The Problem of Scaling in Exponential Random Graph Models

Autor/in	Duxbury, Scott W.
Titel	The Problem of Scaling in Exponential Random Graph Models
Quelle	In: Sociological Methods & Research, 52 (2023) 2, S.764-802 (39 Seiten) PDF als Volltext Verfügbarkeit
Zusatzinformation	ORCID (Duxbury, Scott W.)
Sprache	englisch
Dokumenttyp	gedruckt; online; Zeitschriftenaufsatz
ISSN	0049-1241
DOI	10.1177/0049124120986178
Schlagwörter	Graphs; Scaling; Research Problems; Models; Predictor Variables; Correlation; Simulation; Comparative Analysis; Effect Size; Social Networks; Network Analysis; Probability; Statistical Inference; Algorithms; High School Students; Friendship; Adolescents; Longitudinal Studies; Health; Gender Differences; Instructional Program Divisions; National Longitudinal Study of Adolescent Health + Suchen Sie Ihr Suchwort? Grafische Darstellung; Scale construction; Skalenkonstruktion; Forschungskritik; Analogiemodell; Prädiktor; Korrelation; Simulation program; Simulationsprogramm; Social network; Soziales Netzwerk; Netzplantechnik; Wahrscheinlichkeitsrechnung; Wahrscheinlichkeitstheorie; Inferential statistics; Schließende Statistik; Algorithm; Algorithmus; High school; High schools; Student; Students; Oberschule; Schüler; Schülerin; Studentin; Freundschaft; Adolescent; Adolescence; Adoleszenz; Jugend; Jugendalter; Jugendlicher; Longitudinal study; Longitudinal method; Longitudinal methods; Längsschnittuntersuchung; Gesundheit; Geschlechterkonflikt
Abstract	This study shows that residual variation can cause problems related to scaling in exponential random graph models (ERGM). Residual variation is likely to exist when there are unmeasured variables in a model--even those uncorrelated with other predictors--or when the logistic form of the model is inappropriate. As a consequence, coefficients cannot be interpreted as effect sizes or compared between models and homophily coefficients, as well as other interaction coefficients, cannot be interpreted as substantive effects in most ERGM applications. We conduct a series of simulations considering the substantive impact of these issues, revealing that realistic levels of residual variation can have large consequences for ERGM inference. A flexible methodological framework is introduced to overcome these problems. Formal tests of mediation and moderation are also proposed. These methods are applied to revisit the relationship between selective mixing and triadic closure in a large AddHealth school friendship network. Extensions to other classes of statistical work models are discussed. (As Provided).
Anmerkungen	SAGE Publications. 2455 Teller Road, Thousand Oaks, CA 91320. Tel: 800-818-7243; Tel: 805-499-9774; Fax: 800-583-2665; e-mail: journals@sagepub.com; Web site: https://sagepub.com
Erfasst von	ERIC (Education Resources Information Center), Washington, DC
Update	2024/1/01