Syllabus

Description

This course teaches the why and how of reproducible and collaborative research by combining questions of good computational practice in science, open science and statistical data analysis, in the context of today’s research environment.

Goals

By the end of the course, students will:

  • understand the issues regarding reproducible research in modern scientific practice, including the definitions of key concepts and the different challenges that exist across disciplines

  • understand the computational and statistical issues involved with reproducibility

  • be proficient at the Unix commandline

  • be proficient at version control with Git

  • be able to write documents in Markdown or LaTeX (including using pandoc)

  • be able to publish a research compendium with tools like MyST or Quarto

Prerequisites

  • Statistics 133, 134, 135

  • Graduate standing is required to register for Statistics 259.

  • Willingness to learn programming languages and software tools independently (tools used will include Unix command lines; git; GitHub; GitHub actions; LaTeX, Markdown, etc)

  • Willingness to learn some statistical methodology by reading on one’s own (materials and links will be provided, but not all topics required to do the homework will be covered in lecture).

Format and assessment

This is an in-person class with three one-hour lectures each week and one two-hour lab led by a GSI.

Lectures will focus on theory, philosophy of science, foundations of statistics, scientific applications, software engineering, code reviews and group discussion.

Lab will focus on computing, software tools, workflow, and collaboration; a short and easy checkpoint on that lab’s material will occur each session. You must attend the lab section you are officially enrolled in. If this presents significant burden, please reach out to your lab TA.

For each assigned reading, you will submit a couple of reflections due on Wednesdays at 10:00PM. During discussion lecture (on Fridays), we will draw upon your reflections for some group discussion.

Course Culture

Consistent class participation is crucial: we will be discussing subtle substantive, technical, and philosophical issues and reviewing code during class. If you cannot attend the lectures synchronously, please do not take the course.

You will be interacting with course staff and fellow students in several different environments: in class, in lab, over the discussion forum, and in office hours. Some of these will be in person, some of them will be online, but the same expectations hold: be kind, be respectful, be professional.

If you are concerned about classroom environment issues created by other students or course staff, please come talk to us about it.

Textbook

There is no textbook for this course. Instead, the learning materials rely on notes from previous semesters, as well as papers and other resources listed in the slides.

Waitlisted Students and Late Joining

If you are on the waiting list or have a pending application or added the course late, you must still do all coursework and complete labs and homework by the deadlines. We will not be offering extensions/exceptions if you are admitted/enrolled into the course later. So it is your responsibility to stay up to date on the assignments.

Unfortunately, doing all the work is not a guarantee of enrollment. You will only be enrolled if there is space in your lab. Enrollment will proceed by CalCentral.

Office hours

Me (the instructor) and the GSIs will offer office hours each week across a range of times. Because we are moving from Evans Hall to the Gateway Building, please give us some time to figure out the logistics of OH.

Grading Structure

Grades will be assigned using the following weighted components:

  1. 8% Reading Checkpoints (drop lowest score)
  2. 7% Reading Reflections (drop lowest score)
  3. 5% Discussion Polls (drop lowest score)
  4. 20% Homework (no drops)
  5. 10% Project 1 (no drop)
  6. 20% Project 2 (no drop)
  7. 30% Project 3 (no drop)
  • If you are taking the class pass-fail, the cut-off for passing is 70% (C-).
  • As a matter of course policy, I do not round up when calculating letter grades. Ex: if your overall score is 79.9999%, then the highest letter grade that you can expect is a C+, not a B-.
  • There is no curve; your grade will depend only on how well you do, and not on how well everyone else does.
  • We encourage you to focus on mastering the material, not on your grade. So please do not engage in grade grubbing.
  • Also, please remember that we grade your course performance, not your personal worth.

Reading Assignments

These will be posted on the course website under Readings. For each paper/reading in the weekly list, you will submit a couple of reflections and thoughts. You will submit your reading reflections in bCourses, due on Wednesdays at 10:00 PM.

In addition to the reflections, there will also be reading checkpoints. These will be a short set of questions about the assigned reading, and will take place during lab.

We will drop your lowest scores—for both the reflections and the checkpoints—in the calculation of your final grade.

Projects

There will be a few projects throughout the semester. You will combine all of the tools and techniques learned as we move along the term.

Because projects are the “meat and potatos” of this course, we will not drop any project scores.

Late Policy and HW Assignment Extensions

If you cannot turn in a HW assignment on time, our default policy is:

  • Submissions within 24 hours after the deadline will receive a 15% deduction.
  • Submissions within 48 hours after the deadline will receive a 30% deduction.
  • Submissions that are 48 hours or more after the deadline will receive no credit.

Please plan ahead and pace yourself. Don’t wait until the last day to do an assignment. Don’t wait until the last minute to submit your assignments.

AI Tools policy

We strongly encourage you to focus on independent learning and original problem-solving. At the same time, we recognize that generative AI tools are an increasingly standard part of modern workflows. We are not banning AI tools in this course, as doing so is neither realistic nor desirable.

This course is designed to help you build fundamental skills, judgment, and deep understanding—outcomes AI cannot achieve for you. Our main goal is to foster transparency and genuine engagement with the material, aligning with the core philosophy of STAT 159/259.

Core Expectations

  • Do the thinking yourself. Use AI to support your learning, not replace it. If a tool handles the core reasoning, drafting, or problem-solving while you merely copy and submit the output, you are missing out on learning the material.

  • Disclose your usage. If you use AI tools on an assignment—whether for brainstorming, debugging code, editing text, checking work, or drafting—you must state so explicitly. A short note on your assignment is sufficient: include the tool and version used (e.g., Claude 3.5 Sonnet, ChatGPT-4o), what you used it for, the primary prompts used, and where it was applied.

Why this matters: Transparency aligns directly with the collaborative and reproducible data science practices central to this course. Openly documenting how work was produced ensures your workflow can be evaluated and built upon by others.

  • Understand everything you submit. You are fully accountable for all submitted work. If you include AI-generated code, text, or figures, you must be able to explain, defend, and walk through them as if you created them entirely yourself. If you cannot explain a line of code or a specific claim, do not submit it.

  • Violations of the course AI policy:

    • Undisclosed AI Use: Submitting AI-assisted or AI-generated work without clear disclosure.
    • Lack of Comprehension: Submitting AI-generated work that you cannot explain, defend, or demonstrate understanding of when asked.

The ultimate objective of this course isn’t just to produce correct answers; it is to build critical thinking, master modern tools, and communicate complex ideas clearly. Using AI responsibly and transparently is part of developing those professional skills.

Code of Conduct; attribution of work

The high academic standard at the University of California, Berkeley, is reflected in each degree awarded. Every student is expected to maintain this high standard by ensuring that all academic work reflects unique ideas or properly attributes the ideas to the original sources.

These are some basic expectations of students with regards to academic integrity: Any work submitted should be your own individual thoughts, and should not have been submitted for credit in another course unless you have prior written permission to re-use it in this course from this instructor.

All assignments must use “proper attribution,” meaning that you have identified the original source and extent or words or ideas that you reproduce or use in your assignment. This includes drafts and homework assignments! If you are unclear about expectations, ask your instructor.

Do not collaborate or work with other students on assignments or projects unless the instructor gives you permission or instruction to do so.

Disability Accommodations

If you need an accommodation for a disability, or if you have information you wish to share with the instructor about a medical emergency, please inform the instructor as soon as possible.

If you are not currently listed with DSP (the Disabled Students’ Program) and believe you might benefit from their support, please apply online at https://dsp.berkeley.edu.