We plan to give an introductory tutorial of the R spatial packages (‘sf’, ‘tidycensus’, ‘ipumsr’) and ‘gganimate’ that allow us to download sociodemographic data from as early as 1910 to recent history and to visualize their geographic distributions over time in animated plots. First, we will start with a presentation of introductory geographic information systems (GIS) and spatial epidemiology concepts along with an overview of the Census data. Next, we will demonstrate use of the R spatial packages in a case study investigating the census tract-level relationships between select sociodemographic variables and life expectancy. In our demonstration, will first illustrate how to retrieve recent US Census American Community Survey (ACS) estimates, encompassing variables such as income inequality, racial and ethnic composition, and housing characteristics, using ‘tidycensus’. Additionally, we will showcase how to incorporate national historical GIS information using ‘ipumsr’ for sociodemographic variables, enabling participants to explore long-term trends and disparities. The ‘sf’ package provides us with the functions to map those very trends and life expectancy data from the CDC National Vital Statistics System US Small-area Life Expectancy Estimates Project. Furthermore, the ‘gganimate’ package allows us to extend these visualizations across time in animated maps, thus providing a useful tool to visualize sociodemographic distributions and life expectancy across the US over time.

Throughout the demo, we will emphasize best practices in R programming, empowering attendees to apply the demonstrated techniques to their own datasets beyond the workshop. Additionally, we will provide resources and guidance for further exploration and learning, including relevant R packages and online tutorials. By the end of the session, participants will have gained a foundational understanding of how to leverage R for spatial epidemiological analysis and visualization, enabling them to explore patterns in prevalence and incidence in their own research interests using longitudinal or cross-sectional datasets spanning across time. Whether exploring disease clusters, identifying specific places of focus, or informing public health interventions, attendees will leave equipped with practical skills to drive impactful insights from their data (and of course, create beautiful maps!).