Home
Syllabus
Homework
Notes
Excel Hints
R Hints
Announcements
Links
Project
Review
Discussion Board |
Last updated:
August 11, 2011
The final exam will cover all the material from the course syllabus. The final exam will be
concept oriented but there will also be some calculation involved so bring a calculator. I
will not ask you to do proofs or long derivations. The best place to start your studying
is with the homework assignments. Solutions for the homework assignments are on the
homework page. Check the Notes page for
updates of the class lecture notes.
The exams will be closed book and closed note exam. However, I will
allow one page (double sided) of handwritten or typed notes
Topics to be covered for the Midterm
- Return calculations
- simple and continuously compounded returns
- time aggregation
- Review of random variables
- Shape characteristics (mean, variance,
skewness, kurtosis)
- quantiles
- normal distribution
- linear functions of random variables
- covariance and correlation
- characteristics of portfolios with risky
assets
- Matrix Algebra
- Compute portfolio expected return and variance
using matrix algebra
- Time Series Concepts
- covariance stationarity
- Autocorrelations
- MA(1) and AR(1) models
- Descriptive statistics
- histograms, boxplots, qq-plots
- sample statistics (univariate, bivariate,
time series)
- Constant expected return model
- model assumptions and interpretation
- relationship to random walk model
- Monte Carlo simulation
Topics to be emphasized on
the Final Exam
Constant expected return model
- estimation, standard errors and confidence
intervals
- hypothesis testing (t-tests, normality tests,
rolling estimation)
Introduction to portfolio theory
- characteristics of portfolios with risky and
riskless assets
- portfolio frontier
- efficient portfolios
- global minimum and tangency portfolios
- risk budgeting
Portfolio Theory with Matrix
Algebra
- Express Markowitz algorithm for finding efficient
portfolios using matrix algebra
Single Index Model
- Can you interpret the single index regression: Ri
= ai + bi*Rm
+ ei ?
- How do you compute the covariance matrix using the single index
model?
Final Exams
|