Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

General and specific contextual effects in multilevel regression analyses and their paradoxical relationship : A conceptual tutorial

Merlo, Juan LU orcid ; Wagner, Philippe LU ; Austin, Peter C. ; Subramanian, S. V. and Leckie, George (2018) In SSM - Population Health 5. p.33-37
Abstract

To be relevant for public health, a context (e.g., neighborhood, school, hospital) should influence or affect the health status of the individuals included in it. The greater the influence of the shared context, the higher the correlation of subject outcomes within that context is likely to be. This intra-context or intra-class correlation is of substantive interest and has been used to quantify the magnitude of the general contextual effect (GCE). Furthermore, ignoring the intra-class correlation in a regression analysis results in spuriously narrow 95% confidence intervals around the estimated regression coefficients of the specific contextual variables entered as covariates and, thereby, overestimates the precision of the estimated... (More)

To be relevant for public health, a context (e.g., neighborhood, school, hospital) should influence or affect the health status of the individuals included in it. The greater the influence of the shared context, the higher the correlation of subject outcomes within that context is likely to be. This intra-context or intra-class correlation is of substantive interest and has been used to quantify the magnitude of the general contextual effect (GCE). Furthermore, ignoring the intra-class correlation in a regression analysis results in spuriously narrow 95% confidence intervals around the estimated regression coefficients of the specific contextual variables entered as covariates and, thereby, overestimates the precision of the estimated specific contextual effects (SCEs). Multilevel regression analysis is an appropriate methodology for investigating both GCEs and SCEs. However, frequently researchers only report SCEs and disregard the study of the GCE, unaware that small GCEs lead to more precise estimates of SCEs so, paradoxically, the less relevant the context is, the easier it is to detect (and publish) small but “statistically significant” SCEs. We describe this paradoxical situation and encourage researchers performing multilevel regression analysis to consider simultaneously both the GCE and SCEs when interpreting contextual influences on individual health.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
in
SSM - Population Health
volume
5
pages
5 pages
publisher
Elsevier
external identifiers
  • scopus:85047414523
  • pmid:29892693
ISSN
2352-8273
DOI
10.1016/j.ssmph.2018.05.006
language
English
LU publication?
yes
id
b9e14d92-66e6-47cb-baf3-f0bcc8eccdb2
date added to LUP
2018-06-05 09:24:25
date last changed
2024-06-25 18:02:58
@article{b9e14d92-66e6-47cb-baf3-f0bcc8eccdb2,
  abstract     = {{<p>To be relevant for public health, a context (e.g., neighborhood, school, hospital) should influence or affect the health status of the individuals included in it. The greater the influence of the shared context, the higher the correlation of subject outcomes within that context is likely to be. This intra-context or intra-class correlation is of substantive interest and has been used to quantify the magnitude of the general contextual effect (GCE). Furthermore, ignoring the intra-class correlation in a regression analysis results in spuriously narrow 95% confidence intervals around the estimated regression coefficients of the specific contextual variables entered as covariates and, thereby, overestimates the precision of the estimated specific contextual effects (SCEs). Multilevel regression analysis is an appropriate methodology for investigating both GCEs and SCEs. However, frequently researchers only report SCEs and disregard the study of the GCE, unaware that small GCEs lead to more precise estimates of SCEs so, paradoxically, the less relevant the context is, the easier it is to detect (and publish) small but “statistically significant” SCEs. We describe this paradoxical situation and encourage researchers performing multilevel regression analysis to consider simultaneously both the GCE and SCEs when interpreting contextual influences on individual health.</p>}},
  author       = {{Merlo, Juan and Wagner, Philippe and Austin, Peter C. and Subramanian, S. V. and Leckie, George}},
  issn         = {{2352-8273}},
  language     = {{eng}},
  month        = {{08}},
  pages        = {{33--37}},
  publisher    = {{Elsevier}},
  series       = {{SSM - Population Health}},
  title        = {{General and specific contextual effects in multilevel regression analyses and their paradoxical relationship : A conceptual tutorial}},
  url          = {{http://dx.doi.org/10.1016/j.ssmph.2018.05.006}},
  doi          = {{10.1016/j.ssmph.2018.05.006}},
  volume       = {{5}},
  year         = {{2018}},
}