| Member Profile : Mark Handcock |
|
 | Contact Information | Address: -Map Me-
Mark Handcock
University of California, Statistics
Department of Statistics
8125 Mathematical Sciences Building
Los Angeles, CA, United States 90095-1554
Phone : +1-310-817-6778
Fax : +1-206-457-1953
E-mail : handcock@ucla.edu
Website : http://www.stat.ucla.edu/~handcock
|
| Bibliographic Information |
|
| | | Software & Data | | Active Calendar Listings |
| statnet: software tools for the representation, visualization, analysis and simulation of social network data. | (Software) |
statnet is a suite of software packages for network analysis that implement recent advances in the statistical modeling of networks. The analytic framework is based on Exponential family Random Graph Models (ergm). statnet provides a comprehensive framework for ergm-based network modeling, including tools for model estimation, model evaluation, model-based network simulation, and network visualization. This broad functionality is powered by a central Markov chain Monte Carlo (MCMC) algorithm.
statnet has a different purpose than the excellent packages UCINET or Pajek; the focus is on statistical modeling of network data. The statistical modeling capabilities of statnet include ERGMs, latent space and latent cluster models. The packages are written in a combination of (the open-source statistical language) R and (ANSI standard) C, and are called from the R command line. And because it runs in the R package (www.r-project.org), you also have access to the full functionality of R, including the packages \"network\" and \"sna\" written by Carter Butts. statnet has a command line interface, not a GUI, with a syntax that resembles R. |
|
|
|
| | | Network Graduate Programs | | Network Courses |
|
|
|
| | | Jobs Posted | | Sunbelt Submissions |
|
| Sunbelt XXIX - March 10 to March 15, 2009 - Bahia Hotel | | Abstract : Latent Space Cluster Models with ERGM components |
| Latent space models for social networks postulate the existence of a latent “social space”, where the probability of a relation between entities depends on their relative positions within this space. The latent cluster model for social networks models groups of entities as model-based clusters on the latent space, and Bayesian fitting of this model via MCMC allows the latent space position estimation to borrow strength from the cluster process. We refine and extend this model in a number of ways, including modeling inhomogeneity through actor-level random effects, adding ERGM structure and generalizing the model to non-binary data. We demonstrate applications of this family of models to several datasets. An open-source software package, latentnet, is available that implements this model class. Some of this is also joint work with Peter D. Hoff and Adrian E. Raftery. |
| Sunbelt XXX - June 29 to July 04, 2010 - Riva del Garda Fierecongressi | | Abstract : Estimating Hidden Population Size using Respondent-Driven Sampling Data |
Respondent-Driven Sampling (RDS, introduced by Heckathorn 1997) is an approach to sampling design and inference in hard-to-reach populations. These populations are characterized by the difficulty in sampling from them using standard probability methods. Typically, a sampling frame for the target population is not available, and its members are rare or stigmatized in the larger population so that it is prohibitively expensive to contact them through the available frames. Examples of such populations in a behavioral and social setting include injection drug users, men who have sex with men, and female sex workers.
Most analysis of RDS data has focused on estimating aggregate characteristics of the target population, such as disease prevalence. However, RDS is often conducted in settings where the population size is unknown and of great independent interest. In this paper, we present an approach to estimating the size of a target population based on the data collected through RDS. This strategy uses the successive sampling approximation to RDS introduced in Gile (2009) to leverage the information in the ordered sequence of observed personal network sizes. We develop inference within the Bayesian framework that allows prior knowledge of the population size to be incorporated. We show via a simulation study and application to real data that these approaches also improve estimation of aggregate characteristics based on RDS data.
This is joint work with Krista J. Gile (Nuffield College, Oxford) and Corinne M. Mar (University of Washington). |
| Sunbelt XXVII - May 01 to May 06, 2007 - Corfu Island | | Workshop : 4b. Mark Handcock, Dave Hunter, Carter Butts, Steve Goodreau: A Practical introduction to statnet: an R-based environment for statistical analysis and simulation of social networks (Wed, May 2, 9:00 to noon) |
| 4b. Mark Handcock, Dave Hunter, Carter Butts, Steve Goodreau: A Practical introduction to statnet: an R-based environment for statistical analysis and simulation of social networks (Wed, May 2, 9:00 to noon) |
| Sunbelt XXXI - February 08 to February 13, 2011 - Trade Winds Beach Resort
http://www.tradewindsresort.com/
St. Pete Beach | | Workshop : Introduction to Exponential-family Random Graph (ERG or p*) modeling with statnet |
This workshop is a tutorial on exponential random graph models for social networks, emphasizing a hands-on approach to fitting these models to empirical data. This workshop will provide a hands-on tutorial to statnet, a statistical package for the visualization, analysis and simulation of social network data. The focus in on modeling with the class of exponential random graph (ERG) models. These models recognize the complex dependencies within relational data structures, and provide a very flexible framework for representing them. statnet has a coherent and flexible user interface and can
handle relatively large networks (~3,000 is the largest network we have estimated models for), and it has very efficient algorithms for data manipulation and analysis. The package provides tools for both model estimation and model-based network simulation, with visualization, tools for inference and validation, and goodness of fit diagnostics. The package is written for the R statistical computing environment, so it runs on any computing platform that supports R (Windows, Unix/Linux, Mac), it is freely available through the Comprehensive R Archive Network (CRAN), and it has a seamless interface to sna (an R package for traditional network analysis written by Carter Butts). Attendees are expected to have had some prior exposure to R, but extensive experience is not assumed. Familiarity with basic descriptive network concepts and basic statistical methods for network analysis within the R/statnet platform is recommended. |
| Sunbelt XXXII - March 12 to March 18, 2012 - Crowne Plaza Hotel
https://resweb.passkey.com/go/INSNASunbelt
Redondo Beach | | Workshop : Extending ERGM Functionality within statnet: Building Custom User Terms* |
Exponential-family random graph models (ERGM) represent a powerful and flexible class of models for the statistical analysis of networks. statnet is a suite of software packages that implement these models. This workshop session details how the capabilities for ERGM modeling within statnet can be expanded and customized by programming additional network statistics that may be included in ERGMs. We describe a template R package called \"ergm.userterms\" that can be modified for this purpose. It is designed to make this process as straightforward as possible. We also explain some of the internal workings of statnet that will help users develop their own network analysis capabilities. The workshop will work through examples in a tutorial paper and demonstrate each step in the practical process of extending ERGM.
statnet is a collection of packages for the R statistical computing system that supports the representation, manipulation, visualization, modeling, simulation, and analysis of relational data. statnet packages are contributed by a team of volunteer developers, and are made freely available under the GNU Public License. These packages are written for the R statistical computing environment, and can be used with any computing platform that supports R (including Windows, Linux, and Mac). statnet packages can be used to handle a wide range of simulation and analysis tasks, including support for large networks, statistical network models, network dynamics, and missing data.
|
|
|
| |
|
