Syllabus

PLS 206: Applied Multivariate Statistical Modelling for Agricultural and Environmental Sciences, Fall 2026 · 4 units · CRN 42873

Mondays and Wednesdays 1:10–2:30 PM, plus Friday discussion 12:10–1:00 PM, Asmundson Hall 242

Dr. Grey Monroe — office hours Fridays 1:00 PM, Robbins Hall 262, or by appointment (Zoom) · gmonroe@ucdavis.edu

TA: Matt Davis · mtdavis@ucdavis.edu

When you email either of us, please put PLS 206 in the subject line.

Course information

This course gives graduate students in agriculture, ecology, and related sciences a working foundation in multivariate statistical modeling: how to choose an appropriate analysis for a dataset, run it in R, and interpret and communicate the results. We move from linear regression through generalized and nonlinear models, model selection and regularization, dimension reduction, clustering, and into more advanced territory (random forests, neural networks, structural equation modeling) by the end of the quarter.

The prerequisite is STA 100 (or equivalent). No prior programming experience is required — the course opens with a stats and R refresher in Week 1 so that everyone starts from the same footing, regardless of coding background.

Throughout the course, the emphasis is on building the judgment to pick the right tool for a dataset and defend that choice, not on memorizing formulas. You will leave with a working analysis toolkit and a set of R scripts you can adapt to your own research.

Course format

Lectures (Mon/Wed, 1:10–2:30 PM) are roughly half background on the statistical method of the week and half live coding, applying that method to a real dataset. R scripts are posted in advance — bring your laptop so you can code alongside during lecture.

Friday discussion (12:10–1:00 PM) is for problem-set questions, catching up on anything the week didn’t cover, and a rotating “how-to” topic in practical R skills (data wrangling, writing functions, loops and apply, publication-quality figures, building your own package, parallelizing big data, and more). See the Schedule for what’s covered each week.

Zoom is offered for accessibility, and lectures are recorded and posted to Canvas within 24 hours on a best-effort basis. Zoom and recordings are not guaranteed to work every session, so plan to attend in person, especially for the live coding portions.

Where things live: all course materials — lecture scripts, slides, datasets, and problem-set details — are on this website, updated throughout the quarter. Canvas is where you submit assignments, take the reflection surveys, and see your grades.

Learning outcomes

By the end of this course, students should be able to:

Identify an appropriate statistical model for a given multivariate dataset and explain why it fits.
Implement that analysis in R, from data wrangling through model fitting, diagnostics, and visualization.
Interpret and communicate the results of a multivariate analysis to a scientific audience.
Continue learning new statistical and computational tools independently after the course ends.

Prerequisites and materials

STA 100 or equivalent is the only formal prerequisite. There is no required textbook. The primary recommended resource is An Introduction to Statistical Learning (ISLR2) by James, Witten, Hastie, and Tibshirani — the free PDF covers most of the quarter’s material. Also useful:

Multivariate Analysis of Ecological Data (Greenacre & Primicerio, free online)
StatQuest for short video explanations of most methods we cover
Davis R Users’ Group (D-RUG) for community R help sessions
Stack Overflow and CrossValidated for coding and statistics questions

Before Week 1, install R and RStudio on your own laptop — both are free. See the setup guide for instructions. If you do not have access to a computer that can run R outside of class, contact the instructor as soon as possible so accommodations can be arranged.

Assignments and assessment

Weekly problem sets (90% of grade): nine problem sets, one per module, each worth 100 points. Problem sets are released Monday at the start of each module and due the following Monday at 1:10 PM (start of class). Submit two files to Canvas: a written PDF with your answers and an R script with the code that produced them, named HW##emailID.R and HW##emailID.pdf (where ## is the problem set number and emailID is the part of your email address before the @). List anyone you collaborated with in both files.

Problem sets are graded for completeness, not correctness — your answers must be logical and demonstrate a genuine attempt, but an honest wrong answer with valid reasoning earns credit. We do not accept late problem sets, so note the due date and time; if something extraordinary comes up, contact the instructor as soon as possible. Your two lowest problem-set scores are dropped automatically.

Daily reflections (10% of grade): a short 2-point survey posted after each Monday/Wednesday lecture on Canvas, due before the next class meeting. There is no reflection for the Friday discussion. Late reflections receive 50% credit.

Final assignment (part of the 90% weekly-assignment pool, cannot be dropped): a micro-paper analyzing your own data, data from your lab, or an existing published dataset, using methods from the course. Assigned in Week 9, due the last day of finals week. Full details posted on the Assignments page and in Canvas.

Working in groups: collaboration is encouraged. Discuss problem sets together, share ideas, and work through the logic as a group — but once your group agrees on an approach, do the calculations and write your own answers independently, even if that means re-running code the group already ran. List collaborators’ names on your submission. Any resource available to you is fair game as long as you cite it (see Use of AI below); the point is to learn how to be resourceful, not to memorize.

Grading policy

Grades are assigned on a straight percentage basis — there is no curve, so you are not competing with your classmates for a grade.

Grade	Range	Grade	Range	Grade	Range
A+	97–100%	B+	87–89.99%	C+	77–79.99%
A	93–96.99%	B	83–86.99%	C	73–76.99%
A-	90–92.99%	B-	80–82.99%	C-	70–72.99%

D+/D/D- span 60–69.99% in the usual 3-point bands, and 59.99% and below is an F.

Most students pass this course comfortably; it mainly takes doing all the work and turning it in on time. If you find yourself struggling, reach out before you hit the point of frustration.

Use of AI and outside resources

You are welcome to use AI tools, Google, Stack Overflow, classmates, or any other resource to get unstuck on code or understand a concept — that has always been true in this course, and AI assistants are simply another resource in that category. Since problem sets are graded for completeness and logical reasoning rather than a single correct answer, using these tools to help you understand why a method works is part of the intended way to learn it.

What you submit should reflect your own understanding: write your own answers and interpretation, note where you used AI assistance the same way you would cite a classmate or a Stack Overflow post, and be able to explain any code or result you turn in. For the final micro-paper, any data, statistics, or citations you include must be real and verified by you — do not submit fabricated or AI-hallucinated results.

Academic integrity

Read and understand the UC Davis Code of Academic Conduct and the UC Davis Student Code of Conduct. Academic dishonesty or misconduct is taken seriously and reported to Student Judicial Affairs. Materials posted for this course are copyrighted to the authors and/or the Regents of the University of California; do not redistribute them outside students currently enrolled in the course. Questions about what counts as misconduct are welcome — ask before, not after.

Schedule

The authoritative week-by-week schedule, including dates, topics, and Friday discussion themes, is on the Schedule page and is updated throughout the quarter — that is the version to trust over anything printed elsewhere. All due dates also appear in Canvas.

Accessibility

Talk with the instructor as early in the quarter as possible about any accommodations you need. Solutions that help one student often help the whole class, so questions and suggestions are welcome throughout the quarter. Contact the Student Disability Center for more information and to request accommodations: (530) 752-3184 · sdc@ucdavis.edu · sdc.ucdavis.edu.

Diversity, equity, and inclusion

Students of all races, ethnicities, genders and gender expressions, ages, abilities, nationalities, sexual orientations, citizenship statuses, veteran statuses, religious and political beliefs, and socioeconomic backgrounds are welcome in PLS 206. We aim to use materials and activities that are respectful of that diversity, and suggestions toward that goal are always appreciated — please let the instructor know if any aspect of the class makes it harder for you to learn. All participants should be familiar with the UC Davis Principles of Community.

Land acknowledgment

For thousands of years, the land this course meets on has been the home of Patwin people. Today there are three federally recognized Patwin tribes: the Cachil DeHe Band of Wintun Indians of the Colusa Indian Community, the Kletsel Dehe Wintun Nation, and the Yocha Dehe Wintun Nation. The Patwin people have remained committed to the stewardship of this land over many centuries, cherished and protected as elders have instructed the young through generations. Read more about the UC Davis Land Acknowledgement.

Student wellness

You deserve respect, and are encouraged to practice self-care so you can stay focused and engaged — that might mean getting a drink of water, taking a break, or doing whatever else you need to do to take care of yourself. Graduate school can be overwhelming at times; you are not alone if you are feeling stressed. Student Health and Counseling Services offers free counseling and 24/7 support (Health 34: 530-754-3434), and the Aggie Compass Basic Needs Center can help with food, housing, and other basic needs.

--- title: "Syllabus" --- **PLS 206: Applied Multivariate Statistical Modelling for Agricultural and Environmental Sciences, Fall 2026** · 4 units · CRN 42873 Mondays and Wednesdays 1:10–2:30 PM, plus Friday discussion 12:10–1:00 PM, Asmundson Hall 242 **Dr. Grey Monroe** — office hours Fridays 1:00 PM, Robbins Hall 262, or by appointment ([Zoom](https://ucdavis.zoom.us/my/greymonroe)) · gmonroe@ucdavis.edu **TA:** Matt Davis · mtdavis@ucdavis.edu When you email either of us, please put **PLS 206** in the subject line. ## Course information This course gives graduate students in agriculture, ecology, and related sciences a working foundation in multivariate statistical modeling: how to choose an appropriate analysis for a dataset, run it in R, and interpret and communicate the results. We move from linear regression through generalized and nonlinear models, model selection and regularization, dimension reduction, clustering, and into more advanced territory (random forests, neural networks, structural equation modeling) by the end of the quarter. The prerequisite is STA 100 (or equivalent). **No prior programming experience is required** — the course opens with a stats and R refresher in Week 1 so that everyone starts from the same footing, regardless of coding background. Throughout the course, the emphasis is on building the judgment to pick the right tool for a dataset and defend that choice, not on memorizing formulas. You will leave with a working analysis toolkit and a set of R scripts you can adapt to your own research. ## Course format **Lectures** (Mon/Wed, 1:10–2:30 PM) are roughly half background on the statistical method of the week and half live coding, applying that method to a real dataset. R scripts are posted in advance — **bring your laptop** so you can code alongside during lecture. **Friday discussion** (12:10–1:00 PM) is for problem-set questions, catching up on anything the week didn't cover, and a rotating "how-to" topic in practical R skills (data wrangling, writing functions, loops and `apply`, publication-quality figures, building your own package, parallelizing big data, and more). See the [Schedule](schedule.qmd) for what's covered each week. **Zoom** is offered for accessibility, and lectures are recorded and posted to Canvas within 24 hours on a best-effort basis. Zoom and recordings are not guaranteed to work every session, so plan to attend in person, especially for the live coding portions. **Where things live:** all course materials — lecture scripts, slides, datasets, and problem-set details — are on this website, updated throughout the quarter. Canvas is where you submit assignments, take the reflection surveys, and see your grades. ## Learning outcomes By the end of this course, students should be able to: 1. Identify an appropriate statistical model for a given multivariate dataset and explain why it fits. 2. Implement that analysis in R, from data wrangling through model fitting, diagnostics, and visualization. 3. Interpret and communicate the results of a multivariate analysis to a scientific audience. 4. Continue learning new statistical and computational tools independently after the course ends. ## Prerequisites and materials STA 100 or equivalent is the only formal prerequisite. There is no required textbook. The primary recommended resource is *An Introduction to Statistical Learning* (ISLR2) by James, Witten, Hastie, and Tibshirani — the [free PDF](https://web.stanford.edu/~hastie/ISLR2/ISLRv2_website.pdf) covers most of the quarter's material. Also useful: - [Multivariate Analysis of Ecological Data](https://www.fbbva.es/microsite/multivariate-statistics/maed.html) (Greenacre & Primicerio, free online) - [StatQuest](https://statquest.org/) for short video explanations of most methods we cover - [Davis R Users' Group (D-RUG)](https://d-rug.github.io/) for community R help sessions - Stack Overflow and [CrossValidated](https://stats.stackexchange.com/) for coding and statistics questions **Before Week 1**, install R and RStudio on your own laptop — both are free. See the [setup guide](modules/setup.html) for instructions. If you do not have access to a computer that can run R outside of class, contact the instructor as soon as possible so accommodations can be arranged. ## Assignments and assessment **Weekly problem sets (90% of grade):** nine problem sets, one per module, each worth 100 points. Problem sets are released Monday at the start of each module and due the following Monday at 1:10 PM (start of class). Submit two files to Canvas: a written PDF with your answers and an R script with the code that produced them, named `HW##emailID.R` and `HW##emailID.pdf` (where `##` is the problem set number and `emailID` is the part of your email address before the @). List anyone you collaborated with in both files. Problem sets are graded for completeness, not correctness — your answers must be logical and demonstrate a genuine attempt, but an honest wrong answer with valid reasoning earns credit. **We do not accept late problem sets**, so note the due date and time; if something extraordinary comes up, contact the instructor as soon as possible. Your two lowest problem-set scores are dropped automatically. **Daily reflections (10% of grade):** a short 2-point survey posted after each Monday/Wednesday lecture on Canvas, due before the next class meeting. There is no reflection for the Friday discussion. Late reflections receive 50% credit. **Final assignment (part of the 90% weekly-assignment pool, cannot be dropped):** a micro-paper analyzing your own data, data from your lab, or an existing published dataset, using methods from the course. Assigned in Week 9, due the last day of finals week. Full details posted on the [Assignments](assignments.qmd) page and in Canvas. **Working in groups:** collaboration is encouraged. Discuss problem sets together, share ideas, and work through the logic as a group — but once your group agrees on an approach, do the calculations and write your own answers independently, even if that means re-running code the group already ran. List collaborators' names on your submission. Any resource available to you is fair game as long as you cite it (see Use of AI below); the point is to learn how to be resourceful, not to memorize. ## Grading policy Grades are assigned on a straight percentage basis — there is no curve, so you are not competing with your classmates for a grade. | Grade | Range | Grade | Range | Grade | Range | |---|---|---|---|---|---| | A+ | 97–100% | B+ | 87–89.99% | C+ | 77–79.99% | | A | 93–96.99% | B | 83–86.99% | C | 73–76.99% | | A- | 90–92.99% | B- | 80–82.99% | C- | 70–72.99% | D+/D/D- span 60–69.99% in the usual 3-point bands, and 59.99% and below is an F. Most students pass this course comfortably; it mainly takes doing all the work and turning it in on time. If you find yourself struggling, reach out before you hit the point of frustration. ## Use of AI and outside resources You are welcome to use AI tools, Google, Stack Overflow, classmates, or any other resource to get unstuck on code or understand a concept — that has always been true in this course, and AI assistants are simply another resource in that category. Since problem sets are graded for completeness and logical reasoning rather than a single correct answer, using these tools to help you understand *why* a method works is part of the intended way to learn it. What you submit should reflect your own understanding: write your own answers and interpretation, note where you used AI assistance the same way you would cite a classmate or a Stack Overflow post, and be able to explain any code or result you turn in. For the final micro-paper, any data, statistics, or citations you include must be real and verified by you — do not submit fabricated or AI-hallucinated results. ## Academic integrity Read and understand the [UC Davis Code of Academic Conduct](https://ossja.ucdavis.edu/code-academic-conduct) and the [UC Davis Student Code of Conduct](https://ossja.ucdavis.edu/uc-davis-standards-conduct-students). Academic dishonesty or misconduct is taken seriously and reported to [Student Judicial Affairs](https://ossja.ucdavis.edu/). Materials posted for this course are copyrighted to the authors and/or the Regents of the University of California; do not redistribute them outside students currently enrolled in the course. Questions about what counts as misconduct are welcome — ask before, not after. ## Schedule The authoritative week-by-week schedule, including dates, topics, and Friday discussion themes, is on the [Schedule](schedule.qmd) page and is updated throughout the quarter — that is the version to trust over anything printed elsewhere. All due dates also appear in Canvas. ## Accessibility Talk with the instructor as early in the quarter as possible about any accommodations you need. Solutions that help one student often help the whole class, so questions and suggestions are welcome throughout the quarter. Contact the Student Disability Center for more information and to request accommodations: (530) 752-3184 · sdc@ucdavis.edu · [sdc.ucdavis.edu](https://sdc.ucdavis.edu/). ## Diversity, equity, and inclusion Students of all races, ethnicities, genders and gender expressions, ages, abilities, nationalities, sexual orientations, citizenship statuses, veteran statuses, religious and political beliefs, and socioeconomic backgrounds are welcome in PLS 206. We aim to use materials and activities that are respectful of that diversity, and suggestions toward that goal are always appreciated — please let the instructor know if any aspect of the class makes it harder for you to learn. All participants should be familiar with the [UC Davis Principles of Community](https://diversity.ucdavis.edu/principles-community). ## Land acknowledgment For thousands of years, the land this course meets on has been the home of Patwin people. Today there are three federally recognized Patwin tribes: the Cachil DeHe Band of Wintun Indians of the Colusa Indian Community, the Kletsel Dehe Wintun Nation, and the Yocha Dehe Wintun Nation. The Patwin people have remained committed to the stewardship of this land over many centuries, cherished and protected as elders have instructed the young through generations. Read more about the [UC Davis Land Acknowledgement](https://diversity.ucdavis.edu/land-acknowledgement-statement). ## Student wellness You deserve respect, and are encouraged to practice self-care so you can stay focused and engaged — that might mean getting a drink of water, taking a break, or doing whatever else you need to do to take care of yourself. Graduate school can be overwhelming at times; you are not alone if you are feeling stressed. [Student Health and Counseling Services](https://shcs.ucdavis.edu/) offers free counseling and 24/7 support (Health 34: 530-754-3434), and the [Aggie Compass Basic Needs Center](https://aggiecompass.ucdavis.edu/) can help with food, housing, and other basic needs.