3D SIR model.py AND SIR Model & Simulation.py:

In this project, I implemented a SIR (Susceptible-Infected-Recovered) model to simulate the spread of COVID-19 in Washington state during 2020. I used NumPy and Matplotlib libraries in Python, to perform numerical computations and create 2D and 3D visualizations. The project involved researching and defining the initial conditions for the population, setting the model parameters (infection and recovery rates), and implementing the Euler method to solve the SIR model equations numerically. The Euler method computes the subsequent values of the susceptible, infected, and recovered populations at each time step based on their values and derivatives at the previous step. I created two types of visualizations to represent the simulation results. The 2D plot shows the evolution of the population groups over time, while the 3D plot provides a unique perspective on the epidemic's dynamics by depicting the trajectories of the populations in a three-dimensional space.

inferential_stats_student_talktime_in_classes.py:

This research analyzed student talk-time-percentage in Minerva University's MC and FA classes, a vital component of student engagement. The study revealed a significant difference in talk time between these classes, indicated by a low p-value of 4.34 * 10-18 and large effect size of 2.27. Confidence intervals further affirmed this disparity. A statistical power of 1.0 shows that if my alternative hypothesis is true, then I reject the null hypothesis with 100% probability. These findings highlight the need for varied instructional approaches tailored to each class type, enhancing student participation where it's traditionally lower. However, the study's scope, limited to two semesters, suggests the need for broader research to confirm these trends and explore their underlying causes. The inferences are inductive, as I’m using sample data from random FA and MC classes at Minerva University to make broader generalizations about talk time in all FA and MC classes that year. Therefore, it is a general trend but not absolute causation, and should be viewed as a basis for informed decision-making in educational strategies at Minerva.

regression_model_auction.py:

The research explored the relationship between the starting price of Mario Kart Wii auctions on eBay and the number of bids. The linear regression was used to investigate this relationship. Correlation coefficient of r=-0.633 indicates a moderately strong negative linear relationship between the two variables. The coefficient of determination R2= 0.401 suggests 40.1% of the variability in the response variable is explained by the starting price and other 59.9% by others. The linear equation can be used to predict the number of bids knowing the starting price: n_bids=-0.247 *start_pr+15.707. The 95% confidence interval of [-0.297, -0.197] for the slope suggests a significant negative relationship between the starting price and the number of bids. The linear equation can be used to set the starting price of eBay auctions strategically by predicting the number of bids in this product segment. Knowing about this negative linear relationship, you can intentionally lower the starting price and manipulate the psychology of the bidders.