Specifications

You are responsible for a final squib / project that performs (i) data wrangling, (ii) visualization, (iii) statistical analysis, and (iv) reasonable justification for the validity of those analyses of some quantitative data of linguistic interest using a non-trivial amount of R.

There is no hard and fast rule for the length here (of amount of R code or descriptive prose) but keep in mind this is the final term project for the course and should have a scope which reflects that.

If you are not sure whether your project idea satisfies the above specifications, send a brief note to Spencer over Slack before proceeding.

The data you use and the specific implementation you go with are totally up to you. It is completely fine to use experimental data that someone else gathered. In fact, this might be the most practical option rather than working with something that's in-progress on your end. It is also okay (good, even) if this term project harmonizes with some other research endeavor you're already pursuing (e.g., qualifying papers, MA thesis, etc.), so long as you make it clear in your write-up what part of the project is unique to the term paper.

If you are not sure what data to use or where to begin please get in touch with me (Spencer) and I'll be happy to discuss practical ideas.

What to submit

Your submission should be a .zip file which includes: your code, the data used, and a Markdown file (both .Rmd and knitted html) which describes and implements the following:

  1. the theoretical interest in the data / project and how the data were obtained (whether via experiment, corpus, or otherwise)
  2. the data wrangling (and description in prose of why/how you are doing it)
  3. the statistical analyses (and also prose describing the correct interpretation as you might find in an academic paper)
  4. justifications for any assumptions that are made by the above statistical tests
  5. visualizations where useful and appropriate
  6. limitations to the analyses: both what we can and CANNOT tell on the basis of the existing report

(Note: First, everything needs to be self-contained in the .zip file. If I hit "run" on the Markdown file then everything should be generated dynamically. Any references to data, images, etc. need to be local so that the code runs no matter what machine it is executed from. Second, the term paper should be nicely formatted in a way that is both clear, easy to read, and that you can be proud of. This holds both for the source code as well as the resulting .html)

In order to submit, simply send me a message on Slack with the above!

Rubric

The term project will be evaluated based on clarity, correctness, reproducibility, and the degree to which they meet the above specifications.

The term project is officially due 12/22 (the final day of the semester), but I will grade submissions up to the point where I am required to submit grades to the registrar's office; this is usually a week or so after the end of the semester. If I have not received your term project by then, you will receive an "I" (incomplete) grade until you submit the term project.