Navigating non-positivity in neighbourhood studies: An analysis of collective efficacy and violence

Jennifer Ahern, Magdalena Cerda, Sheri A. Lippman, Kenneth J. Tardiff, David Vlahov, Sandro Galea

Research output: Contribution to journalArticle

23 Citations (Scopus)

Abstract

Background: In multilevel studies, strong correlations of neighbourhood exposures with individual and neighbourhood confounders may generate problems with non-positivity (ie, inferences that are 'off-support'). The authors used propensity restriction and matching to (1) assess the utility of propensity restriction to ensure analyses are 'on-support' and (2) examine the relation between collective efficacy and violence in a previously unstudied city. Methods: Associations between neighbourhood collective efficacy and violent victimisation were estimated in data from New York City in 2005 (n=4000) using marginal models and propensity matching. Results: In marginal models adjusted for individual confounders and limited to observations 'on-support', under conditions of high collective efficacy, the estimated prevalence of violent victimisation was 3.5/ 100, while under conditions of low collective efficacy, it was 7.5/100, resulting in a difference of 4.0/100 (95% CI 2.6 to 5.8). In propensity-matched analysis, the comparable difference was 4.0/100 (95% CI 2.1 to 5.9). In analyses adjusted for individual and neighbourhood confounders and limited to observations 'on-support', the difference in violent victimisation associated with collective efficacy was 3.1/100 (95% CI 1.2 to 5.2) in marginal models and 2.4/100 (95% CI 0.2 to 4.5) in propensity-matched analysis. Analyses without support restrictions produced surprisingly similar results. Conclusions: Under conditions of high collective efficacy, there was about half the prevalence of violence compared with low collective efficacy. The results contribute to a growing body of evidence that suggests collective efficacy may shape violence, and illustrate how careful techniques can be used to disentangle exposures from highly correlated confounders without relying on model extrapolation.

Original languageEnglish (US)
Pages (from-to)159-165
Number of pages7
JournalJournal of Epidemiology and Community Health
Volume67
Issue number2
DOIs
StatePublished - Jan 1 2013
Externally publishedYes

Fingerprint

Violence
Crime Victims

ASJC Scopus subject areas

  • Epidemiology
  • Public Health, Environmental and Occupational Health

Cite this

Navigating non-positivity in neighbourhood studies : An analysis of collective efficacy and violence. / Ahern, Jennifer; Cerda, Magdalena; Lippman, Sheri A.; Tardiff, Kenneth J.; Vlahov, David; Galea, Sandro.

In: Journal of Epidemiology and Community Health, Vol. 67, No. 2, 01.01.2013, p. 159-165.

Research output: Contribution to journalArticle

Ahern, Jennifer ; Cerda, Magdalena ; Lippman, Sheri A. ; Tardiff, Kenneth J. ; Vlahov, David ; Galea, Sandro. / Navigating non-positivity in neighbourhood studies : An analysis of collective efficacy and violence. In: Journal of Epidemiology and Community Health. 2013 ; Vol. 67, No. 2. pp. 159-165.
@article{296ceeb402b343caacbd68f6d589fe14,
title = "Navigating non-positivity in neighbourhood studies: An analysis of collective efficacy and violence",
abstract = "Background: In multilevel studies, strong correlations of neighbourhood exposures with individual and neighbourhood confounders may generate problems with non-positivity (ie, inferences that are 'off-support'). The authors used propensity restriction and matching to (1) assess the utility of propensity restriction to ensure analyses are 'on-support' and (2) examine the relation between collective efficacy and violence in a previously unstudied city. Methods: Associations between neighbourhood collective efficacy and violent victimisation were estimated in data from New York City in 2005 (n=4000) using marginal models and propensity matching. Results: In marginal models adjusted for individual confounders and limited to observations 'on-support', under conditions of high collective efficacy, the estimated prevalence of violent victimisation was 3.5/ 100, while under conditions of low collective efficacy, it was 7.5/100, resulting in a difference of 4.0/100 (95{\%} CI 2.6 to 5.8). In propensity-matched analysis, the comparable difference was 4.0/100 (95{\%} CI 2.1 to 5.9). In analyses adjusted for individual and neighbourhood confounders and limited to observations 'on-support', the difference in violent victimisation associated with collective efficacy was 3.1/100 (95{\%} CI 1.2 to 5.2) in marginal models and 2.4/100 (95{\%} CI 0.2 to 4.5) in propensity-matched analysis. Analyses without support restrictions produced surprisingly similar results. Conclusions: Under conditions of high collective efficacy, there was about half the prevalence of violence compared with low collective efficacy. The results contribute to a growing body of evidence that suggests collective efficacy may shape violence, and illustrate how careful techniques can be used to disentangle exposures from highly correlated confounders without relying on model extrapolation.",
author = "Jennifer Ahern and Magdalena Cerda and Lippman, {Sheri A.} and Tardiff, {Kenneth J.} and David Vlahov and Sandro Galea",
year = "2013",
month = "1",
day = "1",
doi = "10.1136/jech-2012-201317",
language = "English (US)",
volume = "67",
pages = "159--165",
journal = "Journal of Epidemiology and Community Health",
issn = "0143-005X",
publisher = "BMJ Publishing Group",
number = "2",

}

TY - JOUR

T1 - Navigating non-positivity in neighbourhood studies

T2 - An analysis of collective efficacy and violence

AU - Ahern, Jennifer

AU - Cerda, Magdalena

AU - Lippman, Sheri A.

AU - Tardiff, Kenneth J.

AU - Vlahov, David

AU - Galea, Sandro

PY - 2013/1/1

Y1 - 2013/1/1

N2 - Background: In multilevel studies, strong correlations of neighbourhood exposures with individual and neighbourhood confounders may generate problems with non-positivity (ie, inferences that are 'off-support'). The authors used propensity restriction and matching to (1) assess the utility of propensity restriction to ensure analyses are 'on-support' and (2) examine the relation between collective efficacy and violence in a previously unstudied city. Methods: Associations between neighbourhood collective efficacy and violent victimisation were estimated in data from New York City in 2005 (n=4000) using marginal models and propensity matching. Results: In marginal models adjusted for individual confounders and limited to observations 'on-support', under conditions of high collective efficacy, the estimated prevalence of violent victimisation was 3.5/ 100, while under conditions of low collective efficacy, it was 7.5/100, resulting in a difference of 4.0/100 (95% CI 2.6 to 5.8). In propensity-matched analysis, the comparable difference was 4.0/100 (95% CI 2.1 to 5.9). In analyses adjusted for individual and neighbourhood confounders and limited to observations 'on-support', the difference in violent victimisation associated with collective efficacy was 3.1/100 (95% CI 1.2 to 5.2) in marginal models and 2.4/100 (95% CI 0.2 to 4.5) in propensity-matched analysis. Analyses without support restrictions produced surprisingly similar results. Conclusions: Under conditions of high collective efficacy, there was about half the prevalence of violence compared with low collective efficacy. The results contribute to a growing body of evidence that suggests collective efficacy may shape violence, and illustrate how careful techniques can be used to disentangle exposures from highly correlated confounders without relying on model extrapolation.

AB - Background: In multilevel studies, strong correlations of neighbourhood exposures with individual and neighbourhood confounders may generate problems with non-positivity (ie, inferences that are 'off-support'). The authors used propensity restriction and matching to (1) assess the utility of propensity restriction to ensure analyses are 'on-support' and (2) examine the relation between collective efficacy and violence in a previously unstudied city. Methods: Associations between neighbourhood collective efficacy and violent victimisation were estimated in data from New York City in 2005 (n=4000) using marginal models and propensity matching. Results: In marginal models adjusted for individual confounders and limited to observations 'on-support', under conditions of high collective efficacy, the estimated prevalence of violent victimisation was 3.5/ 100, while under conditions of low collective efficacy, it was 7.5/100, resulting in a difference of 4.0/100 (95% CI 2.6 to 5.8). In propensity-matched analysis, the comparable difference was 4.0/100 (95% CI 2.1 to 5.9). In analyses adjusted for individual and neighbourhood confounders and limited to observations 'on-support', the difference in violent victimisation associated with collective efficacy was 3.1/100 (95% CI 1.2 to 5.2) in marginal models and 2.4/100 (95% CI 0.2 to 4.5) in propensity-matched analysis. Analyses without support restrictions produced surprisingly similar results. Conclusions: Under conditions of high collective efficacy, there was about half the prevalence of violence compared with low collective efficacy. The results contribute to a growing body of evidence that suggests collective efficacy may shape violence, and illustrate how careful techniques can be used to disentangle exposures from highly correlated confounders without relying on model extrapolation.

UR - http://www.scopus.com/inward/record.url?scp=84872139349&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84872139349&partnerID=8YFLogxK

U2 - 10.1136/jech-2012-201317

DO - 10.1136/jech-2012-201317

M3 - Article

C2 - 22918895

AN - SCOPUS:84872139349

VL - 67

SP - 159

EP - 165

JO - Journal of Epidemiology and Community Health

JF - Journal of Epidemiology and Community Health

SN - 0143-005X

IS - 2

ER -