22S:152 Applied Linear Regression www.stat.uiowa.edu/~kchan/S152.htm
Fall, 2006
1. Instructor: Kung-Sik Chan SH 263 335-2849 kchan@stat.uiowa.edu
office hours: MF 10:30-11:20, W 2:30-3:20 or by appointment.
2. Department: Statistics and Actuarial Science
DEO contact information (Luke Tierney, 241 SH, 335-0712, luke-tierney@uiowa.edu
)
3. Textbook: “Regression with Graphics” by Lawrence C. Hamilton, plus lecture notes.
4. The objective of the present course is to introduce various modern regression techniques, mainly those in Chapters 1 to 8 of the textbook, and, if time permits, penalized regresson techniques based on a set of lecture notes.
5. Prerequisite: 22S:030 or 22S:039 or 22S:043 or 22S:102 or equivalent.
Same as 056:176.
6. Course requirements:
Homework
Quizzes
Exam 1 date
8/30, 9/13, 10/11, 10/23, 11/15, 12/4
9/29 (Friday)
Exam 2 11/3 (Monday)
Project Presentation 9:45 a.m. 12/14, 2006 percent
15%
30%
20%
20%
15%
Homework must be handed in by the BEGINNING of the lecture on the due date. Late homework will be marked but NO CREDIT will be given. Each homework carries approximately equal weight and the one with the lowest mark will be dropped from the determination of the final grade. Discussion with fellow students on the exercises of the homework is allowed. However, each student should submit his
1

or her OWN solutions. Exams are closed book; however, you may have one page (8 .
5 × 11) of notes. Each student is required to work
INDIVIDUALLY on a project analyzing a real dataset with 3 or more variables. Each student is required to do a project analyzing the data, and write a project report. Dependent on the final student size, each one will be required to do an approximately 4-minute presentation on
12/14. The “powerpoint” presentation file and the project report have to be submitted on 12/13.
7. Grades: Your grade for this course will be assigned according to the following approximate scale:
90 to 100 A
80 to 89 B
70 to 79 C
60 to 69 D
0 to 59 F
This scale is not absolute, and the cutoff points may vary depending on the difficulty of the exams. Also, borderline cases may receive a + or − .
8. Project: A real time dataset, with 3 or more variables and more than
30 datacases, should be used for the analysis. A one-page proposal outlining the scientific questions to be addressed and the relevant techniques to be employed, with a separate listing of the data, has to be handed in during class on 11/27. The final written report should be typed and include a one-page non-technical summary of the findings, followed by the background of the scientific questions, the body of technical analyses with interpretations, a conclusion and the listing of the data. Including graphics, the report ordinarily should not exceed 10 pages in length.
9. Statistical softwares: We will mainly use R (GNU Splus) for statistical analysis. R will be available at the ITC in Schaeffer Hall. R can be freely down-loaded from http://www.r-project.org/
Besides reading my lecture notes on using R to do regression analysis, a readable introduction to R is “An R and S-PLUS companion to Applied
Regression” by John Fox.
2

We shall also occasionally show how to use SAS to do the analysis.
SAS licenses can be purchased in the IMU bookstore.
10. Miscellaneous:
• A list of independent tutors can be found at http://www.stat.uiowa.edu/courses/tutors.html
• Course policies are governed by the College of Liberal Arts and
Sciences.
• I would like to hear from anyone who has a disability which may require some modification of seating, testing or other class requirements so that appropriate arrangements may be made. Please see me about this as soon as possible.
• University policies regarding Student Rights and Responsibilities can be found at http://www.clas.uiowa.edu/students/academic_handbook/
3