1. Which data set did you select and why did you choose it? Summarize the data included, being specific about the types of data (text, sounds, transactions, etc.) included. Make sure you list the title and the website where you found the data.
We chose the U.S. presidential election data set because we thought it would be the most interesting to examine. The data includes numerical data on various things, like the percent of the popular vote for each candidate, number of votes cast by party in each state, and number of electoral votes won by each candidate. There is also similar numerical data on the Senate and house elections. The data can be found on the Federal Election Commission website, at this link: https://transition.fec.gov/pubrec/electionresults.shtml
2. List your 3-5 hypotheses and the data visualizations that you created for each. (Include the visualizations as images on your portfolio or provide a link to them shared with your instructor.)
If a candidate wins the popular vote, they will also win the electoral vote.
If someone wins the presidency, their party will have more votes in the Senate race.
If California has more votes for one party in the House race, it will also have more votes for that party in the presidential race.
3. Explain how collaborating with a partner helped you gain new insight or knowledge about the data.
Collaborating with a partner helped me to more fully understand the data that I was examining. Working together allowed both of us to see things in the data that we wouldn't have if we were working alone. For example, my partner called my attention to the subscripts that explained that 7 electoral votes had gone to candidates not belonging to the Republican or Democratic parties. This was helpful because I was confused about why the total amount of electoral did not add up to 538 like I expected it to.
4. Identify at least one security and/or privacy concern that is associated with the data in the data set you chose.
The data could be examined and used to help rig an election in the future. In order to convincingly deceive people, you would need to have knowledge on the amount of votes that could be expected from a given area in order to make it convincing. This data could be used to do that because it is very in depth about the election numbers.