Syllabus

About the Course

Instructor

  • Randi Garcia (rgarcia@smith.edu). Bass Hall 412. Randi’s office hours will be held on Tuesdays 10:30a-11:30a, Fridays 3:00p-4:00p, or by appointment.

Description and Goals

This course provides students with an overview of statistical methods needed for scientific research. Our discussions will focus primarily on the basic principles of the design of experiments and observational studies, standard balanced designs, extensions of these designs, and the analysis of data collected under these designs. Most physical, biological, and social processes, produce variable results. This variability can often be quantified and decomposed in ways that enhance our understanding of the process and facilitate decision making. Statisticians and data scientists use four steps to quantify and interpret this variability. The steps are:

  1. Formulate a statistical question about the process,
  2. Design a data collection procedure, or comparison scheme, to answer the question,
  3. Collect and analyze the data, and
  4. Interpret and communicate the results in written, visual, and oral forms.

One major objective of this course is to give you practice with all four of these steps. Developing our statistical thinking around the factors that produce variability in observations is a key goal of all statistic courses. SDS 290 course learning goals:

  1. Distinguish between observational and experimental studies and factors. Explain the advantages and disadvantages of each.
  2. Explain the three design principles: random assignment, blocking, factorial crossing.
  3. Identify the factor structures of the four basic experimental designs: 1) One-way Basic Factorial, 2) One-way Complete Block, 3) Two-way Basic Factorial, and 4) Split Plot/Repeated Measures.
  4. Recognize potential sources of confounding and selection bias.
  5. Combine the four basic designs to recommend, recognize, and create new designs.
  6. Carry out, document, and explain a randomization plan for a survey or an experiment.
  7. Analyze data using R statistical software:
    1. Name and be able to check the six Fisher Assumptions.
    2. Calculate and interpret an analysis of variance (ANOVA) table for each of the four basic designs.
    3. Check for and interpret interactions between variables.

Prerequisite: An introductory statistics such as SDS 220/201, ECO 220, or equivalent.

Readings

  • STAT2: Modeling with Regression and ANOVA, Second Edition by Ann R. Cannon, George W. Cobb, and Bradley A. Hartlaub. ISBN-13: 978-1319054076.
  • [PDFs provided on moodle] Introduction to Design and Analysis of Experiments, by George Cobb. Hardcover edition published by John Wiley & Sons, 1998, ISBN: 978-0-470-41216-9.

The first few chapters of the Cobb book are provided as PDFs on our course Moodle page. We will mostly be using the Stat2 book but will supplement with the Cobb book. It is very important that you read the textbook before every class—time in class will be devoted to jumping right into using the ideas presented in the text. The textbook is full of great examples of real statistical studies.

Class Structure

All class sessions will be focused on active learning activities and there will be less lecturing. We will spend class time discussing your questions, looking at other examples, doing homework problems, and doing activities. With this semi-flipped class structure, it is VERY important that you do the assigned readings before coming to class. To this end, I will be starting most class sessions with questions about the readings to encourage you to keep up with the reading and to synthesize your thoughts before we begin class. On some class sessions, I will be giving mini-lectures, but they will often be focused statistical computing in R. Many activities will be designed to give you experience using statistical software to do the extensive computations most statistical analyses require. The computer is faster and more accurate than we are at doing arithmetic and graphs, but we have to know what arithmetic and which graphs will be useful.

The primary way you will get information about this course is from the course website. The course website will be regularly updated with handouts, project information, assignments, and other course resources. All assignments will be submitted via Gradescope or Moodle. Finally, this course will use Slack to communicate including announcements, discussions about extra credit events, group project channels, and other uses as the semester progresses.

Policies

Attendance

Participation has two components: 1) being present and 2) engaging in class activities. Your participation is an important part of the process of learning statistics, and we need you in class to help stimulate discussion. You can make a valuable contribution to the discussion by bringing up connections between our work and study designs you have seen in other courses, in the newspaper, or in research literature. I realize that you won’t always be able to get to class and I ask that if you cannot make it to class that you please let me know why via a Slack direct message. An “A” attendance record assumes that you miss no more than four classes during the semester.

Collaboration and Academic Honor Code

Much of this course will operate on a collaborative basis, and you are expected and encouraged to work together with a partner or in small groups to study, complete homework assignments, and prepare for exams. However, every word that you write must be your own. Copying and pasting sentences, paragraphs, or blocks of code from another student is not acceptable and will receive no credit. No interaction with anyone but the instructor and course assistant is allowed on any exams. All students, staff and faculty are bound by the Smith College Honor Code, which Smith has had since 1944.

You must always provide appropriate citations for others’ work and ideas. Giving other scholars due credit in your written and oral communication is a fundamental social gesture in academic work—a way for us to acknowledge each other’s scholarship and signify that we respect each other. We’ll treat AI code-completion tools as “collaborators” in this class. Whenever you get help with your programming tasks or writing, it is crucial to provide clear and transparent attribution. Include a comment or annotation in your code and add citations in your text specifying that certain sections were generated with the help of an AI code-completion tool. In general, aside from use to create study materials, I prefer you to do the work on your own without the aid of generative AI tools.

Cases of dishonesty, plagiarism, or other infractions, will be reported to the Academic Honor Board. You must always provide appropriate citations for others’ work and ideas. Giving other scholars due credit in your written and oral communication is a fundamental social gesture in academic work—a way for us to acknowledge each other’s scholarship and signify that we respect each other.

From the Smith honor code website:

Smith College expects all students to be honest and committed to the principles of academic and intellectual integrity in their preparation and submission of course work and examinations. Students and faculty at Smith are part of an academic community defined by its commitment to scholarship, which depends on scrupulous and attentive acknowledgement of all sources of information, and honest and respectful use of college resources.

Cases of dishonesty, plagiarism, etc., will be reported to the Academic Honor Board.

Classroom Environment

Realizing the benefits of a diverse space can only occur if we create a climate of psychological safety (Edmondson, 1999). To this end, we will always be respectful of one another. Together we should have the goal of creating an environment where we all feel comfortable sharing our thoughts and opinions. To this end, I value “half-formed,” informal thoughts—sometimes a deeper understanding is reached via communicating ideas before they are perfectly polished.

Accommodations

Everyone should have all that they need to succeed in this course. Please send me your accommodation letter, or have the Accessibility Resource Center (ARC) work with me. If you need to register for accommodations, please contact the ARC at arc@smith.edu. Please check out the center website for more information.

If you have special needs concerning quiz and exam taking, please bring documentation of your needs and make an appointment to discuss them with me, at least ONE WEEK BEFORE the first exam. That will give me time to provide accommodation for your needs.

Assignments

  1. Homework [40%]: Weekly homework will be due on Fridays by 11:55p on Gradescope. Late homework will NOT be accepted except in cases of a family or personal health emergency. Each student will granted 2 no-questions-asked extensions on homework assignments. You must Slack message me before the deadline, during working hours (9a-5p), to request use of an extension. Homework will be a combination of problems sets from the book and statistical computation exercises in R. I recommend that you form study groups of 3 or 4 students from the class, and get together outside of class to discuss the homework. Each of you should try the exercises on your own and then get together to discuss your work. This process helps you to develop your own way of thinking about statistics questions before hearing how others think. I will be dropping the lowest TWO homework grades at the end of the term.

  2. Participation [10%]: Active participation in class and regular attendance will comprise 10% of your grade. Most class periods will begin with questions from the reading for that day and all class periods will end with completion of an “exit ticket.” Participating in the discussion about the readings is a great way to demonstrate engagement. Reading before class will help us move towards a “flipped” classroom. In non-flipped classrooms, students attend lectures and are asked to apply the material outside of class in the form of homework assignments. But often students need the most help from professors when they are in the midst of applying the material (Bergman & Sams, 2012). In flipped classrooms, students are asked to learn the facts at home and do the application in class. There will be many ways to demonstrate engagement throughout the term. At the end of the term you will also be completing a self-assessment of your attendance and participation.

  3. Exams [20%]: There will be two closed-book, self-scheduled exams throughout the term. See the schedule for tentative dates of these exams.

  4. Mini Projects and Presentations [30% split as 10% MP1 + 20% MP2]: There will two mini projects during the semester. The first mini project (MP1) will be completed individually and the second mini project (MP2) will be completed in groups of about three. For these projects, you and your group will be posing your own research questions and designing an experiment. The specific content of your mini projects will vary, but all projects will consist of designing an experiment (or appropriate observational study), collecting and analyzing data, and writing a technical report on your study. For MP2 each group of three students will complete an experiment together. During the last week of class, you (and your group) will create short presentation of your study and record it (or present it live to the class, time permitting). We’ll talk more about the project as the term proceeds and detailed instructions for the projects will be posted on the course website. A self-assessment will accompany the first mini project and a self- and peer-assessment will accompany the second mini project.

Summary

Assignment Percent of Total Due Date
Homework 40% Fridays
Participation 10% Daily
Exams 20% Oct 23 and Dec 4
Mini Project 1 10% Nov 1
Mini Project 2 20% Dec 18
Final Grade 100%

Grading

When we grade your written work, I am looking for problem solutions that are technically correct and reasoning that is clearly explained. Numerically correct answers, alone, are not sufficient on homework or exams. I value neatness and brief, clear, well-organized answers that explain your thinking. If the grader cannot read or follow your work, she cannot give you credit for it. The grader will check each homework submission for completeness and grade a subset of the exercises. Homework answer keys will be posted on Moodle after the due date. When submitting your homework on Gradescope, you must tag specific pages of your submission for each problem solution. If you fail to do this, we will doc 2 out of 10 points from your total assignment grade.

Assignment Late Policy

Each student will granted 2 no-questions-asked extensions on homework assignments. You must Slack message me before the deadline, during working hours (9a-5p), to request use of an extension. In addition to these two planned extensions, you may submit one assignment (except for mini project 2) up to 3 days late, without needing to check in with me first.

Final Grade Brackets

Grade Percent
A 95-100%
A- 90-95%
B+ 87-89%
B 83-86%
B- 80-82%
C+ 77-79%
C 73-76%
C- 70-72%
D+ 60-66%
D 67-69%
E 59% and below

Resources

Course Website and Moodle

The course website will be regularly updated with lecture slides, project information, assignments, and other course resources. Assignments and grades will be submitted via Moodle and Gradescope. You should check both regularly and let me know immediately if the grades do not match across Gardescope and Moodle.

Computing

The use of the R statistical computing environment with the RStudio interface is thoroughly integrated into the course. Both R and RStudio are free and open-source, and are installed on most computer labs on campus. See the SDS 100 lab 1 if you need a refresher on installing R and/or you want to update your system.

Use of Technology during Class

As we will always be using our computers to attend this course, I hope it goes without saying that while the class is in session, you should resist the temptation to use your computer or cell phone for personal email, web browsing, social media, or any activity that’s not related to the class.

Writing

Your ability to communicate results, which may be technical in nature, to your audience, which is likely to be non-technical, is critical to your success as a data analyst. The assignments in this class will place an emphasis on the clarity of your writing.

Extra Help

There are Statistics TAs available from 7:00-9:00pm on Sunday–Thursday evenings in Sabin-Reed 301. In addition, the Spinelli Center for Quantitative Learning supports students doing quantitative work across the curriculum. Your fellow students are also an excellent source for explanations, tips, etc.

Tentative Schedule

Please refer to the complete day-to-day schedule for more detailed information.