random Graph Models arxiv.org/abs/2004.08064
Kernel-based Approximate Bayesian Inference for Exponential Family...

Kernel-based Approximate Bayesian Inference for Exponential Family...

Bayesian inference for exponential family random graph models (ERGMs) is a doubly-intractable problem because of the intractability of both the likelihood and posterior normalizing factor....

arxiv.org
3
Bayesian Computation with Intractable Likelihoods arxiv.org/abs/2004.04620
Bayesian Computation with Intractable Likelihoods

Bayesian Computation with Intractable Likelihoods

This article surveys computational methods for posterior inference with intractable likelihoods, that is where the likelihood function is unavailable in closed form, or where evaluation of the...

arxiv.org
2
Load more