You are here

  • Home
  • Archive
  • Volume 59, Issue 6
  • A brief conceptual tutorial of multilevel analysis in social epidemiology: linking the statistical concept of clustering to the idea of contextual phenomenon

Article Text

Article menu
Download PDFPDF
Continuing professional education
A brief conceptual tutorial of multilevel analysis in social epidemiology: linking the statistical concept of clustering to the idea of contextual phenomenon
  1. Juan Merlo1,
  2. Basile Chaix2,
  3. Min Yang3,
  4. John Lynch4,
  5. Lennart Råstam1
  1. 1Department of Clinical Sciences (Community Medicine), Malmö University Hospital, Lund University, Malmö, Sweden
  2. 2Research Team on the Social Determinants of Health and Healthcare, National Institute of Health and Medical Research, Paris, France
  3. 3Institute of Community Health Sciences, Queen Mary University of London, London, UK
  4. 4Department of Epidemiology, Center for Social Epidemiology and Population Health, University of Michigan, Ann Arbor, USA
  1. Correspondence to:
 Professor J Merlo
 Department of Clinical Sciences (Community Medicine), Malmö University Hospital, Faculty of Medicine (Campus Malmö), Lund University, S-205 02 Malmö, Sweden; juan.merlomed.lu.se

Abstract

Study objective: This didactical essay is directed to readers disposed to approach multilevel regression analysis (MLRA) in a more conceptual than mathematical way. However, it specifically develops an epidemiological vision on multilevel analysis with particular emphasis on measures of health variation (for example, intraclass correlation). Such measures have been underused in the literature as compared with more traditional measures of association (for example, regression coefficients) in the investigation of contextual determinants of health. A link is provided, which will be comprehensible to epidemiologists, between MLRA and social epidemiological concepts, particularly between the statistical idea of clustering and the concept of contextual phenomenon.

Design and participants: The study uses an example based on hypothetical data on systolic blood pressure (SBP) from 25 000 people living in 39 neighbourhoods. As the focus is on the empty MLRA model, the study does not use any independent variable but focuses mainly on SBP variance between people and between neighbourhoods.

Results: The intraclass correlation (ICC = 0.08) informed of an appreciable clustering of individual SBP within the neighbourhoods, showing that 8% of the total individual differences in SBP occurred at the neighbourhood level and might be attributable to contextual neighbourhood factors or to the different composition of neighbourhoods.

Conclusions: The statistical idea of clustering emerges as appropriate for quantifying “contextual phenomena” that is of central relevance in social epidemiology. Both concepts convey that people from the same neighbourhood are more similar to each other than to people from different neighbourhoods with respect to the health outcome variable.

  • ICC, intraclass correlation
  • SBP, systolic blood pressure
  • MLRA, multilevel regression analysis
  • VPC, variance partition coefficient
  • blood pressure
  • multilevel analysis
  • neighbourhood health

https://doi.org/10.1136/jech.2004.023473

Statistics from Altmetric.com

    Request Permissions

    If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.

    View Full Text

    Footnotes

    • ↵* According to the ideas of Durkheim (1858–1917) people belonging to a specific community share a collective conscience (common social values and norms that are formed by human relations and interactions and that generate collective feelings of solidarity and connectedness). This collective conscience operates creating what Durkheim called “social cohesion” to bind the social structure together. Understood in this way, the social group emerges as an independent social fact rising over and above individual circumstances, and going beyond the sum of the people that compose it.11 Thus collective characteristics shape the health of the population in a way that cannot be reduced to individual characteristics. A classic example concerns population differences in suicide rates. Even if within each area the people at risk of committing suicide are not the same in different time periods, the differences between populations in suicide rates are fairly stable over time. This fact suggests the existence of a contextual phenomenon that conditions a clustering of individual suicide risk within areas. In other words, some part of the total differences in health between people might be as a consequence of the differences between the areas where the people live. Analogous consideration can be made when interpreting John Snow’s findings on cholera incidence in different areas of London14 and the ideas of Geoffrey Rose on sick people and sick populations.10,12,18

    • ↵† For a review on other programs suitable for MLRA see the Centre for Multilevel Modelling, Institute of Education, London (http://multilevel.ioe.ac.uk/softrev/index.html).

    • Funding: this study is supported by grants from FAS (Swedish Council for Working Life and Social Research) for the projects “Development and application of multilevel analysis in pharmacoepidemiology and social medicine” (principal investigator: Juan Merlo, number 2002-054) and “Socioeconomic disparities in cardiovascular diseases - a longitudinal multilevel analysis” (principal investigator: Juan Merlo, number 2003-0580).

    • Competing interests: none declared.

    Linked Articles

    • In this issue
      Saluting good health
      Carlos Alvarez-Dardet John R Ashton
      Journal of Epidemiology & Community Health 2005; 59 437-437 Published Online First: 23 May 2005.