Accounting for spatial clustering with models

EPID 684
Spatial Epidemiology
University of Michigan School of Public Health

Jon Zelner
[email protected]
epibayes.io

Today’s Theme

Radon…in space!

Agenda

  • ‘Postcards’ logistics

  • Air pollution exposure and mortality in Los Angeles

  • Radon ☢️ lab 🧪: Pt 2

In groups of 2-3:

  1. What is the major takeaway from this paper?

  2. How many sources of data were employed? What were they?

  3. How was spatial information included in the statistical modeling?

  4. What concerns/critiques or questions do you have about this analysis?

08:00

Spatially interpolated PM2.5 exposure surface

Interpolated \(PM_{2.5}\) from (1)

Relative PM2.5 is consistent across locations over time

1980 to 2000 PM2.5 from (1)

Analyzing spatial autocorrelation in the deaths data

Return of Radon!

Radon hands-on activity

Next Time

Thinking through the linkages between residential segregation and disease risk

References

1.
Jerrett M, Burnett RT, Ma R, et al. Spatial Analysis of Air Pollution and Mortality in Los Angeles: Epidemiology [electronic article]. 2005;16(6):727–736. (https://insights.ovid.com/crossref?an=00001648-200511000-00004). (Accessed December 15, 2019)