1. Give the formula for the covariance between two random variables and , if and are
a. discrete b. continuous.
2. Let Z be a random variable, which is a linear combination of random variables and such that where and are constants. Derive an expression for a. the mean of, b. the variance of
3. Derive, algebraically, the inflation-adjusted one-period simple asset return formula.
4. Suppose the random variable measures the rate of return on a single investment. What is the significance of the mathematical expectation of this random variable in investment decisions?
5. What information does the 4th moment of a probability distribution of a random variable convey? Why this information is considered important in finance?
6. Explain why the normal distribution is not always appropriate for characterizing asset returns? What solution would you propose to this problem?
7. Decide if you agree or disagree with each of the following statements and give a brief explanation of your decision:
(a) Like cross-sectional observations, we can assume that most time series observations are independently distributed.
(b) A trending variable cannot be used as the dependent variable in multiple regression analysis.
(c) Seasonality is not an issue when using annual time series observations.
8. Under which three Gauss-Markov assumptions is the OLS estimator unbiased in a time series regression? Briefly discuss each one.
9. Suppose you have quarterly data on new housing starts, interest rates and real per capita income. Specify a model for housing starts that accounts for possible trends and seasonality in the variables. How would you interpret the estimated coefficients?
10. You are asked to estimate a simple regression model relating the growth in real per capita consumption (of nondurables and services) to the growth in real per capita disposable income. The results are as follows (using the change in the logarithms in both cases):
12. What are the main assumptions underlying the basic OLS regression model. Outline the importance of each assumption for OLS estimation and discuss how would you empirically test each assumption?
13. A partial adjustment model is:
Where yt* is the desired or optimal level of y, and yt is the actual (observed) level. The second equation describes how the actual y adjusts depending on the relationship between the desired y in time t and the actual y in time t-1.
(a) How would you interpret parameters y1and (0<λ<1)?