Stochastic a posteriori blockmodels: Construction and assessment

Stanley Wasserman, Carolyn Anderson

Research output: Contribution to journalArticle

Abstract

In 1983, Holland, Laskey, and Leinhardt, using the ideas of Holland and Leinhardt, and Fienberg and Wasserman, introduced the notion of a stochastic blockmodel. The mathematics for stochastic a priori blockmodels, in which exogenous actor attribute data are used to partition actors independently of any statistical analysis of the available relational data, have been refined by several researchers and the resulting models used by many. Attempts to simultaneously partition actors and to perform relational data analyses using statistical methods that yield stochastic a posteriori blockmodels are still quite rare. In this paper, we discuss some old suggestions for producing such posterior blockmodels, and comment on other new suggestions based on multiple comparisons of model parameters, log-linear models for ordinal categorical data, and correspondence analysis. We also review measures for goodness-of-fit of a blockmodel, and we describe a natural approach to this problem using likelihood-ratio statistics generated from a popular model for relational data.

Original languageEnglish (US)
Pages (from-to)1-36
Number of pages36
JournalSocial Networks
Volume9
Issue number1
DOIs
StatePublished - Mar 1987

Fingerprint

Netherlands
Statistical Data Interpretation
Mathematics
Linear Models
Research Personnel
correspondence analysis
linear model
statistical method
statistical analysis
data analysis
statistics
mathematics

ASJC Scopus subject areas

  • Anthropology
  • Sociology and Political Science
  • Social Sciences(all)
  • Psychology(all)

Cite this

Stochastic a posteriori blockmodels : Construction and assessment. / Wasserman, Stanley; Anderson, Carolyn.

In: Social Networks, Vol. 9, No. 1, 03.1987, p. 1-36.

Research output: Contribution to journalArticle

@article{e9d704d23c4a4aa39225d862f4ed831d,
title = "Stochastic a posteriori blockmodels: Construction and assessment",
abstract = "In 1983, Holland, Laskey, and Leinhardt, using the ideas of Holland and Leinhardt, and Fienberg and Wasserman, introduced the notion of a stochastic blockmodel. The mathematics for stochastic a priori blockmodels, in which exogenous actor attribute data are used to partition actors independently of any statistical analysis of the available relational data, have been refined by several researchers and the resulting models used by many. Attempts to simultaneously partition actors and to perform relational data analyses using statistical methods that yield stochastic a posteriori blockmodels are still quite rare. In this paper, we discuss some old suggestions for producing such posterior blockmodels, and comment on other new suggestions based on multiple comparisons of model parameters, log-linear models for ordinal categorical data, and correspondence analysis. We also review measures for goodness-of-fit of a blockmodel, and we describe a natural approach to this problem using likelihood-ratio statistics generated from a popular model for relational data.",
author = "Stanley Wasserman and Carolyn Anderson",
year = "1987",
month = "3",
doi = "10.1016/0378-8733(87)90015-3",
language = "English (US)",
volume = "9",
pages = "1--36",
journal = "Social Networks",
issn = "0378-8733",
publisher = "Elsevier BV",
number = "1",

}

TY - JOUR

T1 - Stochastic a posteriori blockmodels

T2 - Construction and assessment

AU - Wasserman, Stanley

AU - Anderson, Carolyn

PY - 1987/3

Y1 - 1987/3

N2 - In 1983, Holland, Laskey, and Leinhardt, using the ideas of Holland and Leinhardt, and Fienberg and Wasserman, introduced the notion of a stochastic blockmodel. The mathematics for stochastic a priori blockmodels, in which exogenous actor attribute data are used to partition actors independently of any statistical analysis of the available relational data, have been refined by several researchers and the resulting models used by many. Attempts to simultaneously partition actors and to perform relational data analyses using statistical methods that yield stochastic a posteriori blockmodels are still quite rare. In this paper, we discuss some old suggestions for producing such posterior blockmodels, and comment on other new suggestions based on multiple comparisons of model parameters, log-linear models for ordinal categorical data, and correspondence analysis. We also review measures for goodness-of-fit of a blockmodel, and we describe a natural approach to this problem using likelihood-ratio statistics generated from a popular model for relational data.

AB - In 1983, Holland, Laskey, and Leinhardt, using the ideas of Holland and Leinhardt, and Fienberg and Wasserman, introduced the notion of a stochastic blockmodel. The mathematics for stochastic a priori blockmodels, in which exogenous actor attribute data are used to partition actors independently of any statistical analysis of the available relational data, have been refined by several researchers and the resulting models used by many. Attempts to simultaneously partition actors and to perform relational data analyses using statistical methods that yield stochastic a posteriori blockmodels are still quite rare. In this paper, we discuss some old suggestions for producing such posterior blockmodels, and comment on other new suggestions based on multiple comparisons of model parameters, log-linear models for ordinal categorical data, and correspondence analysis. We also review measures for goodness-of-fit of a blockmodel, and we describe a natural approach to this problem using likelihood-ratio statistics generated from a popular model for relational data.

UR - http://www.scopus.com/inward/record.url?scp=37249037751&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=37249037751&partnerID=8YFLogxK

U2 - 10.1016/0378-8733(87)90015-3

DO - 10.1016/0378-8733(87)90015-3

M3 - Article

AN - SCOPUS:37249037751

VL - 9

SP - 1

EP - 36

JO - Social Networks

JF - Social Networks

SN - 0378-8733

IS - 1

ER -