Stats 111/202: Statistical Methods for Data Analysis II

Winter 2013

Department of Statistics

University of California, Irvine


Jump to...


Course Syllabus

Download the course syllabus here.

Grade Dispute Form: You must print and fill out this cover sheet (pdf) and attach the homework/exam in dispute in order for your grade to be reconsidered. Please read the instructions on the cover sheet carefully.

Agresti's textbook resources:

Additional textbook references:
The following book is free to download on link.springer.com if you're accessing it on UCI campus:

The following books are available for preview on link.springer.com:

The following textbooks are on reserve in the UCI Science Library:


Instructor and Class Information

Lecture: Tue/Thurs 12:30-1:50pm DBH 1500
Lab: Wed 4:00-4:50pm DBH 1500

Instructor
Stacey Hancock, PhD
Office: 2204 DBH
Phone: (949) 824-9795
Email: stacey.hancock_at_uci.edu
Office Hours:
Tue/Thurs 10:00-11:30am or by appointment.

Please email the instructor only for personal questions. Post all questions about course material, homework, exams, etc. on our EEE MessageBoard:  https://eee.uci.edu/boards/w13/stats111-202

R References

Download and Install R:
The R Project for Statistical Computing
R for Windows FAQ
R for Mac FAQ

Quick R References:
Jones R Reference Page
Short R Reference Card

Online R Tutorials and Documentation:
R FAQ
R Wiki
An Introduction to R (pdf) (html)
Verzani Simple R Notes

R Books:  The following two books are free to download on link.springer.com if you're accessing it on UCI campus:

Data Sets

Current Population Survey (1985)
World Bank Data (1990)
Agresti Horseshoe Crab Data
Framingham Data Set (Description)
Donner Party Data (used in Homework 4)
Beetle Insectide Data (used in Homework 5)
Orobanche Data (used in Lecture 14)
CHD Data (used on final exam)
Australian Travel Choices Data (used in Lecture 16)


Class Calendar

This calendar will be updated after each class. Check back periodically for required reading, additional handouts and references, homework assignments, and lecture notes.

Date
Material Covered
(Tentative schedule; may be updated after each class)
Date HW Due
Assignment
Week 1:



Tue. Jan. 8
Lecture 1 Notes
Chapter 1, Sections 1.1-1.3 (Skip 1.4 for now): categorical response data, binomial and multinomial distributions, review of inference for a single population proportion.


Discussion 1
Introduction/review of R software.
R code used in discussion.



Thurs. Jan. 10
Lecture 2 Notes
Chapter 2, Sections 2.1-2.3: probability structures of contingency tables, comparing two proportions, relative risk, and odds ratio.
Fri. Jan. 18
by 5pm
Homework #1
Week 2:



Tue. Jan. 15
Lecture 3 Notes
Finish Lecture 2 notes on inference for odds ratio. Chapter 2, Sections 2.4 and 2.6 (Skip 2.5 and 2.7 for now): inference for two-way contingency tables.


Discussion 2
Discussion Slides
Discussion R code
Review of sampling distributions, confidence intervals, and hypothesis tests.



Thurs. Jan. 17
Finish Lecture 3 notes (and Lecture 2 R code) on tests of independence.



Week 3:



Tue. Jan. 22
Lecture 4 Notes
Start Chapter 3; review ordinary least squares.
Thurs. Jan. 31
Homework #2
(Updated at 11:45pm on Sat. Jan. 26)
Discussion 3
Matrix algebra in R using CPS data.
R code used in discussion.



Thurs. Jan. 24
Lecture 5 Notes (updated Tue. Jan. 29)
Finish Lecture 4 notes and World Bank data example; Chapter 3, Sections 3.1-3.2: components of GLMs and GLMs for binary data.


Week 4:



Tue. Jan. 29
Lecture 6 Notes
Finish Lecture 5 notes on GLMs for binary data; Chapter 3, Section 3.3: GLMs for count data.
Tue. Feb. 5
Homework #3
Discussion 4
No discussion this week; Prof. Hancock will have office hours during discussion time.



Thurs. Jan. 31
Lecture 7 Notes
Finish Lecture 6 notes; Chapter 3, Section 3.4 (Skip Section 3.5): statistical inference and model checking for GLMs.


Week 5:



Tue. Feb. 5
Lecture 8 Notes
Leftovers from Chapter 3; Chapter 4, Sections 4.1-4.5.


Discussion 5
Review for Midterm Exam.



Thurs. Feb. 7
MIDTERM EXAM
Midterm Information, Material, and Practice Problems
Solutions to Practice Problems

Midterm Exam Solutions



Week 6:



Tue. Feb. 12
Lecture 9 Notes
Finish Lecture 8 notes; Chapter 4, Sections 4.3.4-4.3.5 on Cochran-Mantel-Haenszel and Breslow-Day tests.


Discussion 6
Hand back and go over Midterm exam.



Thurs. Feb. 14
Lecture 10 Notes
Finish Lecture 9 notes; Chapter 5, Sections 5.1-5.2 on model selection and model checking (Skip Sections 5.3-5.5).
Fri. Feb. 22
by 5pm
Homework #4
(Updated Sun. Feb. 17)

Color Options in R
Point Character Options in R
Week 7:



Tue. Feb. 19
Lecture 11 Notes
More examples on model checking and model diagnostics.


Discussion 7
More practice with plotting in R.
R code used in discussion.



Thurs. Feb. 21
Lecture 12 Notes
Addendum to Lecture 12 Notes
Finish Moth data example; Chapter 7, Section 7.1 on loglinear models; revisit Chapter 2, Section 2.7 on association in three-way tables (Skip Chapter 6 on multicategory logit models for now).
Fri. Mar. 1
by 5pm
Homework #5
Week 8:



Tue. Feb. 26
Finish Lecture 12 notes.


Discussion 8
No discussion this week; Prof. Hancock will have office hours during discussion time.



Thurs. Feb. 28
Lecture 13 Notes
Chapter 7, Section 7.2.
Fri. Mar. 8
Homework #6
Week 9:



Tue. Mar. 5

Lecture 14 Notes
Finish housing example (loglinear models for higher-dimension tables); Section 7.3; additional material on overdispersion.


Discussion 9
No discussion this week; Prof. Hancock will have office hours during discussion time.



Thurs. Mar. 7
Lecture 15 Notes
Finish Lecture 14 notes; negative binomial regression.
Tue. Mar. 19
by 6pm
Take-home final exam handed out at the end of lecture.
Week 10:



Tue. Mar. 12
Lecture 16 Notes
Additional notes on equivalencies between odds ratios.
Section 5.5 on sample size and power; Section 6.1 on multinomial logistic regression.


Discussion 10
No discussion this week.



Thurs. Mar. 14
Lecture 17 Notes
Finish Lecture 16 notes; Section 6.2 on proportional odds models.
Additional references:


Final Exam:
Due by 6pm, Tue. Mar. 19.

Description of CHD data for Problem 4 of the final exam: chd_description.pdf

Final Exam Solutions
AIC Winners for Problem 4
(Disclaimer: AIC is not the only criteria for a good model!)
Final Exam Grading Information




Homework Solutions

Homework solutions will be posted the evening homework is due (or early the next morning).

Homework Assignment
Solutions
Homework #1
Homework #1 Solutions
Homework #2
Homework #2 Solutions
Homework #3
Homework #3 Solutions
Homework #4
Homework #4 Solutions
Homework #5
Homework #5 Solutions
Homework #6
Homework #6 Solutions