This short book encapsulates everything that we used to cover in an in-person short course, the entire point of which was to collaboratively improve our ability to talk about, describe, and display data. We began the course as a deep-end-of-the-pool method of trying to take away some of the concern and fear that people have when it comes to writing about their Capstone data. Our goals are very simple:

  • remind ourselves about some of the vocabularly associated with data and data analysis,
  • review best-practices for how to describe data,
  • learn a few key techniques that should help you talk about your data when you write up your Capstone, and
  • impress upon you that good analysis equals good writing

The only requirements for this course are: a really good sense of humor, the ability to forgive me if I swear, a positive attitude, and access to Google Sheets.

Our course is organized around four key concepts that should help you feel better and more confident when it is your turn to write up your Capstone:

  1. Assessing your options for measuring how student achievement improves,
  2. Knowing that it is okay to not use heavy-duty stuff like t-tests.
  3. Choosing the best way to textually and graphically describe your data,
  4. Writing about your data and conclusions in an intellectually honest manner

Organization of the course

We do all of our work around three case studies of increasing complexity, and a final admonition. Each case study begins with list of vocabulary that you need be able to use correctly. Don’t laugh! The vocabulary can be the hardest part of what we are about to do with one another.

Following that, a review (or an introduction, if you are really rusty) of an idea related to the description and display of Capstone-style data.

From there, I pose a problem with realistic data and ask you to do the best job you can describing, summarizing and interpreting those data.

This is completely asynchronous: work at your own pace during the week. Many of you are still working and have other commitments. I encourage and expect you to work with one another.

All of your notes, exercises and resources are included in this book (or as links inside this book). The one external resource we have is a Discussion section for each of the four parts of our course.

My expectations

The original short-course was a 9-hour, in-person course that was heavily collaborative. This version of the course is going to swap all the deliberate collaboration with exhaustive iteration. I expect that our three case studies and final assignment will take you about 6 to 8 hours to work through, struggle with, and finally complete. For each case study you are then going to submit a short (no more than a half-page of text, as many figures as you want) data description and summary. I am going to mark it up, correct it, edit it and send it back to you. You then make corrections and we repeat the process until I am happy and you are happy. That iterative process is where the magic happens, and we don’t quit until you succeed!! You are welcome to work in groups and submit group assignments if you are lucky enough to be able to pull that off.


Not going to lie, this is the least interesting part of the course for me. As of the start you all have an “A.” You folks tend to be the sort that wants to generally be excellent at everything you do. I trust you will not turn in something that you are not proud of. Our iterative process means that we don’t quit fixing things until everyone involved is proud of the result.

I expect all of your iteratively-graded assignments to be complete by June 20. Please submit them to me via email, and I’ll respond using the same. I know that many of you are still finishing school or otherwise need some flexibility, so I will accept assignments all the way until June 26. However, I am going to be out of contact starting on June 22, so I will not be able to help you or provide commentary on your assignments (i.e., you get what you get).