首页 | 本学科首页   官方微博 | 高级检索  
     检索      


Fitting ERGMs on big networks
Institution:1. Department of Sociology, University of California, 3151 Social Science Plaza A, Irvine, CA 92697, USA;2. Information School, Mary Gates Hall, 370, University of Washington, Seattle, WA 98195, USA;3. Institute for Mathematical Behavioral Sciences, Department of Statistics, Bren Hall 2019, University of California, Irvine, CA 92697, USA;4. Department of Electrical Engineering and Computer Sciences, 2200 Engineering Hall, University of California, Irvine, CA 92697, USA;1. Indiana University, Departments of Sociology and Statistics, 752 Ballantine Hall, 1020 E. Kirkwood Avenue, Bloomington, IN 47405, USA;2. Post-Graduate Program in Amazonian Society and Culture, Federal University of Amazonas, Brazil;1. Graduate School of Simulation Studies, University of Hyogo, 7-1-28 Minatojima-minamimachi, Chuo-ku, Kobe, Hyogo 650-0047, Japan;2. Research Institute of Economy, Trade and Industry (RIETI), 1-3-1, Kasumigaseki Chiyoda-ku, 100-8901 Tokyo, Japan;3. RIKEN Advanced Institute for Computational Science, 7 Chome-1-26 Minatojima Minamimachi, Chuo, Kobe, Hyogo, Japan
Abstract:The exponential random graph model (ERGM) has become a valuable tool for modeling social networks. In particular, ERGM provides great flexibility to account for both covariates effects on tie formations and endogenous network formation processes. However, there are both conceptual and computational issues for fitting ERGMs on big networks. This paper describes a framework and a series of methods (based on existent algorithms) to address these issues. It also outlines the advantages and disadvantages of the methods and the conditions to which they are most applicable. Selected methods are illustrated through examples.
Keywords:Big networks  ERGMs  MCMLE  PMLE  Meta network analysis  Link tracing
本文献已被 ScienceDirect 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号