Introduction to Statistical Methods for Financial Models 1st Severini Solution Manual - Latest Version Can Be Downloaded Immediately
Introduction to Statistical Methods for Financial Models 1st Severini Solution Manual - Latest Version Can Be Downloaded Immediately
https://testbankmall.com/product/introduction-to-
statistical-methods-for-financial-models-1st-severini-
solution-manual/
https://testbankmall.com/product/solution-manual-for-an-introduction-
to-statistical-methods-and-data-analysis-7th-edition/
https://testbankmall.com/product/numerical-methods-and-optimization-
an-introduction-1st-butenko-solution-manual/
https://testbankmall.com/product/statistical-methods-for-
psychology-8th-edition-howell-solutions-manual/
https://testbankmall.com/product/test-bank-for-essentials-of-lifespan-
development-3th-edition-john-santrock/
Test Bank for Research Stories for Introductory
Psychology, 3/E 3rd Edition : 0205520650
https://testbankmall.com/product/test-bank-for-research-stories-for-
introductory-psychology-3-e-3rd-edition-0205520650/
https://testbankmall.com/product/test-bank-for-statistics-informed-
decisions-using-data-6th-edition-michael-sullivan-iii/
https://testbankmall.com/product/test-bank-for-genetics-from-genes-to-
genomes-5th-edition-by-hartwell/
https://testbankmall.com/product/test-bank-for-blueprint-reading-for-
welders-9th-edition/
https://testbankmall.com/product/solution-manual-for-applied-statics-
and-strength-of-materials-6th-edition-6th-edition/
Test Bank for Human Nutrition: Science for Healthy Living,
2nd Edition, Tammy Stephenson, Wendy Schiff, ISBN10:
1259709957, ISBN13: 9781259709951
https://testbankmall.com/product/test-bank-for-human-nutrition-
science-for-healthy-living-2nd-edition-tammy-stephenson-wendy-schiff-
isbn10-1259709957-isbn13-9781259709951/
2.5. Adjusted prices are given by P̄3 = P3 = $5.40,
D3
P̄2 = 1− P2 = P2 = $4.80
P2
and
D2 D3 0.40
P̄1 = 1− 1− P1 = 1− 4.00 = $3.60.
P1 P2 4.00
7
8 2 Solutions for Chapter 2
(b) Let P̄t , t = 0, 1, 2, . . . , T denote the sequence of adjusted prices. Then P̄T = PT ,
DT
P̄T −1 = 1 − PT −1 = (1 − α) PT −1 ,
PT −1
DT DT−1 2
P̄T −2 = 1− 1− PT −2 = (1 − α) PT −2
PT −1 PT −2
P̄T −k = (1 − α)k PT −k .
2.7. Consider
Let γY denote the covariance function of {Yt : t = 1, 2, . . .} and let γX denote the covariance
function of {Xt : t = 1, 2, . . .}. Since these processes are both weakly stationary,
However, since we do not know anything about the covariance of Yt and Xs , it does not follow
that the process Y1 + X1 , . . . is weakly stationary. For instance, if Yt and Xs are uncorrelated
for all t, s, then it is weakly stationary. However, if the correlation of Yt and Xs is 1/2 if
t = s = 1 and 0 otherwise, then the process is not weakly stationary.
(c) The mean and variance functions of the process are constant. Consider the term in the
covariance function
γ(|t − s − 1|) + γ(|t − s + 1|).
If t = s this is 2γ(|1|) = 2γ(|t − s| + 1). If t ≥ s + 1, then
Similarly, if t ≤ s − 1,
2.9. (a) E(Xt ) = E(ZZt ) = E(Z)E(Zt ) = 0; hence, the mean function is 0. Let µ = E(Zt )
and σ 2 = Var(Zt ). Since E(X 2t) = E(Z 2 Z 2t) = E(Z 2 )E(Zt2 ) = (σ 2 + µ2 ), the variance
function of the process is σ 2 + µ2 .
(b) Since E(Xt ) = 0 for all t,
(c) Since the mean and variance functions are constant and the X1 , X2 , . . . are uncorrelated,
it follows that {Xt : t = 1, 2, . . .} is a white noise process. Hence, it is also weakly
stationary.
2.10. Since E(rt ) does not depend on t, clearly E(r̃t ) does not depend on t. Let σ 2 = Var(rt )
and consider Var(r̃t ). Using the fomula for the variance of a sum,
X
Var(r̃t ) = 21σ 2 + 2 Cov(r̃21(t −1)+i , r̃21(t−1)+j )
i<j
where the sum in this expression is over all i, j from 1 to 21 such that i < j. Note that, since
{rt : t = 1, 2, . . .} is weakly stationary,
where γ(·) is the autocovariance function of {rt : t = 1, 2, . . .}. It follows that Var(r̃t ) does
not depend on t.
Now consider Cov(r̃t , r̃s ) for t = s. Note that
21 X
X 21
Cov(r̃t , r̃s ) = Cov(r21(t −1)+j , r21(s−1)+i ).
j=1 i=1
so that Cov(r̃t , r̃s ) depends on t, s only through |t − s|. It follows that {r̃t : t = 1, 2, . . .} is
weakly stationary.
Consider Cov(Yi , Yk ), where i < k. If k > i + w, then Yi and Yk have no terms in common so
that Cov(Yi , Yk ) = 0. Otherwise, the sums
Xi+w X
k+w
Xj and X`
j=i+1 `=k+1
Since E(Yk ) and Var(Yk ) are constant and Cov(Yi , Yk ) depends only on k − i, it follows that
the process Y1 , . . . , Yn−w is weakly stationary with mean function µ and variance function
σ 2 /w.
The correlation of Yi and Yk is
((i−k+ w)/w 2 )σ 2 k−i
= 1−
σ /w
2
w
so that the correlation function of the process is
|h|
ρ(h) = 1 − , h = 1, 2, . . . .
w
2 Solutions for Chapter 2 11
2.12. (a) Let µX = E(Xt ), σ 2X = Var(Xt ), µY = E(Yt ), and σ 2Y = Var(Yt ). Then
so that
Var(Xt Yt ) = (µ2 + σ 2 )(µ2 + σ 2 ) − µ2 µ2 , t = 1, 2, . . . .
X X Y Y X Y
Similarly, for t = s,
E(Xt Yt Xs Ys ) = µX µY µX µY = µ2X µ2Y
so that
Cov(Xt Yt , Xs Ys ) = µ2 µ2 − (µX µY )2 = 0.
X Y
2.13. (a) The following R commands may be used to download the necessary price data.
> library(tseries)
> x<-get.hist.quote(instrument="PZZA", start="2012-12-31", end="2015-12-31",
+ quote="AdjClose", compression="d")
> pzza0<-as.vector(x)
(b) The returns corresponding to the prices downloaded in part (a) may be calculated using
the commands
> length(pzza0)
[1] 757
> pzza<-(pzza0[-1]-pzza0[-757])/pzza0[-757]
> summary(pzza)
Min. 1st Qu. Median Mean 3rd Qu. Max.
-0.1210 -0.0074 0.0010 0.0011 0.0097 0.0804
12 2 Solutions for Chapter 2
0.05
0.00
Daily Return
−0.05
−0.10
Time
FIGURE 2.1
Plot in Exercise 2.13
(d) The time series plot of the returns may be constructed using the commands
2.14. (a) The following R commands may be used to download the necessary price data.
> library(tseries)
> x<-get.hist.quote(instrument="PZZA", start="2010-12-31", end="2015-12-31",
+ quote="AdjClose", compression="m")
> pzza0<-as.vector(x)
(b) The returns corresponding to the prices downloaded in part (a) may be calculated using
the commands
> length(pzza0)
[1] 61
> pzza.m<-(pzza0[-1]-pzza0[-61])/pzza0[-61]
> summary(pzza.m)
Min. 1st Qu. Median Mean 3rd Qu. Max.
-0.1780 -0.0072 0.0216 0.0265 0.0696 0.1890
(d) The time series plot of the returns may be constructed using the commands
0.0
−0.1
0 10 20 30 40 50 60
Time
FIGURE 2.2
Plot in Exercise 2.14
2.15. The running means may be calculated and the plot constructed using the following
commands.
> library(gtools)
> pzza.rmean<-running(pzza.m, fun=mean, width=12)
> mean(pzza.m) + 2*sd(pzza.m)/(12^.5)
[1] 0.0677
> mean(pzza.m) - 2*sd(pzza.m)/(12^.5)
[1] -0.0147
> plot(pzza.rmean, type="l", ylim=c(-.02, .07), xlab="Time", ylab="Return")
14 2 Solutions for Chapter 2
0.02
0.00
−0.02
0 10 20 30 40 50
Time
FIGURE 2.3
Plot in Exercise 2.15
2.16. The running standard deviations may be calculated and the plot may be constructed
using the following commands.
> pzza.rsd<-running(pzza.m, fun=sd, width=12)
> log(sd(pzza.m)) + (2/11)^.5
[1] -2.21
> log(sd(pzza.m)) - (2/11)^.5
[1] -3.07
> plot(log(pzza.rsd), type="l", ylim=c(-3.6, -2), ylab="log of running sd",
+ xlab="time")
> title(main="Log of Running SDs of Returns on Papa John’s Stock")
> lines(1:49, rep(-2.21, 49), lty=2)
> lines(1:49, rep(-3.07, 49), lty=2)
The plot is given in Figure 2.4. According to this plot, there is some evidence of non-
stationarity of the returns. There is a relatively long period of relatively small variability, as
well as brief periods of relatively large variability.
2 Solutions for Chapter 2 15
−2.0
−2.5
log of running sd
−3.0
−3.5
0 10 20 30 40 50
time
FIGURE 2.4
Plot in Exercise 2.16
2.17. The autocorrelation function based on the daily returns may be calculated using the
command
> print(acf(pzza, lag.max=20))
0 1 2 3 4 5 6 7 8 9 10
1.000 -0.011 -0.013 0.050 -0.013 -0.061 0.005 -0.036 0.062 0.052 -0.007
11 12 13 14 15 16 17 18 19 20
-0.027 0.044 -0.016 -0.023 0.027 0.029 -0.018 0.032 0.008 -0.028
The plot is given in Figure 2.5.
The estimated autocorrelation function based on the monthly returns is given by
> print(acf(pzza.m, lag.max=12))
0 1 2 3 4 5 6 7 8 9 10
1.000 0.167 -0.009 -0.061 -0.057 -0.179 -0.146 -0.053 0.103 -0.218 -0.064
11 12
0.049 0.015
16 2 Solutions for Chapter 2
Series pzza
1.0
0.8
0.6
ACF
0.4
0.2
0.0
0 5 10 15 20
Lag
FIGURE 2.5
ACF for Daily Returns in Exercise 2.17
The plot is given in Figure 2.6. The autocorrelations are all small and, hence, the results
are consistent with the assumption that the returns are uncorrelated random variables.
Series
pzza.m
1.0
0.8
0.6
0.4
ACF
0.2
0.0
−0.2
0 2 4 6 8 10 12
Lag
FIGURE 2.6
ACF for Monthly Returns in Exercise 2.17
2 Solutions for Chapter 2 17
2.18. The daily returns on Papa John’s stock are stored in the R variable pzza. To construct
a normal probability plot of these data, we may use the commands
> qqnorm(pzza)
> abline(a=mean(pzza), b=sd(pzza))
The plot is given in Figure 2.7. The plot is very similar to the one in Figure 2.11 in the
text; it suggests that the distribution of the daily returns on Papa John’s stock is long-tailed
relative to a normal distribution.
Normal Q−Q
Plot
●
0.05
● ●
●
●●
●●
●●
●●
●●
●●
●
●
●●
● ●
●
●●
●
●●●
● ●
●
●●●
●●●
●
●●●●
●●●●
●●●
●●
●●
● ●●
●●●
●●●●
●●
●●
0.00
●
●
●●●●
●●
●●●
●
●
●●
Sample Quantiles
●
●●
●
●
●●●
● ●●
●●●
●
●●
● ●●
●●●
●● ●●●
●●
●●●
●●●●●
●
●
●
●
●●●●
●
●●●●
●
●●●
●
●●
●●
●●
●
●●
●
●
●●●
●
−0.05
●
●●
●
●
−0.10
−3 −2 −1 0 1 2 3
Theoretical Quantiles
FIGURE 2.7
Q-Q Plot for Daily Returns in Exercise 2.18
The monthly returns on Papa John’s stock are stored in the R variable pzza.m. To
construct a normal probability plot of these data, we may use the commands
> qqnorm(pzza.m)
> abline(a=mean(pzza.m), b=sd(pzza.m))
The plot is given in Figure 2.8. The plot suggests that the distribution of the monthly
returns on Papa John’s stock is more nearly normal than is the distribution of daily returns,
although there is some evidence of asymmetry, with a slightly-long left tail.
18 2 Solutions for Chapter 2
Normal Q−Q
Plot
0.2
●
●
●
●
●● ●
0.1
●
●●
●●
●●●
●●●
Sample Quantiles
●●●
●●
●●●●●●●
●●●●●
●●●
0.0
●●●●
●●●●
●
●●
●
●
●●
●
●
●
−0.1
−2 −1 0 1 2
Theoretical Quantiles
FIGURE 2.8
Q-Q Plot for Monthly Returns in Exercise 2.18
Other documents randomly have
different content
The Project Gutenberg eBook of The Story of
Don John of Austria
This ebook is for the use of anyone anywhere in the United
States and most other parts of the world at no cost and with
almost no restrictions whatsoever. You may copy it, give it away
or re-use it under the terms of the Project Gutenberg License
included with this ebook or online at www.gutenberg.org. If you
are not located in the United States, you will have to check the
laws of the country where you are located before using this
eBook.
Language: English
DON JOHN
OF AUSTRIA
Photo Anderson.
Don John of Austria.
DON JOHN
OF AUSTRIA
PAGE
BOOK I 3
BOOK II 105
BOOK IV 315
ILLUSTRATIONS
Don Fernando Alvarez de Toledo. 3rd Duque de Alba, called the "Gran
Duque," 1507-82
164
Married Maria Enriquez, daughter of the Conde de Alba de Lesten. Captain-
General of the Kingdoms of Castille and Aragon, of the Spanish troops in Italy, and
of the army in Portugal. Governor of Milan and Viceroy of Naples. Governor of
Flanders. Councillor of State and War to Charles V and Philip II, whose tutor he
was. He acted as Proxy for the King at Philip II's third and fourth marriages.
Recalled from Flanders in 1573, he fell into disgrace with Philip II, and was
imprisoned in the Castle of Uceda. He was liberated in order that he might pacify
the Portuguese rebellion. In 1580 he won the battles which gained this Kingdom
for Spain. He died at Lisbon.
This portrait by Titian represents the Duke at about the age of forty. He wears
black armour wrought with gold and a red sash, and the balustrade on which he
leans is cushioned with red velvet. It may very possibly have belonged to the Duke
himself; it certainly was in the possession of the celebrated Conde Duque de
Olivares, as it was amongst those entailed by him with the Carpio estate. With this
property it passed to the Alba family, and from thence was brought to its present
place in the Palacio de Liria in Madrid.
Cardinal de Granvelle
261
Born 1517. Died 1586.
Antoine Perrenot. Bishop of Arras. Primate of the Netherlands.
A well-known statesman during the reigns of Charles V and Philip II. Chief
Councillor to the Duchess of Parma when Governess of the Netherlands. He
became so unpopular that in 1564 Philip II was compelled to advise him to retire
to his estates in Burgundy. The Cardinal left vowing that he would not cut his
beard until he returned to Brussels. Three years later he went to Rome, where he
assisted in the negotiations of the Holy League. He subsequently became Viceroy
of Naples.
From his picture by Scipione Pulzone called Gaetano in Municipal Museum,
Besançon.
Princesa de Évoli
427
Born 1540.
Daughter of the Count de Melito. Married in 1553 Ruy Gomez de Silva,
afterwards Prince of Évoli, who died 1573.
She was a great heiress, and her family accused Antonio Pérez of squandering
her fortune. There now seems little doubt that anger at the discovery of her
intrigue with him was the chief reason of the assassination of the Secretary
Escovedo.
Philip II caused her to be arrested suddenly in 1579, and imprisoned first in the
tower of Pinto, and then exiled to her own house at Pastrana for the rest of her
life.
The picture from which the print used is taken is by Sanchez Coello, in the
possession of her descendant, the Duque de Pastrana.
Philip II as an Old Man
437
"This picture is well worthy of note, as it shows how the crowned monk of the
Escorial looked when on the brink of the grave. In Pantoja's worn, sickly, sour old
man, with lack-lustre, restless eyes, protruding under-lip and
'pallid cheeks and ashy hue
in which sad death his portraiture hath writ',
(Spenser)
wearing a rusty sugar-loaf hat and holding in his hand a common brown rosary,
we see the last stage of the sumptuous Prince whose youthful bearing has been
made immortal by the pencil of Titian."
(Sir William Stirling Maxwell.)
By Juan Pantoja de la Cruz in the Prado Gallery, Madrid.
testbankmall.com