Project 1 Final Deliverable

For this project, you and your group will collaborate to produce a stylized, publication-ready report. The report will include an exploratory data analysis complete with styled visualizations and polished tables which address at least two research questions posed by your group.

Weekly Checkpoints

You will complete weekly checkpoints each of which will help you craft the content for your final deliverable.

  • In Week 1 you will craft the potential research questions that will guide your analysis.
  • In Week 2 you will write data summary functions and iterate over those functions to create professionally styled summary tables.
  • In Week 3 you will acquire external data using APIs and webscraping.
  • In Week 4 you will create professionally styled visualizations using non-standard geometries.

Final Deliverable

Once you’ve completed all the checkpoints, the final step is to assemble your project into a report that walks the reader through two of your research questions.

The final report you create must have the following sections.

Data Context (20 points)

In this section you walk the reader through all the data you will use for your analysis. As you have multiple datasets you will draw on, you should have multiple paragraphs describing each dataset. At a minimum you should address the following for each dataset:

  • Who – Who collected the data? If you do not know who collected the data, then be transparent about the information you know (e.g., who published the data).

  • Where – Where were the data collected i.e., what is the observational unit?

  • When – When were the data collected?

  • How – How were the data collected?

  • Why – Why were the data collected? i.e., why are these data of interest?

Research Questions (10 points)

In this section, you will outline the two research questions that will guide your report. One question must be targeted toward the original data and one question must be targeted toward a new dataset.

Your research questions should be as clear and specific as possible, so it is easy for the reader to see how your findings address these questions.

Data Summaries & Visualizations (50 points)

This section contains summary tables and visualizations that address your research question. For each research question, you are expected to have:

  • Two summary tables

    • At least one summary table needs to be produced with a custom function (from Week 2).
    • At least one summary table needs to include iteration (from Week 2).

  • Two data visualizations

    • At least one visualization must use a more complex geometry (from Week 4).

All summary tables must be professionally formatted.

  • Every table must have formatted values (e.g., decimals, percentages, currencies), boldface headers, and captions.
  • At least one table (out of four) must incorporate additional styling (e.g., color, row group labels, spanner labels)

All visualizations must be professionally formatted.

  • Every visualization must have non-default colors, a non-default theme, clear labels, and an informative plot title.
  • Every visualization must also have alternative (alt) text descriptions of which can be read by a screen reader.

Data Model (10 points)

In this section you must fit one statistical model addressing one of the research questions posed. The output of your model is expected to be professionally formatted so the results are easily communicated to the reader.

Either before or after your summary table, you are expected to communicate the findings of your statistical model and connect them back to the research question which they address.

ImportantOne summary table

If you chose to fit multiple statistical models (e.g., comparing different models), you are expected to collapse these multiple models into a single summary table.

Quarto Document (10 points)

  • uses a non-default theme
  • uses headers and subheaders to delineate the sections
  • uses table and figure numbers to reference findings
  • uses code folding to keep the code invisible unless the reader wants to look at it
WarningCoordinated Colors

The colors from the document theme you chose should match the colors in your plots and tables!

Submission

Your final submission varies based on the course in which you are enrolled. Please see below for the expectations for your course.

STAT 431

For your final submission, your group will submit one GitHub repository link and one HTML document. This means, you will need to choose which group member’s repository will be submitted as the final version.

STAT 541

For your final submission, your group will submit one GitHub repository link and one link to the published HTML document. This means, you will need to choose which group member’s repository will be submitted as the final version.

To publish your document, you will need to sign up for a free Connect Cloud account. I would recommend signing up with your GitHub account, since the documents you will be publishing for Project 1 and Project 2 live in a GitHub repository!

Once you’ve signed up, you need to follow these steps to publish your document:

  1. Click on the “Publish” button on the left sidebar
  2. Select the “From GitHub” tab
  3. Select “Quarto” as the framework
  4. Input the URL of your GitHub repository
  5. The branch you want to push from should be “main”
  6. Input the name of the HTML document you want to publish (e.g., project-1.html)
  7. Select “Publish” to publish your document!
TipPublish on Push

I would recommend toggling on the “Automatically publish on push” option, so your document will automatically update when you push changes to your GitHub repository.