Now that you guys are all updated on the terms and foundations of my project, the next step is to create my hypothesis.
As we find ourselves immersed in the 21st century, surrounded by an abundance of TikTok and Instagram trends promoting healthier lifestyles, people become more influenced and interested in living a much more balanced life.
My hypothesis is that if the trends play out with the demographic population, then the rate of statin usage will increase at a faster rate than the rate of heart disease because people are more proactive with their health.
Now to the actual experiment! Below are the steps I took for my project and I used the platform, Excel.
The first step in my experiment in my project is to use the most recent data of the U.S. population from the U.S. Census (2020) and divide each of the numbers in their respective age brackets by five as each age bucket was grouped by five years. Using a table and organizing the numbers, I forecasted the population of each respective age. Then I forecasted the population for each age group up to 2030. Next, using historical data of statin usage by age category, I was able to use linear regression to help model out the percentage of people taking statin all the way to 2030. Implementing the population data and the statin usage data, I created a table to multiply each of the corresponding age brackets by their respective statin usage data also grouped together by age. For example, a specific group would be multiplied by their designated statin usage percentage and then I would get the approximate number of people taking statin all per age group. Next, I calculated the total statin usage by year (total # of statin users divided by total population). Then I calculated the year over year statin usage percent change. Additionally, I used the CDC government website to get the percentage of people with heart disease by age category and year. Using historical data of people with heart disease, I agin used linear regression to help model out the percentage of people with heart disease to 2030. I then multiplied the percentage of people with heart disease to their designated population age bracket. After, calculated the total number of heart disease cases and divided it by the total population. Then I calculated the year over year heart disease change. Lastly, I took the two percentage totals for each progressive year and correlated the 10 year change between 2020 to 2030 for both and compared the percentage increase for each.
To avoid bias or any skewed results, the historical data used to predict the statin usage percentages as well as the heart disease percentages was from the same year span of 2007 to 2013. Furthermore, I also multiplied each population age category to the same age category of the corresponding variable (either Statin usage or heart disease) to ensure that the percentage total would be as accurate as it could be. Doing the same 10 year span also ensured that the data was given a fair amount of time to remain consistent.
It’s important to note that before I was able to get accurate data, it took a lot of trial and error before I could actually graph and explain my results.
Join in with me for the last segment of my blog post where I uncover the results and my conclusion for my 2023 Science Fair Project!


Leave a comment