Course Details & Expectations

AGST 50104 Experimental Design

Dr. Samuel B Fernandes

2026-01-01

Learning Objectives

By the end of this course, you will:

  1. Design rigorous experiments (CRD, RCBD, factorial, split-plot, etc.)
  2. Choose appropriate designs based on constraints and research questions
  3. Analyze data using ANOVA, linear mixed models, and GLMs
  4. Interpret statistical results in practical, domain-relevant language
  5. Communicate results clearly (reports, presentations, visualizations)
  6. Recognize and avoid common pitfalls
  7. Use R & Quarto for reproducible, professional analyses

Course Structure & Grading

Grade Components (1000 points):

Component Points %
Homework 300 30%
Exam I 150 15%
Exam II 150 15%
Final Exam 200 20%
Project 200 20%

Letter Grade Scale:

Grade Range %
A 900–1000 90%+
B 800–899 80%+
C 700–799 70%+
D 600–699 60%+
F 0–599 <60%

Homework & Teamwork

How Homework Works:

  • Groups of ~5 students (formed Week 1)
  • Assigned almost every Friday
  • Due Thursday 11:59 PM
  • Friday Lab: One member randomly selected to present
  • Lowest homework score is dropped

Team Success Tips:

  • Communicate early and often
  • Submit Thursday, not Friday
  • Practice explaining your work
  • Use AI (GitHub Copilot) to learn
  • Go to office hours

Grading is 60% group + 20% your presentation + 20% peer evaluation

Your individual grade depends on effort AND how much you contribute to the group.

Exams: What to Expect

Caution

AI Policy on Exams:

  • NO AI during exams (GitHub Copilot, ChatGPT, etc.) –> Unauthorized use = Academic integrity violation
  • Exams test YOUR understanding, not AI’s
  • Exam I (Feb 20): CRD through early RCBD concepts
  • Exam II (April 3): Factorial to Incomplete Block designs
  • Final Exam (May 6): Comprehensive; can include anything from the course
  • Format: Closed-book; bring one handwritten formula sheet (single side)
  • Exam can be handwritten OR coded

The Final Project

Project Requirements:

  • Topic: Randomly assigned in Week 1
  • Format: 9–11 minute YouTube video
  • Deadline: April 24, 2026, 11:59 PM
  • Grading: 200 points = check rubric
  • All group members must appear in the video to receive a grade

Projects showcase REAL experimental design thinking—not just formulas!

What to Include:

  • Clear explanation of your assigned design
  • Why it’s appropriate for the scenario
  • Complete analysis workflow:
    • Data exploration
    • Statistical analysis
    • Diagnostics
    • Conclusions
  • Visualizations that tell the story

Computing & Resources

Required Software (Free):

  1. R (statistical computing)
  2. VS Code (code editor + Quarto)
  3. Quarto (reproducible documents)
  4. GitHub Account (version control)
  5. GitHub Copilot (AI programming)

Alternative: RStudio/Posit Cloud

Key Packages You’ll Learn:

  • Tidyverse: Data manipulation, Visualization, Data reshaping
  • car: ANOVA & diagnostics
  • emmeans: Post-hoc comparisons
  • ASReml-R/lme4/nlme: Mixed models

Install these as we go—no upfront burden!

GitHub Copilot helps you write R code faster. It’s built into VS Code and free with your .edu email.

Course Expectations & Policies

  • Attendance: Expected at all lectures and labs (excused absences: illness, family, religious observance, etc.)
  • Office Hours: Monday & Wednesday, 1–2 PM (PTSC 107), or by appointment
  • Communication: Please allow 24 hrs (weekdays) or 48–72 hrs (weekends) for email responses
  • Procrastination: Homework is due Thursday 11:59 PM—don’t start Friday morning!
  • Respect: This is a collaborative environment. Support your teammates and classmates

Questions?

Contact Information:

Dr. Samuel B Fernandes
📧 samuelbf@uark.edu
📍 PTSC 107
📞 (479) 575-5677

Office Hours:
Mon & Wed: 1:00–2:00 PM
Or by appointment

Course Materials:

  • Lectures: Blackboard
  • Assignments: Blackboard Ultra
  • Communication: Microsoft Teams (preferred)
  • Announcements: Email + Blackboard

Everything is linked in Blackboard!

Welcome to the AGST50104 2026!