Jump to comment:

• Multilevel modelling of the longitudinal influence of neighbourhoods on health
  Alastair H Leyland
  Published on: 27 April 2016

• Published on: 27 April 2016

  Multilevel modelling of the longitudinal influence of neighbourhoods on health

  • Alastair H Leyland, Senior Research Scientist
  • Other Contributors:
    • Øyvind Næss

  Dear Editor

   

  ...

  Show More

  Dear Editor

   

  We read with interest the recent editorial setting an agenda for future research considering neighbourhood influences on health.[1] Whilst agreeing with many of the points raised in the editorial we take issue with the proposed use of multiple membership multilevel models to explore contextual effects at different points in time.

   

  A recent paper used multiple membership models to analyse the effect of area of residence observed over 9 years on individuals’ health (measured just at the final time point).[2] An accompanying editorial pointed out the problems with the use of such models.[3] Since we agree that understanding the longitudinal influence of area of residence over time will form a key part of the neighbourhood research agenda we expand on the reasons that make multiple membership models unsuitable for important research questions pertinent to the field and propose an alternative model.

   

  If person P₁ lived in area A₁ at time T₁ and in area A₂ at time T₂ then from a life course perspective we might expect there to be a contribution of both areas to that person’s measured or reported health at time T₂. Similarly, if person P₂ moved in the opposite direction then we would expect a contribution from both areas. The multiple membership model, however, makes two simplifying and unrealistic assumptions. Firstly, the effect of each area is assumed to be the same at both times, having the same effect on person P₁ at time T₁ as on person P₂ at time T₂. This means assuming that the area effect is not dependent on the period; the regeneration or decay of areas is ignored. Secondly, the multiple membership model requires explicit weights to be attached to the contribution of each area to an individual’s health. Suggesting that this should be done on the basis of the time spent in each area[1] is to assume that the effect of an area is constant irrespective of the stage of the life course – in other words, such an analysis assumes that the risk associated with neighbourhoods accumulates at a steady rate throughout the life course. So if persons P₁ and P₂ spent an equal amount of time in each area, the direction of movement (from A₁ to A₂ or from A₂ to A₁) is ignored. Alternative models – such as a critical period model – cannot be investigated under such a framework.[4] Yet the influence of the social environment along the life course has been shown to differ for specific diseases.[5]

   

  The authors propose extending the above model to one where health, as well of area of residence, is measured at both time points.[1] In addition to the assumptions noted above, the suggestion that the area of residence at time T₂ affects health measured at time T₁ clearly departs from the usual model of causation.

   

  A more suitable model for such data is the cross-classified multilevel model. Figure 1 illustrates the classification diagram for individuals (at level 1) whose health is measured at time T₂ and who live in a cross-classification of areas at times T₁ and T₂. Every individual lives in an area at each time point, whether these are different areas (P₁ and P₂) or the same area (P₃ and P₄). When health is measured at T₁ individuals are nested within areas in a strict hierarchy; when health is measured at T₃ there is a three-way cross-classification of areas at T₁, T₂ and T₃. The cross-classified model does not make the assumption that area effects will be the same at the two time points; in fact, the assumption that the effects for one area at different times are uncorrelated is likely to lead to conservative estimates of the variance components. However, the free estimation of the variances associated with each time point means that a variety of life course models can be examined without the need for prior assumptions.

   

   

  Level 1: Person

  Level 2(1): Neighbourhood at time T1

  Level 2(2): Neighbourhood at time T2

  

   

   

  Figure 1 Multilevel structure of individuals nested within a cross-classification of areas at two time points (T₁ and T₂). Diagram shows person P₁ moving from area A₁ to area A₂ and person P₂ moving from area A₂ to area A₁.

   

   

   

  Alastair H Leyland

  Senior Research Scientist

  MRC Social and Public Health Sciences Unit, Glasgow, Scotland

   

  Øyvind Næss

  Senior Scientist

  Epidemiological Division, National Public Health Institute, Oslo, Norway

   

  Correspondence to:

  Alastair H Leyland

  MRC Social and Public Health Sciences Unit

  4 Lilybank Gardens

  Glasgow G12 8RZ

  Scotland

   

   

  References

   

  1.       Kawachi I, Subramanian SV. Neighbourhood influences on health. Journal of Epidemiology and Community Health 2007; 61:3-4.

  2.       Chandola T, Clarke P, Wiggins RD, et al. Who you live with and where you live: setting the context for health using multiple membership multilevel models. Journal of Epidemiology and Community Health 2005; 59:170-5.

  3.       Leyland AH. Assessing the impact of mobility on health: implications for lifecourse epidemiology.Journal of Epidemiology and Community Health 2005; 59:90-1.

  4.       Kuh D, Ben-Schlomo Y, Lynch J, et al. Life course epidemiology. Journal of Epidemiology and Community Health 2003; 57:778-83.

  5.       Næss Ø, Strand BH, Davey Smith G. Childhood and adulthood socioeconomic position across 20 causes of death. A prospective cohort study of 800 000 Norwegian men and women.Journal of Epidemiology and Community Health (in press).

   

   

  Show Less

  Conflict of Interest:
  None declared.

  • Back to top