class: center, middle, inverse, title-slide .title[ # LECTURE 0: course overview ] .subtitle[ ## FANR 6750 (Experimental design) ] .author[ ### <br/><br/><br/>Fall 2025 ] --- # logistics **Lecture**: Monday, Wednesday, Friday 11:30-12:20, 1-304 **Lab**: Monday **or** Tuesday **or** Wednesday **Credits**: 3 --- # instructors .pull-left[ Dr. Clark Rushing [clark.rushing@uga.edu](clark.rushing@uga.edu) **Office**: 3-409 **Office hours**: M 12:30-2:00; Tu 9:00-10:00 ] .pull-right[ **TAs** Himasree Kolla (TBD) [himasree.kolla@uga.edu](himasree.kolla@uga.edu) **Office**: TBD **Office hours**: TBD Alan Bond (W) [alan.bond1@uga.edu](alan.bond1@uga.edu) **Office**: 1-102 **Office hours**: M 10:00-12:00 ] --- # course schedule and materials Lectures and labs: [rushinglab.github.io/FANR6750](https://rushinglab.github.io/FANR6750)¹ .footnote[[1] Bookmark this page!] -- .pull-left[ **Primary texts** (not required): Fieberg, J. (2022). Statistics for Ecologists: A Frequentist and Bayesian Treatment of Modern Regression Models. [An open-source online textbook.](https://fw8051statistics4ecologists.netlify.app/) Quinn, G.P. & Keough, M.J. 2002. Experimental Design and Data Analysis for Biologists. Cambridge University Press ] .pull-right[ <img src="fig/experimental-design-and-data-analysis-for-biologists-1.jpg" width="225" height="300" /> ] --- # labs **Meet weekly** -- - You should have registered for one and only one lab section -- - Always attend your assigned lab section unless both TA's have provided prior approval to attend the other section -- **Taught in R** -- - No prior experience required -- - But those without prior experience may need to spend time learning outside of class -- - You can use your own laptop but make sure you have R and RStudio installed prior the first lab² .footnote[[2] See [here](https://rushinglab.github.io/FANR6750/articles/syllabus.html#course-resources-1) for instructions] --- # lab assignments -- - 8 throughout semester -- - Meant to help with: + Understanding lecture/lab concepts + Implementing statistical procedures in R + Interpreting and presenting results -- - Worth 10 points each + Grade based on turning in **complete** assignment **on time** + Answer keys will be posted after all assignments have been submitted --- # grading #### 200 points total -- - 3 lecture exams, 40 points (20%) each + In-class format using eLC/Lockdown Browser³ + Primarily focused on concepts, not coding + Pool of 8-10 potential questions provided in advance + Exam consists of 2 questions chosen by me, 2 questions chosen by student + Not (explicitly) cumulative + See schedule for approximate dates (subject to change) .footnote[[3] Remote students must take exams during class period in an approved setting] -- - 8 lab assignments, 10 points (5%) each --- # a note on ai AI tools (e.g., ChatGPT) have advanced very rapidly in a very short time -- - AI can increasingly help answer questions about statistical concepts, coding, etc. -- AI = resource (similar to Google, Cross Validated, etc.) - AI can help you perform statistical analyses but **it cannot replace your own statistical knowledge** -- My goal is not to fight AI, but instead focus on responsible and appropriate use - Students may use AI to assist with lab assignments but must acknowledge, document, and assess all AI use - Students may use AI to assist with exam preparation but must complete exams without the use of AI - Unacknowledged use of AI will be considered a violation of course policy. Suspected violations will be referred to the Office of Academic Honesty --- # a note on ai Later in the semester, we will have a class discussion on the role of AI in research/statistical analysis -- In preparation for that discussion, I highly recommend reading [Bull$&!t Machines](https://thebullshitmachines.com/table-of-contents/index.html), a short, self-paced course on the LLM <img src="fig/bs_machines.png" width="3873" /> --- # remote students Although we do our best to make instruction and materials accessible to remote students, *this is not officially a hybrid class*. That has several implications: - Teaching to in-person and remote students is hard, especially labs. Technology problems are inevitable - Remote students should be prepared to spend extra effort engaging with course materials if they - Remote students must arrange to take exams with a proctor present and exam arrangements must be approved by the instructor prior to the exam - MAKE SURE YOU HAVE ACCESS TO THE PRIMARY eLC PAGE! -- **A note to in-person students:** In my experience, lab and lecture attendance are strong predictors of performance. Although zoom links can be used for brief or unanticipated absences, students based in Athens should attend classes in person --- # course objectives **To understand:** <br/> -- 1) the logical structure of experiments, including the design of manipulative and observational experiments; <br/> -- 2) the analysis of such experiments, focusing on linear models; <br/> -- 3) the use of models in ecological studies (experimental and observational); <br/> --- # basic structure -- 1) Foundational concepts for statistical inference and experimental design -- 2) Linear model basics -- 3) Null hypothesis significance testing -- 4) Linear model variations for experiments (t-tests, ANOVA, ANCOVA) -- 5) Generalized linear models and model selection --- # pre- and post-course assessment Two short quizzes used to assess collective learning outcomes - Posted under `Quizzes` on eLC - Require Lockdown Browser extension - Pre-assessment available until 8/17/2025 -- The assessments do not count towards your grade, but students who complete them will receive extra credit on their final grade - 2 points for completing pre-assessment - 2 points for completing post-assessment - 1 points for completing both assessments (5 points total) --- # looking ahead ### Next time: Basic Concepts in Statistics ### Reading: [Quinn chp. 1](https://www2.ib.unicamp.br/profs/fsantos/apostilas/Quinn%20&%20Keough.pdf#page=21.08)