COVID-19, Vaccination, and Labor Force Trends in Chicago: Initial Findings
Introduction
The COVID-19 pandemic was a major public health emergency, causing widespread disruption, lockdowns, and a significant amount of illness. The impacts of the pandemic continue to be felt today, shaping the country’s economic conditions. Research has been conducted to understand the economic impacts. This project investigates whether variations in COVID-19 infection rates and vaccination coverage at the ZIP-code level are associated with labor force participation in Chicago, IL. This project utilizes predictive modeling to examine the impact of health and socioeconomic characteristics on labor force participation in Chicago, to identify key drivers of local economic recovery. This research aims to fill the gap by examining Chicago to assess the impact of COVID-19 on the local economy, with a specific focus on the workforce, and to identify any disparities.
Map of Vaccinaiton
The choropleth of vaccination rates reveals some critical information for the rest of the project data provided by City of Chicago Open Data. It is very clear that the south side of the city of Chicago tends to have the worst vaccination rates, along with a few western zip codes. These results further highlight economic disparities present before the pandemic and likely exacerbated during the pandemic. Also note that downtown Chicago had a very high vaccination rate over 100%, likely due to either vaccination centers or misclassification. However, this can help highlight that the most densely populated and more affluent areas tend to have better vaccination rates.
Summary Stastics
Variable | Mean | Standard Deviation | Median | Min | Max | Count |
|---|---|---|---|---|---|---|
Monthly Cases | 279.74 | 456.44 | 139.00 | 0.00 | 4,755.00 | 2,907 |
Monthly Vaccination Rate | 0.39 | 0.34 | 0.49 | 0.00 | 1.28 | 2,907 |
Total Population | 47,801.89 | 25,283.29 | 46,621.00 | 729.00 | 107,930.00 | 2,907 |
Health Insurance Coverage | 47,322.42 | 25,033.32 | 46,283.00 | 729.00 | 107,917.00 | 2,907 |
Labor Force Total | 39,058.77 | 20,023.44 | 38,046.00 | 724.00 | 80,443.00 | 2,907 |
The descriptive statistics above provide a snapshot of ZIP-code-level data variation in Chicago data from the US Census American Community Survey (ACS), highlighting the key variables in this research. For the monthly case average, 280 COVID-19 cases with a large standard deviation of 456, along with the 4,755 maximum value, indicate that there are likely large constraints in specific time periods and or areas. It is also worth noting that some of the monthly case counts were recorded prior to the pandemic.
Total population and health insurance coverage are very close to one another in almost all categories, showing that only a minimal number of individuals in the city of Chicago lack health insurance. The gap between labor force totals and population shows some variation by zip code. These results suggest disparities in labor force participation, with some areas having notably smaller workforces, highlighting underlying inequalities.
Labor Force Trends
The histogram displays the distribution of the total labor force across Chicago ZIP codes data from the ACS. The majority of the labor force is between 20,000 and 65,000; a small number of zip codes are below 1000. The values were for transparency but likely reflect more non-residential areas, data limitations, and under-reporting. This could also be because different zip codes have unequal population distribution and therefore different economic values. The chart highlights the variation in labor force size across Chicago ZIP codes, highlighting that areas with a large workforce population may play a role in shaping public health and economic outcomes. This helps to show the broader context of the labor force in Chicago. This is a key variable in the analysis of the economic impact of the COVID-19 pandemic and aids in further prediction.
Conclusion
This research will utilize a set of machine learning (ML) methods as an example. Linear regression will aid in establishing a baseline for both R-squared and RMSE, and will serve as a basis for comparing Random Forest and hierarchical clustering methods. The research shifted toward predicting where to allocate resources for policymakers to help mitigate further inequalities. These summary statistics and visualizations begin to reveal meaningful trends and highlight areas for improvement. While more advanced analysis is still needed, initial patterns are already emerging.
Citations
City of Chicago. n.d. COVID-19 Vaccination Coverage by ZIP Code. https://data.cityofchicago.org/Health-Human-Services/COVID-19-Vaccination-Coverage-by-ZIP-Code/553k-3xzc (accessed July 9, 2025).
City of Chicago. n.d. COVID-19 Cases, Tests, and Deaths by ZIP Code. https://data.cityofchicago.org/Health-Human-Services/COVID-19-Cases-Tests-and-Deaths-by-ZIP-Code/yhhz-zm2v (accessed July 9, 2025).
U.S. Census Bureau. 2021. American Community Survey 5-Year Estimates, 2020. https://www.census.gov/programs-surveys/acs (accessed July 15, 2025).