STAT22200 SPRING 2019
STAT222 SPR 2019 Linear Models And Experimental Design
Caution: Here is the old site for Spring 2019. [Click here to go to the new site for Spring 2021]
Please note that the official course website is on Canvas (log in with CNetID), NOT here.
This webpage is for those who are interested in STAT 22200 to get an idea of what the course is like.
Class Meeting: MWF 10:30-11:20 AM, Eckhart 133
Prerequisites
STAT 22000 or 23400 grade of at least C+, or STAT 22400 or 22600 or 24500 or 24510 or PBHS 32100, or AP Stat credit for STAT 22000] & [2 quarters of calculus (MATH 13200 or 15200 or 15300 or 16200 or 16210 or 15910 or 19520 or 19620 or 20250 or 20300 or 20310)]
Textbook
- Primary Testbook: A First Course in Design and Analysis of Experiments (Oehlert, 2000)
Available online for free at http://users.stat.umn.edu/~gary/Book.html
by the courtesy of the author, Professor Oehlert.
- A highly recommended book: Statistical Sleuth (3rd edition) by Ramsey & Schafer
This book is not solely on experimental design but is a bible on data analysis, which covers a lot of contents in STAT 222, 224 and 226.
- Other commonly used textbooks (a partial list; for your reference only, NOT required)
- Statistics for Experimenters Design, Innovation, and Discovery, (2005, 2nd ed.) by George E. P. Box, J. Stuart Hunter, William G. Hunter
- Design and Analysis of Experiments (2012, 8th ed.) by Douglas C. Montgomery
- Introduction to Design and Analysis of Experiments by Cobb
R, RStudio, and R Markdown
We will use R and RStudio.
- Please refer to Lab 1, Lab 2, and Lab 3 in http://www.stat.uchicago.edu/~yibi/s220/labs/ for the instruction of installation of R, RStudio, and the mosaic library, and a few R Basics, including loading data sets from a file, making data summary and plots
- We highly recommend writing your homework in R Markdown (though not required). which is a simple way to interweave the R output, figures and your explanation and comments in a single file. Click here for a tutorial.
Also refer to R Markdown Cheatsheet 2.0
Course Outline
This course covers principles and techniques for the analysis of experimental data and the planning of the statistical aspects of experiments. Topics include linear models; analysis of variance (ANOVA); randomization, blocking, factorial designs; confounding; and incorporation of covariate information.
Course Schedule and Slides
Week/Date | Topics | Coverage | Datasets |
1 |
April 1,3 |
Completely Randomized Designs, One-Way ANOVA |
3.1-3.8 |
grassweed.txt |
April 3,5 |
Pairwise Comparison and Contrasts
Additional Exercises for Chapter 3 and 4 and the Solutions
|
4.1-4.2 |
|
2 |
April 8, 10 |
(Review of) Multiple Linear Regression |
- |
housing.dat |
April 12 |
Experiments with Quantitative Factors, Goodness of Fit
Related R codes
|
3.9 |
resin.txt |
3 |
April 15 |
April 15 |
Definition of Completely Randomized Design, Measurement Unit v.s. Experimental Unit |
3.1, 1.5 |
|
April 17,19 |
Model Adequacy Checking and Remedies |
Chapter 6 |
Hodgkins.txt
resinlife.txt
|
4 |
April 22 |
April 24,26 |
Permutation-based and rank-based methods for two-sample data, one-way ANOVA data and matched-pair data |
Chapter 2 +Slides |
|
5 |
April 29May 1,3 |
Two-Way Factorial Designs
|
8.1-8.6 |
SproutingBarley.txt |
6 |
May 6,8,10 |
General Factorial Designs |
8.7-8.11 |
amylaze.txtpr8_6.txt |
7 |
May 13 |
Unbalanced Factorial Designs |
10.1 |
|
May 15 |
Quantitative Factors |
9.2.3 |
|
May 17 |
Randomized Complete Block Designs, (Replicated) Latin Square Designs, Graeco-Latin Square Designs |
Chapter 13 |
cycad.txtemission.txt |
8 |
May 20, 22 |
May 24 |
Balanced Incomplete Block Designs
No class on Monday, May 27, Memorial Day
|
14.1 |
|
9 |
May 29,31 |
10 |
June 3, 5 |
Multiple Comparisons |
Chapter 5 |
beetlice.txt |
June 5 |
Review |
|
|
June 7 |
No class on, Reading Period |
|
|