Final Project Grading Rubrics

These are in addition to the usual rubrics for problem sets and exams.

  • It is not enough to simply use an already-assembled data set. Instead, you must combine data from two or more different sources. Looking at your data-munging code will confirm for us that you have made an actual contribution to human knowledge. Imagine that your roommate also cares about soccer/wine/politics/whatever. You are building something that would interest her, something that will make her say, “That is cool! Let’s spend 30 minutes poking around with your data.” Projects without at least 10,000 data points are unlikely to be interesting enough, but feel free to convince us otherwise. Projects must feature some statistical modelling, most commonly a regression.

  • You should have a one and four sentence summary of your project memorized for Demo Day. The one sentence summary is for listeners who want the briefest possible pitch. The four sentence summary is for those who want more details. Both should be smooth and persuasive. People are busy. Why should they pay attention to you?

  • Your repo must be public.

  • Your repo must contain a professional README.

  • We will look at (and grade) your code in conjunction with the Demo Day evaluation.

  • Give your repo and Shiny App a descriptive name. “Vaccine-Explorer” or “syrian_civil_war” is good. “Gov_1005_Final_Project” or “project_test” is not.

  • The typical Shiny App will include three tabs. The “About” tab will provide background information about the project and your data. The second tab will display some data/graphics, and allow the user to make some choices. The display must change depending on user input. The third tab will be a detailed explanation of your model and what it means.

  • Apps should all have an “Info” or “About” tab which includes, your name, contact information, GitHub repo and data source information. Include other background information as you see fit.

  • Apps should “open” on an interesting tab, which will usually not be the “About” tab.

  • Apps should have at least one tab in which the user can select something and see a change.

  • Apps often have “story” tabs which, although they do not allow for user selections, do highlight specific aspects of the data which are interesting, and which users are unlikely to discover by themselves. They are not labeled with the word “story.”

  • Fill out the Final Project Spreadsheet accurately. Failure to do so will cost you two points.

David Kane
Data Scientist
comments powered by Disqus