Biometry 802: Experimental Design

Objective

Both as a consumer and a producer of science it is important to understand the process of conducting research. In this course we will examine the process from the "question stage" to the "report stage" and back again. Along the lines we will examine the statistical tools we have for formulating models, efficiently collecting data, analyzing and interpreting data. By the end the course it is hoped that you will have developed the skills needed to design and analyze simple experiments. It is also important that you understand the underlying concepts. It is the underlying concepts which will allow you to handle situations not specifically covered in the course.

Course Info

Instructor:	Steve Kachman
E-mail:	skachman@unl.edu
Office:	104 D Miller Hall
Phone:	472-2903
Office Hours:	MWF 10:00-11:30 and by appointment
TA:	Bruce DeGroot
TA's E-mail:	bdegroo1@bigred.unl.edu
Text Book:	Design of Experiments: Statistical Principles of Research Design and Analysis, Robert Kuehl
Prerequisites:	Biometry 801 Estimation including confidence intervals Hypothesis testing Analysis of variance Regression SAS
Homework:	Approximately once a week 20% will be deducted for each day late.
Exams:	Two exams, will be announced at least one week in advance
Final Exam:	7:30-9:30 am Friday, Dec. 15 Revise travel plans accordingly.
Check Grades:	Blackboard Course Info

Course Material

Course Syllabus
To view the Course Syllabus click on Course Syllabus . If Acrobat Reader is not installed on your computer click on .
Notes
- Completely Randomized Designs Chap. 2
  - White paper on CRD
    The section on estimation is for your information.
- Contrasts and Multiple Comparisons Chap. 3
  (The book focuses heavily on polynomials. I will address polynomials as part of factorial designs/response surfaces.)
  - White paper on contrasts and multiple comparisons
- Power and Sample Size
  - White paper on power and sample size
  - Mixed Model Procedures to Assess Power, Precision, and Sample Size in the Design of Experiments, W. W. Stroup
- Factorial Arrangement of Treatments Chap. 6
  - White paper on factorial arrangement of treatments
- Response Surfaces, Least Square Means, and Type 1 versus Type 3 Hypotheses
- Fixed and Random effects Chapter 7
  - White paper on fixed and random effects
- Nested effects Chapter 7.3
  - White paper on nested effects
- Blocking and Randomized Complete Block Designs Chapter 8
  - White paper on blocking and RCBD
- Latin Squares Chapter 8.3 and 16
  - White paper on Latin squares
- Split Plot Designs Chapter 14
  - White paper on split plot designs
SAS Programs
- CRD example (Proc GLM): dough.sas
  To download dough.sas under Netscape right-click on dough.sas and select Save Link As.
- CRD Example (Proc Mixed): dough_mixed.sas
- Calculting Power with Proc Mixed power.sas
  6.12 power612.sas
- Determining Sample Size with Proc Mixed pow2.sas
  6.12 pow2_612.sas
- Version 8.0 Example Programs from "Mixed Model ...."
- FAT examples:
  asphalt.sas
  zinc.sas
  water.sas
- Mixed examples: spbl.sas
- Crossover example: crossover.sas
- Split Plot examples:
  oatsm.sas
Data Sets
- CRD data: dough.dat
- FAT data:
  asphalt.dat
  zinc.dat
  water.dat
- Mixed models: spbl.dat
- Crossover: crossover.dat
- Split Plot data:
  oat.dat
- Orthogonal Polynomial Coefficients:
  orpol.sas
Homework
- Homework 1
- Homework 2
- Homework 3
- Homework 4
- Homework 5
- Homework 6
- Homework 7
- Homework 8
- Homework 9
- Homework 10
- Homework 11
- Homework 12
  orpol.sas
Practice Problems
- 8/24/00 Chapter 2: 1,3,5
  Problem 7 will be appropriate after we talk about Power
  Skip part g.
- 9/15/00 Chapter 2: Problem 7 would be a good idea now. You may also want to try your hand with the example 2.3.
- 10/12/00 Chapter 6
Examples
for PDF files

Steve Kachman <skachman@unl.edu>
Last modified: Wed Dec 6 08:27:07 CST 2000