Textbook

Stat2: Modeling with Regression and ANOVA (2019), A. R. Cannon, G. W. Cobb, B. A. Hartlaub, J. M. Legler, R. H. Lock, T. L. Moore, A. J. Rossman, J. A. Witmer, W. H. Freeman and Company.

Learning Goals

• Improve technical communication skills
• Introduce RStudio statistical software
• Develop statistical computing skills
• Foster productive work habits with peers, including joint presentations and assignments
• Build an understanding of statistical models, including methods for choosing, fitting, assessing, and using those models

Statistical Packages & Computing

R and RStudio will be used extensively throughout the course. Assignments and course announcements will be sent to you via e-mail or posted on the course web page. Data sets and programs will be placed in our Google Drive folder Stat206-DataAnalysis-F2023. Proper maintenance of computer accounts, files, etc. is your responsibility.

Our class meets in a classroom where you will be expected to use your laptop, and we will be using statistical software extensively in the course. During regular class hours, the use of the computers is restricted to activities deemed appropriate by the instructor. Playing computer games, reading e-mail, conversing in a chat room, surfing the web, and working on assignments for other courses are a few examples of inappropriate activities that can be distracting to other students in the course and the instructor. Inappropriate computer use may result in penalties ranging from warnings to loss of computer privileges for the period. In cases of extreme and/or repeated violations, grade penalties or expulsion from the course may result.

R scripts and class examples

Sample R scripts will be demonstrated and discussed during class. These R scripts and data sets will be provided in the Google Drive folder !Class Material. Other data sets, especially those discussed on the power point slides, will be provided in the Google Drive folder !ClassData.

Power Point Slides

Power point slides will be provided for every section in the textbook. These slides are provided in the Google Drive folder !2ePowerPoint. You are encouraged to read these power point slides along with the appopriate sections in the text before our class discussions. My hope is that we can use our class time to answer your questions about the material.

R Markdown files

R Markdown files are provided for every section of our textbook so that you can see exactly how we used R to fit, assess, or use models and output presented in your reading assignments. We will not discuss every command in these files during our class periods, but I will definitely allow time for any questions you have about these important files that will be helpful for your learning and understanding of new statistical methods and models.

Data from our textbook

Every data set from our textbook is provided for you in the Google Drive folder 2eStat2Datasets. However, I strongly encourage you to install the Stat2Data package in RStudio on your computer. This will allow much easier access and complete descriptions of all variables.

Accessibility Accomodations

A student who thinks they may need an accommodation to access a campus program, activity, or service should contact Ruthann Daniel Harteis in Student Accessibility and Support Services (SASS) at danielharteis1@kenyon.edu  to discuss specific needs. Advance notice is required to review documentation, evaluate accommodation requests and provide notice or arrangements for any accommodation.

Title IX Responsibilities

As a member of the Kenyon College faculty, I am concerned about the well-being and development of students, and am available to discuss any concerns. However, I want you to know that faculty members are legally obligated to share certain information with the College’s Civil Rights & Title IX Coordinator. This requirement is to ensure your safety and welfare is being addressed. These disclosures include, but are not limited to: reports of discrimination or harassment due to a protected characteristic, including sexual harassment, sexual assault, relational/domestic violence, and stalking.

Homework

Homework assignments will be given throughout the semester. I encourage you to work on as many problems as possible, including problems which have not been assigned. Subsets of the homework assignments will be collected and graded. Your solutions must be submitted electronically to your Google Drive folder. You must submit a PDF of your solutions using a very specific naming structure. For example, the name of the file for the first homework assignment should be HW1-yourname.PDF. Working with other students is encouraged, but each student must submit her/his own solution for problems to be collected. For more infomation, see the departmental guidelines for collaboration on homework, which I expect you to follow.

Homework is due at the start of class on the assigned due date, unless specified otherwise. Each student will be allowed two "free" 48-hour extensions on homework assignments; no reason needs to be provided. Simply email me in advance of the due date to say that you would like to use one of your two extensions. After the second extension, late homework will not be accepted. However, your lowest homework score will be dropped at the end of the semester.

The grading rubric for all HW exercises is:

Complete (10/10)

• Contains no non-trivial errors and clearly communicates understanding
• Achieves a correct solution
• Justifies decision(s) toward solution
• Effectively communicates solution and support
• Notation used is appropriate and clearly shows all steps

Substantial (9/10)

• Meets expectations and contains an easily correctable mistake
• Makes correct decision(s) toward solution
• Justifies decision(s) toward solution
• Effectively communicates solution and support
• A slight error, confused reasoning, or notational mistake
• Refinement is needed

Developing (8/10)

• Contains correct work and a serious error in understanding or communication
• Makes some correct decision(s) toward solution
• Some justification of decision(s) toward solution
• Attempts to communicate solution and support
• A wrong decision, confused reasoning, and/or notational mistakes
• Revision is needed

Developing (7/10)

• Does not contain the correct answer but shows some correct work
• Incorrect decision(s) toward solution
• Insufficient or incorrect justification for decision(s) toward solution
• Little or no communication of solution and support
• Several wrong decisions, confused reasoning, and/or notational mistakes
• Revision is needed

Minimal (5/10 or 6/10)

• Does not contain the correct answer or work in the correct direction
• Missing or incorrect decision(s) toward solution
• Little or no justification for decision(s) toward solution
• Several wrong decisions, confused reasoning, and/or notational mistakes
• Major revision is needed

No work or something completely off base (0/10)

Problem Sessions

During the semester we will have problem sessions which will be conducted by you (the students). These sessions are designed to improve your understanding of statistical ideas and enhance your mathematical reasoning skills by requiring a clear, detailed presentation of the material to your peers. During these sessions, you will be responsible for solving an assigned problem and presenting the solution to the rest of the class. Randomization will be used to assign at least two students to each exercise. Answering all questions about your solution is a required part of the presentation. Being able to solve problems and being able to present the solutions to a group in a logical and coherent fashion are two different tasks. Our goal is to master both tasks.

After your problem session presentation, you are required to upload a complete copy of your solution to the Google Drive folder !Student R Code_Solutions for Exercises using a specific naming structure. For example, the name of the file for exercise 0.42 will be 0.42_yourname.PDF or 0.42_yourname.R or 0.42_yourname.RMD. The primary reason for the specific naming structure is so that the folder stays organized and the entire class has a complete set of solutions for every exercise that we discuss during our problem sessions.

Late Policy

Your work must be turned in before class begins on the assigned due date. No credit will be given for late papers, except in the two cases where you may opt to use your "free" 48-hour extension. If for any reason you cannot turn in your paper on the assigned date, you must contact me or send e-mail to hartlaub@kenyon.edu before class begins.

Attendance Policy:

In relation to the Kenyon Class Attendance Policy and The Department of Mathematics and Statistics Attendance Policy, nine class absences (whether excused or unexcused) will result in expulsion from the course.

Exams

Quizzes

Short in class or take home quizzes will be given occasionally throughout the semester. The goal is to help you comprehend and apply the important concepts and techniques that we have been studying in a timed setting. In other words these quizzes are designed to help you prepare and practice for the exams. Sample quizzes from previous semesters are provided in the Google Drive foler !Exam and Quiz Samples.

Small Group Projects

You will be asked to solve practical data analysis problems with at least one other member of the class. A written component (paper or poster) or an oral presentation to the class will be required. The deadlines and more detailed instructions on the project will be announced in class. Sample projects from previous students are provided in Google Drive folders, see !Unit A Project Samples and !Unit B Project Samples.

Final Project

Each student will find a data set and apply an appropriate analysis. Ideally, this data set will be one which you collect yourself or obtain from a local resource. The variables in the data set and the purpose of the study must be clearly defined. If the data are obtained from a periodical, the date of publication must be later than January 1, 2019. Summaries of your proposed analysis must be submitted on or before Monday, December 4. Final papers explaining the problem of interest, your analysis, and your conclusions must be submitted on or before Wednesday, December 13 at 8:30 am. Sample final projects are provided in the Google Drive folder !Final Project Samples.

Grades

Your course grade will be based on your overall percentage. The categories used to determine your overall percentage and their respective weights are listed below.

Class participation will be used to help make borderline decisions.

Course Outline

• Chapter 0 - What is a Statistical Model?
• Chapter 1 - Simple Linear Regression
• Chapter 2 - Inference for Simple Linear Regression
• Chapter 3 - Multiple Linear Regression
• Chapter 4 - Additional Topics in Regression
• Chapter 5 - One-way Analysis of Variance (ANOVA) and Randomized Experiments
• Chapter 6 - Blocking and Two-way ANOVA
• Chapter 7 - ANOVA with Interaction and Factorial Designs
• Chatper 8 - Additional Topics in Analysis of Variance
• Chapter 9 - Logistic Regression
• Chapter 10 - Multiple Logistic Regression
• Chapter 11 - Additional Topics in Logistic Regression
• Chapter 12 - Time Series Analysis (if time permits)