Feel free to check out the links for more details on my work
The main goal here was to determine which features best predict high frequency users of an emergency department using the MIMIC-III clinical dataset. Understanding high frequent users of the emergency department, and what makes them frequent users is essential in determining how we can better manage wait times in our hospitals.
The goal of this project was to look at the factors behind the ‘deadliness’ of a mass shooting event across the United States. We ask the questions:
Understanding how different personal factors and state level policies are associated with gun violence can help us improve future policies, and implement better strategies to combat gun violence in the US. (Note, I am Canadian but this was too cool of a project to not look at).
This project uses Python to wrangle provincial election data and Tableau to show how different parties in Ontario performed in the 2018 and 2022 election. I highlight how each main party (LIB, CON, NDP) performed in each riding, which riding actually changed parties between the two elections, and how they changed in their performance between the two elections. (WIP for the latest provinvial election).
I decided to use an autoregressive integrated moving average (ARIMA) in two different styles, manual and automatic arima, to forecast COVID-19 cases in the US. In this instance, I used the NYT Covid Dataset from Kaggle and looked at the daily COVID cases across all of the United States from the beginning of the pandemic to the end of January 2023.
This project also asks whether COVID 19 mortalities were higher in states where people traveled more during the first year of the pandemic, is there a realtionship between increased travel and COVID-19 mortality?
This project is about understanding how we can create structured data from an unstructured dataset (like chess notation data), and perform out own analysis on it. Often times, the most time consuming and critical parts of data analys is simply being able to create a nice rectangular dataset. Understanding how to do this well, and how to do it right is critical in any future statistical analysis. We also take a quick look at how advantageous the first move is in chess and how popular the e4 pawn move is across all the different ELOs.
============================================================================================ You can also visit my github profile : here And My CV: here