DYNAMIC NETWORKS AND BEHAVIOR: SEPARATING SELECTION FROM INFLUENCE: separating selection from influence

By Christian E. G. Steglich, Tom A. B. Snijders, Michael Pearson. 2010

882 citations recorded by the source corpus.

A recurrent problem in the analysis of behavioral dynamics, given a simultaneously evolving social network, is the difficulty of separating the effects of partner selection from the effects of social influence. Because misattribution of selection effects to social influence, or vice versa, suggests wrong conclusions about the social mechanisms underlying the observed dynamics, special diligence in data analysis is advisable. While a dependable and validmethod would benefit several research areas, according to the best of our knowledge, it has been lacking in the extant literature. In this paper, we present a recently developed family of statistical models that enables researchers to separate the two effects in a statistically adequate manner. To illustrate our method, we investigate the roles of homophile selection and peer influence mechanisms in the joint dynamics of friendship formation and substance use among adolescents. Making use of a three-wave panel measured in the years 1995–1997 at a school in ...

Subfields: Experimental and Cognitive Psychology, Statistical and Nonlinear Physics

View Paper: https://www.semanticscholar.org/paper/08cc64a6ede4b844ee2bd7f49695ecc6f638a3c7

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Experimental and Cognitive Psychology

In Statistical and Nonlinear Physics

Citations in the corpus

The dynamics of interfirm networks along the industry life cycle: The case of the global video game industry, 1987–2007 (2013, methodology): “Correlation between observations can lead to unreliable estimations of parameter coefficients and SEs (Steglich et al., 2010).”
Mapping symbolic (anti-) consumption (2009, background): “At the same time it may have been friendship with a smoker that made him or her start smoking in the first place (influence)” (Steglich et al., 2004, p. 2).”
Models of Social Influence: Towards the Next Frontiers (2017, background): “Stochastic actor orientedmodels developed by Snijders and others (Snijders 2011; Snijders & Steglich 2015; Steglich et al. 2010) combine agent-based modeling of such longitudinal data with statistical estimation and testing of themechanisms assumed by themodeler.”
Distinguishing between Personal Preferences and Social Influence in Online Activity Feeds (2016, methodology): “, [45, 34, 15]) or strong knowledge of latent variables that indicate homophily (e.”
Social contagion theory: examining dynamic social networks and human behavior (2011, background): “We also note that there are certainly other valuable ways of analyzing such data, albeit with other strengths and limitations (such as constraints on network size and on parameter interpretation), including the so-called “actor-oriented” models [71, 72]; see [73, 74] for illustrative applications.”
Statistical Models for Social Networks (2011, background): “This distinction is explained at length by Sterba (2009), who also shows how the discussion about these traditions goes back to debates in the 1920s and 1930s between two of the founding fathers of statistics, Ronald Fisher and Jerzy Neyman, of whom the former championed model-based and the latter d”
Social Networks and Causal Inference (2013, methodology): “We will also describe an alternative approach based on a stochastic actor-oriented model (Snijders 2001, 2005; Steglich et al. 2010) that more explicitly models the selection of ties.”
Beyond and Below Racial Homophily: ERG Models of a Friendship Network Documented on Facebook1 (2010, background): “Two students may become friends because they both like Bob Dylan/classical sociological theory, or they may become friends for other reasons and then subsequently assimilate to each other’s preferences (Steglich, Snijders, and Pearson 2010).”
Popularity as a moderator of peer selection and socialization of adolescent alcohol, marijuana, and tobacco use (2013, result): “In fact, models estimating selection and socialization separately for each substance indicated a pattern consistent with previous research suggesting that socialization is relatively more important than selection for alcohol and marijuana use, whereas selection is relatively more important than soci”
Measuring Large-Scale Social Networks with High Resolution (2014, background): “discussed how friendship formation in a dynamic network based on homophily can be mistaken for influence [65], and Shalizi and Thomas showed examples of how homophily and influence can be confounded [6].”
Regular Article (2004, neutral): “The most promising approach is to model the joint dynamics of network-behavior processes based on panel network data (Steglich et al., 2010).”
Network–Behavior Dynamics (2013, methodology): “The stochastic actor-based model was developed to model network evolution and behavior change as two interdependent processes (Steglich et al., 2010).”
Manual for RSiena (2011, methodology): “…estimation of models for repeated measures of social networks according to the Stochastic Actor-oriented Model (‘SAOM’) of Snijders and van Duijn (1997), Snijders (2001), Snijders et al. (2007), Snijders et al. (2010a), Snijders et al. (2013), and Greenan (2015); also see Steglich et al. (2010).”
Transformations in adolescent peer networks (2011, methodology): “Not controlling for such structural network tendencies in the analyses can lead to overestimation of selection effects, which, in turn, affects the estimates for influence by failing to rule out selection effects in a statistically sound way (Steglich et al., 2010).”