A Comparison of Peer Influence Estimates from SIENA Stochastic Actor–based Models and from Conventional Regression Approaches

Daniel T. Ragan, D. Wayne Osgood, Nayan G. Ramirez, James Moody, Scott David Gest

Research output: Contribution to journalArticle

Abstract

The current study compares estimates of peer influence from an analytic approach that explicitly address network processes with those from traditional approaches that do not. Using longitudinal network data from the PROmoting School–community–university Partnerships to Enhance Resilience peers project, we obtain estimates of social influence on multiple outcomes from both conventional linear modeling approaches and the stochastic actor–based modeling approach of the simulation investigation for empirical network analysis (SIENA) software. Our findings indicate that peer influence estimates from SIENA are not more conservative relative to other methods, that each method is subject to omitted variable bias from stable individual differences, and that imprecision among each method could lead to erroneous conclusions in samples that lack sufficient power. Together, these results underscore the difficulty in obtaining estimates of peer influence from observational data, and they give no indication that results from conventional methods tend to be biased toward overestimating peer influence, relative to SIENA.

Original languageEnglish (US)
JournalSociological Methods and Research
DOIs
StatePublished - Jan 1 2019

Fingerprint

network analysis
regression
simulation
data network
resilience
indication
lack
trend

All Science Journal Classification (ASJC) codes

  • Social Sciences (miscellaneous)
  • Sociology and Political Science

Cite this

Ragan, Daniel T. ; Osgood, D. Wayne ; Ramirez, Nayan G. ; Moody, James ; Gest, Scott David. / A Comparison of Peer Influence Estimates from SIENA Stochastic Actor–based Models and from Conventional Regression Approaches. In: Sociological Methods and Research. 2019.
@article{38989f3ad7084f6a83eca1317f35004b,
title = "A Comparison of Peer Influence Estimates from SIENA Stochastic Actor–based Models and from Conventional Regression Approaches",
abstract = "The current study compares estimates of peer influence from an analytic approach that explicitly address network processes with those from traditional approaches that do not. Using longitudinal network data from the PROmoting School–community–university Partnerships to Enhance Resilience peers project, we obtain estimates of social influence on multiple outcomes from both conventional linear modeling approaches and the stochastic actor–based modeling approach of the simulation investigation for empirical network analysis (SIENA) software. Our findings indicate that peer influence estimates from SIENA are not more conservative relative to other methods, that each method is subject to omitted variable bias from stable individual differences, and that imprecision among each method could lead to erroneous conclusions in samples that lack sufficient power. Together, these results underscore the difficulty in obtaining estimates of peer influence from observational data, and they give no indication that results from conventional methods tend to be biased toward overestimating peer influence, relative to SIENA.",
author = "Ragan, {Daniel T.} and Osgood, {D. Wayne} and Ramirez, {Nayan G.} and James Moody and Gest, {Scott David}",
year = "2019",
month = "1",
day = "1",
doi = "10.1177/0049124119852369",
language = "English (US)",
journal = "Sociological Methods and Research",
issn = "0049-1241",
publisher = "SAGE Publications Inc.",

}

A Comparison of Peer Influence Estimates from SIENA Stochastic Actor–based Models and from Conventional Regression Approaches. / Ragan, Daniel T.; Osgood, D. Wayne; Ramirez, Nayan G.; Moody, James; Gest, Scott David.

In: Sociological Methods and Research, 01.01.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A Comparison of Peer Influence Estimates from SIENA Stochastic Actor–based Models and from Conventional Regression Approaches

AU - Ragan, Daniel T.

AU - Osgood, D. Wayne

AU - Ramirez, Nayan G.

AU - Moody, James

AU - Gest, Scott David

PY - 2019/1/1

Y1 - 2019/1/1

N2 - The current study compares estimates of peer influence from an analytic approach that explicitly address network processes with those from traditional approaches that do not. Using longitudinal network data from the PROmoting School–community–university Partnerships to Enhance Resilience peers project, we obtain estimates of social influence on multiple outcomes from both conventional linear modeling approaches and the stochastic actor–based modeling approach of the simulation investigation for empirical network analysis (SIENA) software. Our findings indicate that peer influence estimates from SIENA are not more conservative relative to other methods, that each method is subject to omitted variable bias from stable individual differences, and that imprecision among each method could lead to erroneous conclusions in samples that lack sufficient power. Together, these results underscore the difficulty in obtaining estimates of peer influence from observational data, and they give no indication that results from conventional methods tend to be biased toward overestimating peer influence, relative to SIENA.

AB - The current study compares estimates of peer influence from an analytic approach that explicitly address network processes with those from traditional approaches that do not. Using longitudinal network data from the PROmoting School–community–university Partnerships to Enhance Resilience peers project, we obtain estimates of social influence on multiple outcomes from both conventional linear modeling approaches and the stochastic actor–based modeling approach of the simulation investigation for empirical network analysis (SIENA) software. Our findings indicate that peer influence estimates from SIENA are not more conservative relative to other methods, that each method is subject to omitted variable bias from stable individual differences, and that imprecision among each method could lead to erroneous conclusions in samples that lack sufficient power. Together, these results underscore the difficulty in obtaining estimates of peer influence from observational data, and they give no indication that results from conventional methods tend to be biased toward overestimating peer influence, relative to SIENA.

UR - http://www.scopus.com/inward/record.url?scp=85066879748&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85066879748&partnerID=8YFLogxK

U2 - 10.1177/0049124119852369

DO - 10.1177/0049124119852369

M3 - Article

AN - SCOPUS:85066879748

JO - Sociological Methods and Research

JF - Sociological Methods and Research

SN - 0049-1241

ER -