1. What are 3 different ways to account for SES in an analytic model when investigating racial/ethnic health disparities? (describe a fourth for extra bonus points!). Briefly discuss the interpretations/implications of each approach as it relates to the interest in understand health disparities by race/ethnicity.
Mediation analysis (utilized in the Lorch article) investigates the effect that a mediator has on the measure of association between an exposure and outcome. This type of analysis employs the use of sequential logistic regression models.
Generalized Estimating Equations or GEEs) (Headen article) uses a log link function to estimate the parameters of a generalized linear model with unknown correlation between outcomes.
Multilevel modeling (Coley) involve construction of a model that varies at more than one level. In the Coley article, they found racial differences in low birth weight outcomes across neighborhood risk levels.
2. Describe a potential effect modifier, mediator, or contextual variable (for definition of contextual variable, see first page of option Merlo reading) for an association of interest to you and relevant to health disparities. For example, for investigating the association between SES and maternal mortality, I might be interested in the contextual variable of exposure to violence in the neighborhood. Describe how you would study whether this relationship exists.
Walsh et al investigated the impact of socioeconomic variables on the relationship between race and survival from ALL in children. They found that no differences in survival between black and white children with standard risk disease, however they found that white children with HR disease had a statistically significant increased OS compared to black children. In multivariable analysis they looked at effects of insurance status, poverty, and other demographic features.
Reference: http://onlinelibrary.wiley.com/doi/10.1002/pbc.26222/full