STATISTCS 200C: Intermediate Probability and Statistical Theory
(Theory of linear models)
Lecture notes: Review of linear algebra, LSE, Estimable functions (1, 2), Computational Issues
Multivariate Normal (1, 2) , Chisquared and quadratic forms, Cochran’s theorem, Ftest, examples, asymptotic results,
Simultaneous regions, randomeffect models, model diagnostics
Homework assignments: homework 1, homework 2, homework 3, homework 4, homework 5 , homework 6 (due on)
Practice exam: stat200c final (2016), solution
Description and
Objectives
Stat200C is the last of a threequarter series on intermediate probability and statistical theory. The objective of this course is to develop the theoretical basis of statistical methods for linear models.
Meeting times and location: 12:30pm on every Monday and Wednesday @ MSTB122
Stats 200C INT PROB & STAT THY (Prerequisites) 

Code 
Type 
Sec 
Units 
Instructor 
Time 
Place 
Final 
Max 
Enr 
WL 
Req 
Rstr 
Textbooks 
Web 
Status 
37840 
Lec 
A 
4 
YU,
Z. 
MW
12:30 1:50p 
Wed,
Jun 13, 4:006:00pm 
31 
30 
1 
31 
K
and A 
Waitl 

37841 
Dis 
1 
0 
YU,
Z. 
W
2:00 2:50p 

31 
30 
1 
30 
K
and A 

Waitl 
Office hours: 10 am on every Thursday
The following book is
highly recommended:
Seber, G.A., and Lee, A.J. (2003).
Linear regression analysis (2^{nd} edition). Wiley Interscience.
Reference Texts:
Neter, J., Kutner, MH., Nachtsheim, CJ., and Wasserman, W. (2005). Applied linear statistical models, 5^{th} edition. McGrawHill Irwin.
Casella, G. and Berger, R. (2001). Statistical inference (2^{nd} edition). Duxbury Press.
Grading
The grade is based upon about seven homework assignments (20%), a midterm (40%) and a final exam (40%). No late homework will be accepted.
Important Dates
Both the midterm and the final are closedbook and inclass. The final exam will cover the material presented in 200C.
Prerequisites
Statistics 200B (or equivalent), or permission from instructor. Students are assumed to be familiar with linear algebra, basic properties of multivariate distribution, and basic convergence theorems of random variables. Prior exposure to applied linear regression is also desirable.
Topics