CHAPTER 12: EQUITY VALUATION
1.
P = 2.10/0.11 = 19.09
2.
(a) and (b).
3.
a.
This director is confused. In the context of the constant growth model, it is true
that price is higher when dividends are higher holding everything else
(including dividend growt
CHAPTER 11: MACROECONOMIC AND INDUSTRY ANALYSIS
1.
Expansionary (i.e., looser) monetary policy to lower interest rates would help to
stimulate investment and expenditures on consumer durables. Expansionary fiscal
policy (i.e., lower taxes, higher governme
CHAPTER 8: EFFICIENT MARKETS
AND THE BEHAVIORAL CRITIQUE
1.
The assumptions consistent with efficient markets are (a) and (c). Many
independent, profit-maximizing participants [statement (a)] leads to efficient
markets. Statement (c) is a consequence of t
CHAPTER 7: CAPITAL ASSET PRICING
AND ARBITRAGE PRICING THEORY
1.
a, c and d.
2.
a.
E(rX) = 5% + 0.8(14% 5%) = 12.2%
X = 14% 12.2% = 1.8%
E(rY) = 5% + 1.5(14% 5%) = 18.5%
Y = 17% 18.5% = 1.5%
b.
i. For an investor who wants to add this stock to a well-dive
CHAPTER 5: RISK AND RETURN: PAST AND PROLOGUE
1.
i and ii. The standard deviation is non-negative.
2.
c.
3.
Investment 4. For each portfolio: Utility = E(r) (0.5 3 2 )
Determines most of the portfolios return and volatility over time.
Investment
1
2
3
4
E
Final Exam
Date:
Time:
Venue:
11 Dec 2007
9:30 AM to 11:30 AM
Sir RR Shaw Hall
Part A:
30 MC questions (48%)
Part B:
4 non-MC questions (52%)
Show your calculations and steps for your answers. A single
numerical answer, even a correct one, will scor
CHAPTER 6: EFFICIENT DIVERSIFICATION
1.
E(rP) = (0.5 16%) + (0.4 10%) + (0.10 6%) = 12.6%
2.
a.
The mean return should be less than the value computed in the spreadsheet.
The fund's return is 5% lower in a recession, but only 3% higher in a boom.
The vari
NOTES 9
Forecasting:
Mean squares error prediction
Give a random vector (Y, X) , where Y is a scalar and X is a vector. We want to
get a function g (X) which predict Y as closely as possible, in the Mean squares error
sense, i.e
M SE = E [Y g (X)]2
is to
Notes 7
Parameter estimation:
In general, for AR(p), MA(q) and ARMA(p,q) models, what we want to estimate are
the series mean , the AR parameters s, the MA parameters s and the error variance
2
a .
Estimation methods:
1. Method of moment
2. Method based o
Notes 8
Diagnostics Checking:
Recall
Zt =
j Ztj + at
j =1
Put
at = Z t
j Ztj
j =1
Residual = actual value - estimated value
Residual Analysis
1. Plot residuals at against t (See whether trend exists)
2. Histogram of at (or standardized residuals), normal
Notes 6
Model Specication:
Overall strategy - Box Jenkins Approach:
1. To decide a reasonable - but tentative - values for p, d, q .
2
2. Estimate , and a , for that model.
3. Check the models adequacy.
4. If the model appears inadequate, consider the nat
CHAPTER 16: FUTURES MARKETS
1.
a.
2.
d.
3.
Total losses may amount to $525 before a margin call is received. Each contract
calls for delivery of 5,000 ounces. Before a margin call is received, the price per
ounce can increase by: $525/5,000 = $0.105 (or $
STA3008 Applied Regression Analysis
Instructor: Thomas C. M. Lee
Lecture 7: Drawing Conclusions (Part 1)
STA3008 Lecture 7 p. 1/
Drawing Conclusions
meaning of parameter estimates:
e.g., E(Y |X) = 15 + 3X1 + 4X2 2X3
coefcient for X1 is 3, meaning: an incr
STA3008 Applied Regression Analysis
Instructor: Thomas C. M. Lee
Lecture 8: WLS and LOF
STA3008 Lecture 8 p. 1/1
Weighted Least Squares (WLS)
relax the assumption Var(Y |X ) = 2
2
wi
change to Var(Y |X = xi ) = Var(ei ) =
where w1 , , wn are known positiv
STA3008 Applied Regression Analysis
Instructor: Thomas C. M. Lee
Lecture 7: Polynomials and Factors
STA3008 Lecture 7 p. 1/1
Polynomials
what shall we do if lack of t exists?
we could do nothing and just sit there and cry
or we could improve our model
Pol
STA3008 Applied Regression Analysis
Instructor: Thomas C. M. Lee
Lecture 4: After Fitting
STA3008 Lecture 4 p. 1/2
Comparing Models
known as Analysis of Variance
a simplest example: comparing the following two
regression models
E(Y |X = x) = 0 with E(Y |X
STA3008 Applied Regression Analysis
Instructor: Thomas C. M. Lee
Lecture 7: Drawing Conclusions (Part 2)
STA3008 Lecture 7 p. 1/
How to handle missing data?
rst we need to understand why some data are missing
"missing at random" (MAR) is the easiest to ha
STA3008 Applied Regression Analysis
Instructor: Thomas C. M. Lee
Lecture 6: More on Multiple Linear Regression
STA3008 Lecture 6 p. 1/1
Fuel Consumption Data
goal: fuel consumption changes over different places in
the U.S.
Y : Fuel, fuel comsumption adjus
STA3008 Applied Regression Analysis
Instructor: Thomas C. M. Lee
Lecture 2: Basic
STA3008 Lecture 2 p. 1/?
Review of Basic (Appendix A.2 of Text)
Let u1 , . . . , un be n random variables.
Let a0 , . . . , an be u + 1 constants.
E(ui ): expectation of
STA3008 Applied Regression Analysis
Instructor: Thomas C. M. Lee
Mid-Semester Review
STA3008 Mid-Semester Review p. 1/
Why Do We Study Statistics?
want to make money, answer questions, have fun .
one method: statistical modeling
lazy and stupid
regression
STA3008 Applied Regression Analysis
Instructor: Thomas C. M. Lee
Lecture 3: Properties of OLS Estimators
STA3008 Lecture 3 p. 1/1
Estimating 2
2 is essentially the average size of e2
i
2 can be obtained by dividing RSS =
by its degrees of freedom (df )
STA3008 Applied Regression Analysis
Instructor: Thomas C. M. Lee
Lecture 1: Why do we study statistics?
STA3008 Lecture 1 p. 1/
An Important Question
Why do we study statistics?
Because we are lazy and stupid!
STA3008 Lecture 1 p. 2/
Course Title: Applied
Mid-term exam
FIN3080 E
Class average:
1 S.D.:
Distribution:
26.90
2.86
32 (2)
31 (2)
30 (5)
29 (5)
Correct answers
1
2
3
4
5
6
7
8
C
D
B
B
B
D
A
C
17
18
19
20
21
22
23
24
C
A
B
B
C
A
B
B
9
10
11
12
13
14
15
16
B
B
B
C
A
D
C
C
25
26
27
28
29
30
31
32
C
B
CHAPTER 19: BEHAVIORAL FINANCE
AND TECHNICAL ANALYSIS
1.
Trin =
Volume declining / Number declining
582,866 / 1,488
=
= 0.883
Volume advancing / Number advancing 712,318 / 1,606
This trin ratio, which is below 1.0, would be taken as a bullish signal.
2.
R
STA3008 Applied Regression Analysis
Instructor: Thomas C. M. Lee
Lecture 5: Multiple Linear Regression
STA3008 Lecture 5 p. 1/1
Multiple Regression
generalizes the simple linear regression model by
allowing more terms than just the intercept and slope
a s