Abraham, B., Ledolter, J., Introduction to Regression Modeling, Doxbury, 2006.
Rice, J., Mathematical Statistics and Data Analysis, Duxbury Press (Third Edition)
...
SYLLABUS FOR STATISTICS 100C - LECTURE 1 LINEAR MODELS SPRING QUARTER 2012 Instructor: Nicolas Christou Office: 8931Math Sciences Bldg. Telephone: (310) 206-4420 e-mail:
[email protected] WWW: http://www.stat.ucla.edu/~nchristo/statistics100C Office hours: MWF 14:00 - 16:00, T 12:00 - 14:00 Lecture Lecture 1 Lecture 1A
Day R
Day MWF
Class Time 12:00 - 12:50
Discussion Time 14:00 - 14:50
Location MS 5128
Location KAUFMAN 101
COURCE RESOURCES: Textbooks (optional): Abraham, B., Ledolter, J., Introduction to Regression Modeling, Doxbury, 2006. Rice, J., Mathematical Statistics and Data Analysis, Duxbury Press (Third Edition), 2006. In-class handouts can be accessed at Handouts can be accessed at http://www.stat.ucla.edu/~nchristo/statistics100C. Probability and Statistics EBook (freely available at): http://wiki.stat.ucla.edu/socr/index.php/EBook. Software: R (can be downloaded freely from http://cran.stat.ucla.edu), and Statistics Online Computational Resource (SOCR), freely available at: http://www.socr.ucla.edu. COURSE DESCRIPTION AND OBJECTIVES: The focus of this course is on regression analysis and the analysis of variance. Emphasis will be given to the matrix approach of regression analysis and in analyzing data sets from various fields using the open source statistical package R. Students are expected to be familiar with discrete and continuous random variables, expectation, variance, covariance, and correlation, joint, marginal, and conditional distributions (Statistics 100A), Central limit theorem, χ2 , t, and F distributions, properties of estimators, method of maximum likelihood, statistical tests (Statistics 100B). COURSE TOPICS 1. Simple linear regression - Method of least squares. 2. Statistical properties of least squares. 3. Assessing the fit. 4. Multiple regression. 5. Matrix approach to least squares. 6. When is least squares a good method? 7. Assumptions of the regression model - Complications. 8. Heteroscedasticity, multicollinearity. 9. Generalized least squares. 10. Analysis of variance (one-way, two-way). 11. Bivariate normal. 12. Principal component analysis. COURSE POLICIES: Please remember to turn off cell phones. The use of laptop computers will not be permitted in class. You are expected to adhere to the honor code and code of conduct. If you have a disability that will require academic accommodation, please contact the UCLA Office for Students with Disabilities (OSD).
COURSE GRADES: There will be two (2) midterms, a final exam (cumulative), homework, and labs that will be assigned every week. Please write your name and staple your homework and labs. Late homework or labs will not be accepted and make-up exams will not be given. Being in class on time and fully participating is important for your understanding of the material and therefore for your success in the course. The tentative dates/times for the exams are shown below. The course grade will be based on the calculation: F inal score
=
0.10 × Homework/Labs + 0.25 × M idterm1 + 0.25 × M idterm2 + 0.40 × F inal
Communication: In-class handouts can be accessed at http://www.stat.ucla.edu/~nchristo/statistics100C. Please keep a current e-mail address with my.UCLA.edu in order to receive class announcements and reminders. Important dates: First day of classes: 02 April. Holidays: 28 May (Memorial Day). Last day of classes: 08 June. Exam 1: Week 4. Exam 2: Week 7. Exam 3: Week 10. Good Luck !!!
