DASC 240 (Applied Regression Analysis) Syllabus

DASC 240 (Applied Regression Analysis) Syllabus

About the Course

Instructor

Dr. Amelia McNamara (she/her), amelia.mcnamara@stthomas.edu

Office hours/student hours: Mondays 11 am - noon in person (OSS 407) or via Zoom, Fridays 2-3 pm on Zoom only, and by appointment. Links available in the first Module of the course.

Course format

This course is scheduled as live and in person. I am not providing a Zoom option this semester.

Covid-19 circumstances: At St Thomas, we are committed to a culture of care for all. If you are spending time on campus, you are expected to abide by the campus preparedness plan. I will be continuing to mask in our classroom, and would appreciate if you did the same. However, masks are no longer required on campus.

If anything changes regarding the format of the course, I’ll keep you informed through course announcements.

Class meetings

  • Section D01: 9:55-11:35 am, OSS 432
  • Section D02: 1:30-3:10 pm, OSS 432

Course Description

This course provides students with the knowledge to effectively use various forms of regression models to address problems in a variety of fields. Students learn both simple and multiple forms of linear, ordinal, nominal, and beta regression models. There is an emphasis on simultaneous inference, model selection and validation, detecting collinearity and autocorrelation, and remedial measures for model violations. Students are also introduced to the use of time series and forecasting methods.

Prerequisites:

Prerequisites: Grades C- or higher in DASC 112, DASC 120, STAT 303, or STAT 314.

Course Goals

  • Gain a basic understanding of regression models, including the assumptions they make and when to use them.
  • Learn to apply regression models to data sets using R.
  • Describe and interpret regression output, including real-world implications of models.

Textbooks

There is no required textbook. Every week there will be readings provided from a variety of texts, including:

and more

Policies and Expectations

Inclusive classroom

Because data is collected by and about humans, it always encodes our viewpoints and biases. As a result, this course will likely touch upon difficult topics related to race, gender, inequality, class, and oppression.

We each come into this class with different perspectives that can be shared to enhance our understanding of these issues. I ask that you enter these conversations with respect, curiosity, and cultural humility. You should be open to alternative perspectives and willing to revise beliefs that are based on misinformation. As a general rule, your ideas and experiences can always be shared during these conversation but refrain from dismissing the experiences of others.

Please plan to treat me and your classmates with respect. To me, respect includes using peoples’ pronouns and preferred name (both for me and for your classmates), arriving at class on time or coming in quietly if you are late, and focusing on the task at hand. Of course, personal attacks of any kind will not be tolerated.

Stressor Statement

The course content may elicit strong reactions from some students, and it is understandable that some may feel uncomfortable discussing these issues in class. Please take the time to care for yourself. If you are struggling with personal issues, or find the content of course overwhelming, please seek assistance at the Center for Wellbeing or by calling (651) 962-6750. Full-time students are eligible for health services including individual counseling sessions.

I also encourage you to speak with me. You do not need to share why a topic may be overwhelming, but by alerting me that you may not be able to participate during particular discussions, we may be able to find a way to avoid those topics, or can then work together to find alternate ways for you to share your ideas instead of verbally expressing them in class.

Bias Reporting

St. Thomas is committed to providing an inclusive living, learning and working environment that supports the well-being of each member and respects the dignity of each person. Incidents of hate and bias are inconsistent with the St. Thomas mission and convictions and have no place here. If you are a student who has experienced or witnessed a bias or hate incident, we want to address the incident and provide you with resources. Go to the Bias or Hate Reporting website to get more information and to make an online report.

Sexual Harassment and Title IX Reporting

The University of St. Thomas mission and convictions embody our commitment to promote and protect the personal dignity and well-being of every member of the St. Thomas community. Sexual harassment, sexual assault and other forms of sexual misconduct are antithetical to the commitment, and they constitute unlawful sex discrimination. All forms of sexual misconduct are prohibited by St. Thomas.

I am a responsible employee when it comes to reporting sexual violence. That means I am required to report certain incidents to the Title IX Coordinator. Our school cares about the safety of our students and has created this requirement because sexual violence, in all its forms, is unacceptable, and we’re committed to holding perpetrators accountable and keeping survivors safe. Your privacy is of utmost importance and this institution will do everything possible to keep all reports private and only share with those who need to know. You will never be forced to share information and your level of involvement will be your choice.

For more information, please go to the St Thomas Title IX website.

Financial Hardship

Hungry? Groceries Out of Reach? Food and housing insecurity is a hidden, yet common, issue among college students. If you have difficulty affording groceries or accessing sufficient food to eat every day, or if you lack a safe and stable place to live, and if you believe this may affect your performance in this course, you are urged to contact the Dean of Students Office for support (2x6050 or deanstudents@stthomas.edu) You are probably not alone. You may also access food assistance through the Tommie Shelf Food Mobile: https://www.stthomas.edu/center- for-common-good/volunteer-opportunities/foodjusticetommieshelf/. If you feel comfortable doing so, please notify me so that I may connect you to other resources: https://www.stthomas.edu/deanofstudents/foodinsecurity/.

Disability Statement

Academic accommodations will be provided for qualified students with documented disabilities including but not limited to mental health diagnoses, learning disabilities, Attention Deficit Disorder, Autism, chronic medical conditions, visual, mobility, and hearing disabilities. Students are invited to contact the Disability Resources office about accommodations early in the semester. Appointments can be made by calling 651-962-6315 or in person in Murray Herrick, room 110. For further information, you can locate the Disability Resources office on the web at https://www.stthomas.edu/student-life/resources/disability/.

Collaboration and generative AI

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. It is okay to use generative AI (such as ChatGPT) to help you understand concepts, debug code, and clean up written work.

However, I expect all work submitted to be substantively yours. This means that copying and pasting large blocks of code or major textual elements from another student, internet websites, or generative AI systems, is not acceptable. If I suspect work you submitted is not substantively yours, I may ask you to come in and discuss the work with me. If you cannot explain how you arrived at the solution, and restate the communication in your words, you will receive no credit. All students are bound by the Undergraduate Student Academic Integrity Policy. Cases of dishonesty, plagiarism, etc., will be reported to the dean.

Attendance

Attendance is recommended, but not required. You are an adult and make your own priorities. If you are not in class, I will assume you understand the material that was covered. In a case where you may need an extended absence and feel it will impact your learning (e.g. an illness, death in the family, conference, etc), please let me know so we can find a way for you to make up the material.

Grading

Your course grade is determined by:

  1. Weekly work [Total 45%]

    • Reading [5%]: Each week, you will read the assigned reading and annotate Perusall as you go. There are several ways to earn full credit on Perusall, including high quality comments, making lots of comments, answering questions, upvoting, and more.
    • Problem sets [30%]: There will be regular problem sets over the course of the semester. Problem sets will involve computational assignments in R with written explanations. You must complete all of your homework assignments in Quarto and submit electronically via GradeScope. 25% credit will be given for completion, 75% for correctness.
    • Participation [10%]: Active and timely participation in class activities is expected. While attendance is not required, regular absences may be noted into this category.

  2. Exams [20%]: There will be two timed exams in this course. Opportunity will be given to perform exam corrections to make up points missed during the exam.

  3. Final project [Total: 35%]

    • Technical report [30%]: You will work on a term project in a small group over the course of the semester. This is an opportunity for you to demonstrate your understanding of the material and put it into practice. The main output of your work will be a technical report, which we will work on in stages. Grades on the final project will be weighted by your participation in the project.
    • Project reflection [5%]: The second component of the term project is a reflection on the work you did in your technical report. This reflection will be done individually, during a timed synchronous session. You may review your report as you work, but no other resources are allowed. One component of the reflection will be explaining how work was split throughout the team.

When grading your written work, I am looking for solutions that are technically correct and reasoning that is clearly explained. The explanation and context of an answer are the most important components. Numerically correct answers, alone, are not sufficient on homework or tests. Neatness and organization are valued, with brief, clear answers that explain your thinking. If I cannot read or follow your work, I cannot give you full credit for it.

Late work

In general, I am very lenient with extensions (particularly during covid), however some elements of this course are time-specific. For example, because we will be building collaborative keys in class most Tuesdays, I can’t give you full credit for problem sets turned in after that class. Please let me know if you are having trouble meeting deadlines, as I may be able to move things for the entire course if that makes sense.

Grade return policy

I strive to return work to you within a week of the submission deadline, or no more than two weeks later. Work submitted past a deadline may have a longer turnaround time.

Computing

The use of the R statistical computing environment with the RStudio interface is thoroughly integrated into the course.

In this course, we will be using the desktop version of RStudio. RStudio ia already installed on the lab computers in our classroom, and in the library, but you will likely want to have access to it when you are not on campus. I recommend installing the software (all free) on your own computer. This requires a few steps:

  • installing R, the programming language
  • installing RStudio Desktop
  • installing some R packages

Using the desktop version means you are only limited by the speed and memory of your machine, and you can work offline. It also means that your files live right on your computer, and especially in this pandemic, you probably have the most access to them there! If you regularly use more than one computer (such as the computer in the lab, and your laptop at home), you may wish to use a version control package like git/GitHub, or keep your work in a OneDrive folder in order to have access to your files wherever you go.

There is a cloud option for RStudio, but it now costs money so I am no longer suggesting it for this class. However, if you have a computer that is incompatible with the desktop version of RStudio for some reason (Chromebook or other computer where you cannot install software, very old operating system, lack of hard drive space, etc) we can talk about how to use the cloud version.

Writing

This class has been designated as a Writing in the Disciplines (WID) course in the Writing Across the Curriculum program at UST. As such, a substantial portion of the semester will be devoted to producing a final project, the main outcome of which will be a technical report. You will select a topic, find and synthesize relevant data, perform a regression analysis, and describe the results you have found. Your ability to communicate technical results is critical to your success as a data analyst. Assignments in this class will place an emphasis on the clarity of your writing, to help you develop and refine this skill.

Tentative Schedule

The following is a brief outline of the course, which is subject to change. Please refer to the course modules for more detailed information, and the Academic Calendar for important enrollment dates.

Week Topic Writing
1: 9/2-9/6 Introduction to the course, intro to modeling
2: 9/9-9/13 Review of intro stat, exploratory data analysis.
3: 9/16-9/20 Beginning simple linear regression Interpreting simple linear regression coefficients
4: 9/23-9/27 More simple linear regression. Statistical question generation, part I
5: 9/30-10/4 Multiple Linear Regression. Statistical question generation, part II
6: 10/7-10/11 Second-order models. Interaction terms and polynomials. Multicolinearity. Initial project proposal
7: 10/14-10/18 Randomization & the bootstrap as methods of inference, Exam review
8: 10/21-10/25 Exam 1, Intro to logistic regression.
9: 10/28-11/1 More logistic regression. Feedback and discussion on initial project proposals
10: 11/4-11/8 Election day, finishing logistic regression
11: 11/11-11/15 Multiple logistic regression Interpreting logistic regression coefficients
12: 11/18-11/22 Advanced logistic regression topics Revised project proposal
13: 11/25-11/29 Time series analysis, Thanksgiving
14: 12/2-12/6 TBD, Exam review First draft and peer review
15: 12/9-12/13 Exam 2, work time
Project reflection Final project

Final exam periods for this course are as follows:

  • Section D01 (9:55 am): Thursday, December 19, 10:30 a.m. - 12:30 p.m.
  • Section D02 (1:30 pm): Tuesday, December 17, 1:30 p.m. - 3:30 p.m.