Course Policies

Course Policies#

Communication#

Office Hours: Generally, answering questions about the assignments is much more efficient in person. As such, please ask questions about the assignments during office hours or class whenever possible.

Ed Discussion: We will primarily use Ed for discussion outside of class and office hours. I will also be using Ed to post announcements and other course updates. The system is highly catered to getting you help efficiently from classmates and the course staff. Rather than emailing, we encourage you to post your questions on Ed.

Gradescope: We will use Gradescope for all assignment submissions. For assignments that have a autograder, you will be able to see your score and feedback immediately, and there will be no submission limit. Thus, it is in your best interest to submit early and often!

Moodle: Moodle will only be lightly used in the course, primarily for grade book-keeping. Instead, look to the Ed Discussion board for announcements, Gradescope for assignment submissions, and to this course website for the content and assignments.

Grading#

Point transparency

Wherever possible, assignments will have their overall point value attached to them.

Worksheets: 30%#

These are guided assignments that are “lightly graded” – the bulk of the grade is based on good faith effort and completion. The worksheets are designed to help you practice material from class and prepare for the projects. There will be six worksheets over the course of the semester, worth 5% each.

Projects: 30%#

These are longer assignments that are an opportunity to explore and apply a foundational causal inference method to a real-world problem. We will have time in class for you to begin these projects and ask any clarifying questions. There will be three such projects:

  • Project 1: Randomized experiments

  • Project 2: Observational studies

  • Project 3: Instrumental variables

Final Project: 25%#

The final project will be an open-ended assignment that will allow you to explore a causal question you are interested in. I will also provide a list of potential datasets and project ideas as suggestions and starting points.

Participation: 15%#

As discussed in the Course Values page, participation is a key component of this course. Active participation includes:

  • Attending classes prepared.

  • Asking questions in class, office hours, and on Ed. All questions are good questions!

  • Answering questions. Your answers don’t have to be right!

  • Participating in class activities.

  • Completing feedback surveys, Over the course of the semester, I will check in to ask what is going well for you, what difficulties you are encountering, and what could be adjusted to improve your learning experience.

  • Respectful engagement with your peers and the course staff.

Attendance

Attendance is required for this course. However, I understand that unexpected situations may arise. If you are unable to attend a class, please let me know as soon as possible. Together, we can figure out a way to proceed.

Late Policy#

Worksheets: Because the worksheets are designed as jumping off points for class, I expect them to be completed on time. Thus there are no late days for worksheets. Again, they will be largely graded on good faith effort, so it is in your best interest to stay on top of them and submit every worksheet.

Projects: You will have 4 late days for the projects over the course of the semester. They may be used for any reason and you do not need to ask permission to use them, as I will track the number of late days being used as indicated in your submission. You can ask me at any point during the semester for the number of late days you have remaining. These late days may not be used for the final project. After these late days have expired, you will lose 10% of the assignment’s value for each day that it is late.

Extensions will be given in the event of extenuating circumstances, such as illness or an unexpected emergency. If this is the case, please reach out to me as soon as possible so we can work together on a plan and timeline for any make-up work.

Equipment#

Pencil/Pen: We will sometimes be doing pencil-and-paper exercises in class. You can use any pen or pencil you have.

Laptop: You will need a laptop for this course. We will be using Jupyter notebooks for all assignments as well as a centralized JupyterHub for the course, which is a cloud-based service for running Jupyter notebooks. If you don’t have a laptop, you may borrow one from LITS. If you have any issues here, please let me know.

Textbooks: There are no required textbooks for this course. However, there is an abundance of excellent causal inference textbooks freely available online. If you would like an additional reference in your causal inference journey, I’ve listed a few below, each coming from a different academic perspective – though all overlap heavily!

Academic Integrity and Collaboration#

In order to protect the integrity and value of our work together, we expect that all of your work in this class will comply with the MHC Honor Code:

MHC Honor Code

I will honor myself, my fellow students and Mount Holyoke College by acting responsibly, honestly and respectfully in both my words and deeds.

Collaboration#

Science and learning are collaborative endeavors, and I would like you to be able to work your peers. For problems and assignments that we work on in class, you will be working with your peers, and you can – for example – whiteboard your ideas or discuss the implications of a reading together. However, I expect that you and your collaborators contribute equally – you cannot just copy someone else’s work. Finally, everyone must write up their implementations and solutions individually.

Collaboration acknowledgements

Whenever you collaborate with your peers, you must acknowledge their contributions, and you also must briefly describe the nature of your collaboration in your write-up.

Large Language Models / Generative AI#

Large Language Model (LLM)-based assistants, like ChatGPT, Copilot, and Gemini are powerful tools that are having a profound impact across industry and society. These tools can assist in many aspects of programming such as through providing suggestions or even generating code snippets. However, one of the key shortcomings of these models is that they are prone to (often confidently) incorrect output. In order to use these technologies effectively, you must first have a strong conceptual foundation in order to identify and correct any mistakes they may make.

LLM use

Thus, to make sure the use of LLMs do not compromise your learning experience, you may not use them to generate code for assignments, solve problems, or summarize assigned readings, unless the assignment explicitly allows the use of LLMs.

I consider violations of any of the above policies to be honor code violations. If you find yourself for whatever reason (stress, mental health, life circumstances, etc.) thinking about violating these policies, please come talk to me before you do – I want to help you feel happy and proud of your learning and growth.

Accessibility#

We are committed to equal access for everyone in the course, regardless of ability. Please let us know if there is anything in the course content or presentation that is hindering your learning experience. Official accommodations for disabilities or disability-related needs are determined through the Disability Services Office. If you need accommodations through Disability Services, you have a right to have these met and kept confidential. You can request accommodations by filling out the Disability Services Application form on my.mtholyoke or by contacting Disability Services via email at disability-services@mtholyoke.edu. If you are eligible for academic accommodations, you will be provided with an accommodation letter. Once you receive your letter, please reach out to us to meet and discuss these accommodations.

Contents