Hello, dear friend, you can consult us at any time if you have any questions, add WeChat: daixieit

Syllabus: STAT 3032 Lecture Section 001, Spring 2024

4 credits (3 for lecture and 1 for lab)

Regression and Correlated Data

Course description:

Course Goals : By the end of this course, you will be able to

● Fit the appropriate regression models to datasets;

● Make statistical inferences based on the regression models;

● Use the programming language R for computing, analyzing, and visualizing data.

Prerequisites : STAT 3011 or STAT 3021. Please make sure that you are familiar with the following topics: random variable, probability, expectation (mean), variance, correlation, independence, conditional probability, central limit theorem, basic probability distributions (such as the Normal and t distribution), hypothesis testing, and confidence interval.

Course Canvas Site: https://canvas.umn.edu/courses/411059 We will only use the Canvas site of the Lecture Section 001. The Canvas site of Lab Sections 002 and 003 will not be used.

Additional Resources (Optional):

Textbook: Sheather, S. J. (2009). A Modern Approach to Regression with R. New York, NY: Springer.

- I have never used this textbook, but previous students have found it helpful.

-You can download a pdf of the textbook for free from the University of Minnesota Libraries with your UMN account.

- You can also order a “MyCopy SoftCover” copy for $39.99, according to the agreement between the University of Minnesota Libraries and the publisher (Springer).

Penn State Open Online Courses:

- These tend to be quite well designed and cover most of the material included in this course.

- The biggest downside is the 501 course doesn’t use R

- Its also good to note that the depth is often deeper than we need.

Linear and generalized linear regression - https://online.stat.psu.edu/stat501/

Time series - https://online.stat.psu.edu/stat510/

Course modality:

Lecture and lab sessions: This course is scheduled as an in-person course. All lecture and lab sessions are held in-person except if situational factors arise, such as personal illness of the instructor or TA, when the class may be held synchronously via Zoom or recorded for later viewing.

If you miss a lecture feel free to email me and I can provide relevant resources and discuss the content. I also recommend coming to office hours to discuss what you have missed.

Student/Office hours: The instructor and the TA will hold office hours either in person or through Zoom. I intend to hold three in person office hours each week. Many students like to come, stay, and just listen. This is encouraged in all office hours. If no students are there I may use the time to work or practice, if I look busy interrupt me, this time is for you.

Assignments: The concept quizzes and homework are assigned, administered and submitted on Canvas. Late submissions are accepted until the solutions are posted (generally 3 days after the due date), every day an assignment is late will be 10% off. The lowest concept quiz score and the lowest homework score are dropped. This is to cover situations when you cannot turn in your assignments on time because you are sick, your computer or internet breaks, too many tests, etc.. Use your assignment drop wisely.

Exams: There are three timed and closed-book exams that take place during the lecture sessions on .

● You are allowed one letter-sized (8.5 by 11 inches), double-sided cheat-sheet and a calculator.

● You are not allowed to seek help from other people during the exam. See details in the Academic Dishonesty section.

● Make-up policy for exams: A student may receive a make-up exam if they provide documentation that demonstrates that the circumstance is unforeseeable and unavoidable by a preponderance of the evidence. The instructor will make a decision on a case-by-case basis.

● We will use a platform called Gradescope to grade the exams and provide feedback. The university currently has a contract with Gradescope, so there is no cost to you. You don’t need to do anything about Gradescope until the grades of Exam1 are released.

Academic dishonesty:

If we discover that a student has taken unfair advantage or misrepresented someone else’s work as their own, the student will be assigned a penalty appropriate for the level of offense, which could be receiving a zero for the assignment or failing the course. If you have any questions regarding the expectations for a specific assignment or exam, ask.

Concept quizzes: No collaboration is allowed. However, after the quiz is due (typically on Thursdays), you may discuss the answers with other students.

Homework: You can talk to other students when you work on the homework. However, the final work (answer and code) must be written on your own. If you would like to form study groups with other students, you can use this sheet to organize groups Study Group Sign-up 001

Exams: If we discover that a student has taken unfair advantage or misrepresented someone else’s work as their own in this exam, the student will receive a score of 0 in this exam and be reported to the University. The student who assists another person in cheating will receive the same penalty. In especially egregious cases, the student may receive an F in the course.

Use of Chat GPT: The use of Chat GPT is overall discouraged but permitted for certain tasks. Acceptable use would include having it edit sentences and writing structure. Unacceptable use would be having it solve problems or write code. Use of Chat GPT in these unacceptable cases will be considered academic dishonesty. I would not even recommend it for editing sentences because we often teach specific statistical language in this course which Chat GPT is unlikely to follow, leading to you potentially losing points from its edits.

Instructional time and student efforts:

This is a 4-credit course (3 credits for the lecture section and 1 credit for the lab section), which means that you are expected to have 12 hours of course-related work. In each week, you are expected to spend

● 4 hours in synchronous or asynchronous lecture and lab sessions with the instructor and the TA.

● 4+ hours working on the assignments (quizzes and homework), reading the materials, visiting office hours, and reviewing for exams.

Communication:

Class-wide Announcements: Class-wide announcements are made in class or through the Announcement function in Canvas. Please make sure to set up the Canvas notification preference so that you receive it in your UMN email right away, when a class-wide announcement is made in Canvas. Here is the instruction to set Course Level Notification Preferences.

Email: You can send me or the TA emails through your UMN email or the Canvas Conversation (Inbox) function. Our goal is to respond to your email within 48 hours of receiving it (weekends excluded). Please include “STAT 3032” in the title.

● Last-minute emails: Please understand the TA and I may not see emails sent shortly before a due date. You are therefore encouraged to ask for help early enough to make sure we can respond (by 5pm the day its due should guarantee a response).

Assessment:

Grade Concerns: We try to maintain fair and consistent grading. If you see mistakes in grading, please bring them to us within a week of the release of the grades and we are happy to make corrections or adjustments.

Incompletes: We give out an “Incomplete” only if the following criteria are met

-The student has a documented case of hardship that prevents the completion of the course.

-The student has, up until the point of the request, been completing the coursework and exams.

-The student’s average grade in percentage at the point of the request is 70% or above.

Please talk to the instructor if you are considering requesting an “Incomplete”.

Programming:

This course involves some programming, as we will be performing data analysis in R.  R is a free, open-source, high-quality statistical software with millions of users worldwide. It is also a programming language. However, we won’t interact with R directly. Instead, we will access R through RStudio, a user-friendly interface for R.

Please download first R and then RStudio to your desktop or laptop. For installing R use https://cran.rstudio.com/ and for Rstudio https://www.rstudio.com/products/rstudio/download/ .

Discussion board (in Canvas)

If you email us with a question about the assignments or general course materials, we may answer it on the discussion board (without disclosing your name). Some of your classmates may have the same question and they will benefit from the Q&A.

You can also post a question on the discussion board. One of your classmates may just have the answer for it. Or you may be able to answer someone else’ questions!

We will be monitoring the discussion board every day, to review the posts, evaluate the responses, and provide revisions/corrections/suggestions.