Accounting for Projection Bias in Models of Delinquent Peer Influence: The Utility and Limits of Latent Variable Approaches

Rebellon, Cesar J.; Modecki, Kathryn L.

doi:10.1007/s10940-013-9199-9

Cited by 44 publications

(59 citation statements)

References 69 publications

(100 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Two main results emerged. First, and in keeping with prior research, Rebellon and Modecki's (2014) structural coefficient linking personal violence to that of peers was much larger in the first model. Upon adjusting this model via Matsueda and Anderson's (1998) suggested error correlation strategy, the structural peer violence coefficient decreased by approximately 15 %, but nonetheless remained substantially larger than the corresponding coefficient in the model using direct measures of peer violence.…”

Section: Introductionsupporting

confidence: 80%

“…Although Rebellon and Modecki's (2014) intention was to explore the utility of correlated errors in SEM models, the prior discussion highlights a series of important and unexplored theoretical and practical implications of their study. Using a large sample of young adult friendship dyads, our study replicates and extends Rebellon and Modecki's study by investigating how the effect size of peer deviance and other independent variables may change across three sets of structural equation models.…”

Section: Current Studymentioning

confidence: 99%

“…In the first set, we estimate models utilizing perceptions of peer deviance without correlating the error terms between perceptions of peer deviance and respondent deviance. In the second set, we re-estimate these models utilizing the correlated-error correction technique employed by both Matsueda and Anderson (1998) and Rebellon and Modecki (2014). 1 In the third set, we estimate models utilizing measures of peer self-reported deviance as a means of comparison with the models based on respondent perceptions of peer deviance, as was done by Rebellon and Modecki. Being that our overall goal is to compare how the coefficient strength of structural variables may change based on each of the three measurement strategies, we draw upon past research using uncorrected (e.g., Boman and Gibson 2011;Meldrum et al 2009) and corrected (Rebellon and Modecki 2014) models to formulate hypotheses.…”

Section: Current Studymentioning

confidence: 99%

“…While perceptions of peer deviance constitute an important component of deviant behavior's etiology (Akers 2009), gauging the relative influence of actual peer behavior on deviance remains critically relevant (see Rebellon and Modecki 2014). In their own assessment of peer influences on deviance, Matsueda and Anderson (1998) attempted to control for respondent misperceptions of peer behavior using latent variable methods.…”

Section: Introductionmentioning

confidence: 99%

“…Although Matsueda and Anderson's (1998) data did not contain the measures needed to test the effectiveness of their strategy for dealing with respondent misperceptions of peer deviance, Rebellon and Modecki (2014) recently provided such a test in this journal. Using original data from a sample of 269 young adult dyads, they estimated two separate models of violence.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Can Item-Level Error Correlations Correct for Projection Bias in Perceived Peer Deviance Measures? A Research Note

2015

Self Cite

View full text Add to dashboard Cite

Objectives Research indicates respondents overestimate the similarity between their own deviance and that of their peers. Extending Rebellon and Modecki's (J Quant Criminol 30:163-186, 2014) study, we examine if item-level error correlations in structural models reduce bias for non-peer-based, theoretically derived covariates such as self-control. Our specific interest lies in investigating the theoretical implications and practical value of using the correlated error technique in 'everyday' structural equation modeling.Methods Using dyadic data and multiple constructs of deviance, we present three sets of structural equation analyses. The first assesses the relationship between peer behavior and deviance via perceptual measures. The second uses identical constructs, but estimates itemlevel error correlations between perceptual and deviance items. The third replaces perceptions of peer deviance with items measuring peers' self-reported behavior.Results Self-control and demographic variables have equivalent effects in perceptuallybased correlated error models and models controlling peer self-reported deviance. However, latent variable adjustments to perceptions of peer behavior fail to bring perceived peer deviance coefficients into line with corresponding coefficients from models using peer self-reports, indicating that perceptions and peer self-reports are distinct constructs.Conclusion Researchers cannot use item-level error-correlations to model peer effects without collecting data from peers. They may, however, use these correlations to control for peer effects even when peer self-reports are not available. Because we find strong effects of self-control while maintaining social learning theory's emphasis on perceptions, we argue that the technique is a form of theoretical reconciliation and recommend criminologists adopt the use of correlated errors in all social influence-based structural models.

show abstract

Section: Introductionsupporting

confidence: 80%

Section: Current Studymentioning

confidence: 99%