Add/drop deadlines
The last date to add/drop this course without grade designation is 2025-01-22. Please act accordingly.
Time/Place
- Discussion: Thursdays 10:00-12:00
- Office hours: Mondays 16:00-17:00
Weekly schedule
| Date | Week | Topic | Due |
|---|---|---|---|
| Jan 13 | 1 | Introduction and review | |
| Jan 20 | 2 | Organizing work | HW1 |
| Organizing your work | |||
| Jan 27 | 3 | Factor variables | |
| Factor variables | |||
| Feb 03 | 4 | Model formulas | HW2 |
| Model formulas | |||
| Feb 10 | 5 | Building linear models | HW3 |
| Building linear models | |||
| Feb 17 | 6 | Logistic regression | |
| Logistic regression | |||
| Feb 24 | 7 | Generalized linear models | HW4 |
| Generalized linear models ~ Journal reporting requirements | |||
| Mar 03 | 8 | Log linear models | |
| Log linear models | |||
| Mar 10 | 9 | Tidyverse: Data transformations & tibbles | HW5 |
| Data transformations ~ Tibbles | |||
| Mar 17 | 10 | Tidyverse: Tidy data and relational data | HW6 |
| Tidy data ~ Relational data | |||
| Mar 24 | 11 | Tidyverse: Strings | |
| Strings, factors, and dates | |||
| Mar 31 | 12 | Data manipulation ecosystems in R | HW7 |
| base vs tidyverse vs data.table ~ A taste of data.table | |||
| Apr 07 | 13 | Reproducible software environments | Optional project draft (V0) |
| Introduction to renv ~ Workflow: projects | |||
| Apr 14 | 14 | Project guidelines | |
| Project guidelines ~ BXD longevity data | |||
| Apr 21 | 15 | Linear mixed models | HW8, Optional project draft (V1) |
| Linear mixed models | |||
| Apr 28 | 16 | Divide and gather | HW9, Optional project draft (V2) |
| Many models | |||
| May 05 | 17 | Censored data | HW10, Compulsory project draft (V3) |
| Survival analysis | |||
| May 12 | 18 | ||
| May 19 | 19 | Student presentations | Presentations, Final project (V4) |
| Presentation order: Freitas, Kurzbach, Gipson, Johnson, Zhang, Lenart |
Course objectives
- Apply sound project organization and reproducibility principles
- Understand the model formula syntax for specifying regression models
- Apply advanced regression techniques such as and generalized linear models (eg. logistic regression)
- Apply tidy data principles to data manipulation and analysis
- Analyze project data using appropriate statistical and computational methods
Other topics such as survival analysis and hierarchical models may be covered depending on student interest.
Pre-requisites
BIOE805 or consent of instructor.
Course director
Saunak Sen, PhD
Professor, Division of Biostatistics
Department of Preventive Medicine
645 Doctors Office Building
66 North Pauline Street
901-448-4590
sen@uthsc.edu
Grading
- Participation: 20 (1 point per class, 4 points overall)
- Homeworks: 40 (4 points per homework)
- Final project: 40 (30 for paper and code, 10 for presentation)
| Points | Grade |
|---|---|
| 00-40 | F |
| 41-50 | D |
| 51-60 | C |
| 61-80 | B |
| 81-100 | A |
See grading page for more details.
Course policies
General
- Please be on time, and bring a laptop to class. If nobody shows up within the first 15 minutes of a regularly scheduled session or office hours, the meeting will terminate.
- All assignments must be submitted on Blackboard by the time specified there.
- Students are expected to follow the honor code.
- Co-operation between students is permitted, and should be cited (eg. “Jane Doe helped me debug the code for producing the scatterplot.”).
- If you have any questions, use the Blackboard discussion forum. This way everyone benefits. Use email only if the question is confidential.
Use of generative AI
- Follow UTHSC policy.
- Use of generative AI is permitted, but (a) you have to cite it and (b) you have to generate the prompts in your own words. Copying any class material into a generative AI application is violation of class policy.