In our project examining the impact of the COVID-19 pandemic on California's county-level unemployment rates, we sought to address the following problem statement: 'How can we accurately discern the influence of COVID-19 case densities on California's county-level unemployment rates, considering the diverse economic landscapes and industry compositions?' Through meticulous analysis of employment data and COVID-19 case metrics spanning from 2019 to 2022, we aimed to uncover underlying patterns and correlations, shedding light on the pandemic's socioeconomic ramifications at a granular level. By delving into historical trends and conducting statistical analysis, our objective was to provide policymakers and stakeholders with actionable insights to navigate and mitigate the socioeconomic impacts of future public health crises.
In this project, I was a Head Coder, spearheading various critical tasks. I initiated the acquisition of unemployment data, prepared it using Python, and discarded irrelevant columns. Utilizing Panda Dataframes, I successfully created a cohesive dataset for analysis. Crafting yearly unemployment rates relative to population figures was among my responsibilities. Additionally, I was tasked with clipping US Tiger shapefiles to target counties in California and refining fields to enhance data clarity. Subsequently, I joined multiple datasets, including unemployment and COVID data, into shapefiles, enabling comprehensive regression analysis and facilitating map visualization. Moreover, I implemented various functions and loops to automate much of the workflow. Later, I added onto the code to work with other variables and rewrote it to be more concise.
Our regression analysis aimed to shed light on the relationship between COVID-19 case density and changes in unemployment rates. Surprisingly, our findings revealed a lack of statistically significant correlation between these variables for the years 2020 and 2021. However, an unexpected weak negative correlation emerged in 2022, suggesting a potential inverse relationship between COVID-19 case density and unemployment rates. This intriguing result prompts further exploration into the underlying factors influencing economic recovery in counties with higher COVID-19 case densities.
Our project's data findings provide a comprehensive understanding of the intricate dynamics surrounding the impact of the COVID-19 pandemic on unemployment rates at the county level in California. Our analysis uncovered discernible patterns and correlations between various socioeconomic factors and employment fluctuations, particularly throughout the pandemic period spanning from 2019 to 2022.
Noteworthy shifts in unemployment rates were identified across different counties, with prominent spikes observed during the peak of the pandemic in 2020. These fluctuations underscored the significant economic disruptions resulting from the implementation of lockdown measures and business closures. However, as subsequent years unfolded, signs of economic recovery emerged, albeit with varying degrees of improvement observed across counties.
Looking back on our project, we're excited about the next phase. we're proud of the insights we've gained into how the pandemic affected unemployment rates across California's counties. Despite data challenges, we persevered and uncovered valuable trends, shedding light on the complex relationship between economic factors and external influences.
As we transition to our next endeavor of automating regression models for American Community Survey (ACS) data, we carry forward the lessons learned from our COVID-19 analysis. By leveraging data-driven approaches, we aim to deepen our understanding of socio-economic dynamics and contribute to more informed decision-making processes.