Within the likes of any highly contagious and unpredictable disease, lies a predictable and attainable growth rate that researchers can find in order to make logistical conclusions about that particular disease and its affected regions' counterparts. The foundation that researchers pull from when studying a particular disease and looking for its growth rate is the Susceptible-Infected-Removed (SIR) model, presented by a series of differential equations. The issue with the SIR model lies not in its complexity, but actually its simplicity and lack of a potentially high-finite amount of factors; the limit being bounded by the amount of data available for that particular factor. Our research involves the application of multiple regressions to pinpoint and identify our Covid lockdown periods, followed by the modification of the SIR model. This involved creating new model approximations such as the time-delayed SIR model and the reinfected SIR model in order to take into account factors such as incubation and reinfection, and get the lowest error discrepancy as possible for our infection rate. We were able to conclude that the more factors that we took into account, our error rate became lower and our results became more accurate. We could also identify outlier Metros and draw certain conclusions on performance level and the reasons behind them. We then moved on to find correlations, if any, between the infection rates and outside factors. We looked at demographic and weather data to demonstrate whether correlations appeared. We found that there are a few factors with high correlations, including graduate education and low temperatures.

翻译：在高度传染性和不可预测的疾病中，始终存在一种可预测且可实现的增长率，研究人员可借此对该疾病及其影响区域做出后勤学结论。研究人员在研究特定疾病并寻找其增长率时所依赖的基础是易感-感染-移除(SIR)模型，该模型由一系列微分方程构成。SIR模型的问题不在于其复杂性，而在于其过于简单且缺乏大量潜在影响因素，这些因素的数量受限于该特定因素可获得的数据量。我们的研究涉及应用多元回归技术来精确定位和识别新冠封锁期，随后对SIR模型进行修改。这包括创建新的模型近似方法，如时滞SIR模型和再感染SIR模型，以考虑潜伏期和再感染等因素，从而尽可能降低感染率的误差偏差。我们得出结论：考虑的因素越多，误差率越低，结果越准确。我们还能够识别出异常大都市区域，并对其绩效水平及背后原因做出特定推断。随后我们进一步探究感染率与外部因素之间是否存在关联，分析了人口统计数据和气象数据以验证相关性是否成立，发现包括高等教育水平和低温在内的少数因素与感染率存在高度相关性。