ITS-530 Midterm Project
The Assessment Instructions
This assignment requires you to demonstrate your understanding from Kirk (2019)11 Kirk, A. (2019). Data visualisation: A handbook for data driven design (2nd ed.). Sage. chapters 1 – 6, in addition to the lessons in R, Units 1 through 5. Remember that your grade is based on your demonstrated understanding of the course content. It is not based on your demonstrated ability to regurgitate others’ ideas or words.
The objective of this project:
Considering the polling during the 2020 presidential campaign,22 The lesson in Unit 5 is based on the 2016 election. Do not submit work based on the 2016 election. If your midterm work is based on that election, you will not earn points for your work. Using the data consolidated by FiveThirtyEight (2020)33 FiveThirtyEight. (2020, November 2). 2020 election forecast [data set and code book] https://data.fivethirtyeight.com/ and election results from Wikipedia (n.d.):44 Wikipedia. (n.d.). 2020 United States election results [data set]. Retrieved May 8, 2020, from https://en.wikipedia.org/wiki/2020_United_States_presidential_election
What relationships exist between the pre-election polling attributes and the 2020 election results that indicate that former President Trump would or could lose the election?
Use Table 1 and Table 2 to understand what information is available for the project. Download the RData files from this document.
Table 1 Data Dictionary for the Polling before the 2020 Presidential Election Data
|State||The target location of the polling sample|
|Candidate Names||The candidate receiving the percentage of polling votes in pct|
|Start Date||The first day interviews were conducted for this poll|
|End Date||The last day interviews were conducted for this poll|
|Pollster||The name of the polling organization|
|Sample Size||The size of the sample|
|Target Population||Whether the population interviewed was adults a, registered voters rv, voters v, or likely voters lv|
|Percentage||The percentage of the vote the candidate in candidate_name received in the poll|
|Poll Identification Number||Specific poll the data is derived from|
Note. The data dictionary of the polling data leading up to the 2020 presidential election is adapted from FiveThirtyEight (2020).
Table 2 Data Dictionary for the Results of the 2020 Presidential Election Data
|State||The location of the voting results|
|Available Electoral Votes||The number of electoral votes allocated to the state in the state field|
|Biden||The percentage of election votes Biden received|
|Trump||The percentage of election votes Trump received|
Note. The data dictionary of the 2020 presidential election results is adapted from Wikipedia (n.d.).
You will document the objective and results of visual analysis in an APA 7 formatted student paper. This document is not an analysis plan; your paper needs to describe the results of an executed visualization project. It may help to think of the paper as a brief business report for a busy executive, except that you will use APA 7 formatting.
You will analyze the data in R. You will submit an R script file with programming that demonstrates the collection, cleaning, exploration, and analysis of the data. When you are conducting your research, you will come across key findings. A key finding is a graph that is interesting and must specifically relate to the overall objective of the research project. Only key findings are included in the research paper. Investigating critical findings from multiple perspectives in the programming will demonstrate your understanding of the weaknesses of visual analysis and prevent false conclusions. If you have done this correctly, there should be numerous figures in the programming that are not in the paper. Lastly, make sure that you provide interpretations of the information learned from each figure included in the paper. The report shall also include how these findings relate to the research objective.
When you think you’ve finished your analysis, revisit the objective. Did you achieve the objective? Did you provide an answer or answers to the research question? Were you thorough? Did you make sure that you did not misinterpret or misrepresent the results due to false conclusions?
Good to know
When you initialize the R script file for the assignment, make sure that the file begins with the three leading comments required in every script file. After these leading comments, call the necessary libraries and load the data before documenting other programming code. Don’t forget to use inline comments.
Reported results not found in the script file will be interpreted as unsupported or erroneous findings because there is no evidence to support the information.
I encourage you to write your report in its entirety before you add any figures. After you’ve written and proofread your paper, then place tables and figures between complete paragraphs, limiting the amount of whitespace figures. The figure labels must be in this order, as well. For example, the first figure is Figure 1; the second is Figure 2, and so on.
A professionally written report will not include discussions regarding R, RStudio, or programming code. Use real words. Don’t use variable names in place of real words. For example, candidate_names is not a real word. However, you could refer to the candidates’ names because those are real words.
When you document this information, you will need to write it as a paper. This is not a blog, a discussion, or a short answer paper. You will need to include an introduction, a topic sentence, supporting paragraphs, and a conclusion. Not great at writing? Go to Start Here in the main menu and look at the resources available to you. Make sure that you document your work using the standards of APA 7. To help with formatting, use the APA 7 student paper template.
You must submit a paper and an R script file for this assignment.
This submission differs from previous coursework because this paper is not a planning document. It is time to see the analysis all the way through and provide the results.
This document does not have a minimum or maximum length. Typically, this submission is about two pages, not including the cover page or reference section. No external sources are required for this assignment, except for the sources of the data. For every reference listed, there must also be content cited that is derived from the references.
There is no reason to regurgitate the words or ideas of others. I am not interested in your ability to research and repeat the words of others. You can use others’ ideas and credit their work. However, I expect to read your ideas, your experiences, and your observations when I read your submitted work.
FiveThirtyEight. (2020, November 2). 2020 election forecast [data set and code book] https://data.fivethirtyeight.com/
Kirk, A. (2019). Data visualisation: A handbook for data driven design (2nd ed.). Sage.
Wikipedia. (n.d.). 2020 United States election results [data set]. Retrieved May 8, 2020, from https://en.wikipedia.org/wiki/2020_United_States_presidential_election/