Final Course Survey

Thanks so much for your participation in Probability for Scientists. As instructors, we enjoyed this class and learned a lot from teaching it. Please help us improve by answering the following anonymous survey.

The final survey is available here. You have a week to complete it.

Administrative notes

  • Due to low interest, Drew will *not* be available this Thurs 12 Dec.
  • We will be emailing you feedback on your written report. Please email the class website if you would like to arrange to pick up the physical copy.

Final Project Posters

Posters from the final project are now available as pdfs here. In the event that you have any updates, email a new pdf to the class address and we will post them.


Final Project Details

The final poster session will be on Thursday, the 5th of December. Feel free to invite friends/family to this class.

Key points to keep in mind as you work on the written projects:

  • The written report is *separate* from your poster. We strongly encourage you to complete your written reports early so you have ample time to focus on your poster.
  • Mark corresponding author, include email address.

  • Your report should be between 500 and 1,000 words total (including captions). Use simple, declarative statements - avoid "flowery" language like "we intend to", "we hope to", "it might be the case that", etc.

  • When there are multiple authors, use "We" rather than "I".

  • Aim for 3-5 final figures. Each figure should be numbered, have sensible axis labels w/units, and a 2-3 sentence caption.

  • Always spell check.

  • Bibliography: you can use any accepted style. An online tool like this can be helpful.

Poster details:
  • We will be printing posters for you. Thus, we need a final version by 5pm Tues 3 Dec.
  • To submit your poster, export your finished poster from Powerpoint as a pdf and email it to the class address.
  • I strongly suggest that each group reads this post about poster design. It includes several templates that you can use to start your poster. The final poster size should be 36" wide by 24" tall.


Week 13: Working with Rstudio and Data

For class this Thursday, each group should have a laptop with Rstudio installed, and a dataset that's ready to be imported.


  • First, you need to install R from here.
  • Next, install Rstudio from here.
  • There's very good documentation on Rstudio here. Learning a few shortcuts and understanding syntax highlighting can make your life much easier.

Importing Data

  • First, make sure you can open your data in a spreadsheet program like Excel or OpenOffice.
  • If there are multiple tables or "sheets", identify the most important ones, and think about how you might combine several tables together into a single table.
  • From your spreadsheet program, select "Save as" and save the spreadsheet as a CSV (comma-separated value) file.
  • Finally, load the CSV file using Rstudio ( nice instructions here).

For class, please download this R script and data file to the same directory.


The Monty Hall Problem

There are several different valid specifications of the Monty Hall problem. All use Bayes' theorem to incorporate the initial choice of the contestant and the information that the host "gives away" to reach the same conclusion.

This link provides a concise explanation of the set-up and the math.

The Wikipedia article for the problem is long, but contains a very good introduction, as well as some interesting history on the problem, and a detailed list of solutions.

Finally, there's a New York Times interview with Monty Hall himself here that describes some of the intricacies of the actual game show.

Annotated Outline Instructions

The annotated outline (Due Thurs 14 Nov) is an expanded version of your proposal, and will form the outline of your poster. This should be typed, and written to address a non-technical audience (can a high school senior understand it?). As noted in class, probability and statistics Wikipedia pages will be considered valid sources for this project.

The format for the annotated outline is as follows:

  • Introduction (200 words max, at least 2 sources)
    • Background of the research system
    • Problem statement
    • Significance of problem
  • Methods (200 words max, at least 2 sources)
    • Describe data, including source, number of samples, variables, whether data collection is complete.
    • Analysis: What will you do to answer the question, and how did you choose these methods? How will you interpret the results? Describe any (nontrivial) assumptions you'll be making.
  • Discussion (200 words max)
    • Expected outcome and reasoning.
    • Significance of results.

Proposal Feedback and Revisions

We've reviewed all of your final projects and provided feedback.
We need a few things from you:

  • Please choose one corresponding author per group. We will email feedback to the corresponding author ASAP.
  • For Tuesday 12 November, please revise your proposals, taking our comments into account.

Revised proposals should be typed, and addressed to a non-technical audience (would a high school senior understand it without further explanation?). When revising your proposals, please use the following format:

  • Title
  • List of authors (mark corresponding author and provide preferred email)
  • Proposal text. Text should be less than 200 words. It should explain the research question and significance. Briefly describe the data that will be used, and whether it has been collected already. Describe the methods you will use, and how they answer the research question. Finally, include a brief description of your expected results and their practical significance.