Share

Multilevel Modeling

3. Multilevel Framework

Figure 1 identifies a typology of designs for data collection and analyses (Blakely and Woodward, 2000; Kawachi and Subramanian, 2006) where the rows indicate the level or unit at which the outcome variable is being measured, i.e., at the individual level (y) or the aggregate, or ecological, level (Y), and the columns indicate whether the exposure is being measured at the individual level (t) or the ecological level (T).

Figure 1

Typology of Studies



Exposure


t
T
Outcome
y
{y, t}
Traditional risk factor study
{y, T}
Contextual study
Y
{Y, t}(A)
{Y, T}
Ecological study
Note: (A) This type of study is impossible to specify as it stands. Practically speaking, it will either take the form of {Y, T}, i.e., ecological study, where T will now simply be central tendency of t. Or, if dis-aggregation of Y is possible, so that we can observe y, then it will be equivalent to {y, t}.

  • Study-type {y, t} is most commonly encountered when the researcher aims to link exposure measured at the individual level (e.g., diet) to individual health outcomes (e.g., BMI). Study-type {y, t} not only ignores ecological effects (either implicitly or explicitly), but with its individualistic focus resonates with the notion of health as solely a matter of individual responsibility (Moon, Subramanian et al., 2005).
  • Conversely, study-type {Y, T} - referred to as an “ecological study” – may seem intuitively appropriate for research on population health and ecological exposures.
  • However, study-type {Y, T} conflates the genuinely ecological and the ‘aggregate’ or compositional (Moon, Subramanian et al., 2005), and precludes the possibility of testing heterogeneous contextual effects on different types of individuals.

Ecological effects reflect predictors and associated mechanisms operating solely at the contextual level. The search for such measures and their scientific validation and assessment is an area of active research (Raudenbush, 2003).

Aggregate effects, in contrast, equate the effect of a neighborhood with the sum of the individual effects associated with the people living within the neighborhood. In this situation the interpretative question becomes particularly relevant. If common membership in a neighborhood by a set of individuals brings about an effect that is over and above those resulting from individual characteristics, then there may indeed be an ecological effect (i.e., the whole may be more than the sum of its parts). If this is not the case, then it is individual factors that matter, not ecological effects.

Raudenbush, S. W. (2003) The quantitative assessment of neighborhood social environment. In: I. Kawachi and L. F. Berkman (Eds.). Neighborhoods and health. New York: Oxford University Press.
Moon, G., Subramanian, S. V., et al. (2005) Area-based studies and the evaluation of multilevel influences on health outcomes. In: A. Bowling and S. Ebrahim (Eds.). Handbook of Health Research Methods: Investigation, Measurement and Analysis.Berkshire, UK : Open University Press. 266-292.