Understanding the promise and perils of hierarchical modeling

EPID 684
Spatial Epidemiology
4/5/2022


Jon Zelner
[email protected]
epibayes.io

Agenda

  • Discussing Subramanian et al. paper (1)

  • Hands-on with some multi-level models.

Discussion Questions

  1. What is the goal of the hierarchical modeling exercise in Subramanian et al.(1)

  2. What is learned from the inclusion of multiple levels of scale (i.e. block group, census tract) in this analysis?

  3. What do you think 1-2 important takeaways are from reading this analysis?

Use this document to share your conclusions

Area-level covariates explained more spatial variation in mortality for Black vs. White residents

Table 4 from (1)

Capturing systematic and random variation with multi-level models

Time to generate some data

Next Time

The Modifiable Areal Unit Problem!

References

1.
Subramanian Sv, Chen JT, Rehkopf DH, et al. Racial Disparities in Context: A Multilevel Analysis of Neighborhood Variations in Poverty and Excess Mortality Among Black Populations in Massachusetts. American Journal of Public Health [electronic article]. 2005;95(2):260–265. (http://ajph.aphapublications.org/doi/full/10.2105/AJPH.2003.034132). (Accessed January 31, 2021)