Scribd
Upload
6K views11 pages

Practice 1 From Analysis of Financial Time Series

This document contains R code and comments from the book "Analysis of Financial Time Series" by Ruey S. Tsay. The code analyzes various time series data, including stock prices of Apple and exchange rates between the US dollar and Euro. Various statistical analyses are performed, such as calculating correlations between time series using different methods, plotting time series data, and fitting distributions to returns.

Uploaded by

api-285777244
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
6K views11 pages

Practice 1 From Analysis of Financial Time Series

This document contains R code and comments from the book "Analysis of Financial Time Series" by Ruey S. Tsay. The code analyzes various time series data, including stock prices of Apple and exchange rates between the US dollar and Euro. Various statistical analyses are performed, such as calculating correlations between time series using different methods, plotting time series data, and fitting distributions to returns.

Uploaded by

api-285777244
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 11

Practice 1 from Analysis of Financial Time Series

YIK LUN, KEI


[email protected]
This paper is a practice from the book called Analysis of Financial Time Series
by Ruey S. Tsay. All R codes and comments below are belonged to the book
and author.

0.1
0.0
0.2

ibm

0.2

0.3

data=read.table("m-ibm6708.txt",header=T)
ibm=data$ibm
sp=data$sprtn
plot(sp,ibm)

0.2

0.1

0.0
sp

cor(ibm,sp,method="pearson")
## [1] 0.5949041
cor(sp,ibm,method="kendall")
## [1] 0.4223351
1

0.1

cor(sp,ibm,method="spearman") # rank correlation


## [1] 0.5897587
x=rank(ibm)
y=rank(sp)
cor(x,y)
## [1] 0.5897587
x=exp(rnorm(1000))
y=exp(20*rnorm(1000))
cor(x,y,method='pearson')
## [1] 0.002533287
cor(x,y,method='kendall')
## [1] 0.04594194
cor(x,y,method='spearman')
## [1] 0.06884192
data<-read.table("d-aapl0413.txt",header=T)
data.ts<-ts(data[,3],frequency=252,start=c(2004,1)) # Start from Jan and 252 weekdays
plot(data.ts,type='l',xlab='year',ylab='rtn')
title(main='Daily returns of Apple stock from 2004 to 2013')

0.05
0.15

rtn

0.05

0.15

Daily returns of Apple stock from 2004 to 2013

2004

2006

2008

2010
year

percentage=data.ts*100 #percentage returns


hist(percentage,nclass=50,main='Percentage returns')

2012

2014

100 150 200 250


0

50

Frequency

Percentage returns

15

10

percentage

d1<-density(percentage)
plot(d1$x,d1$y,xlab='returns',ylab='den',type='l',main="Density")

10

15

0.10
0.00

0.05

den

0.15

0.20

Density

20

15

10

returns

data1<-read.table("m-tb3ms.txt",header=T)
data2<-read.table("m-tb6ms.txt",header=T)
dim(data1);dim(data2)# unequal time frame
## [1] 914

## [1] 615

914-615 #difference
## [1] 299
window=cbind(data1[300:914,4],data2[,4]) # Window from 299 + 1
index=(c(1:dim(data2)[1])+11)/12+1959 # start from 1958 Dec
plot(index,window[,1],xlab='year',ylab='rate',type='l')
lines(index,window[,2],lty=2) # Plot the 6m-TB rate on the same frame

10

15

15
10
0

rate

1960

1970

1980

1990

2000

year

plot(index,window[,2]-window[,1],xlab='year',ylab='spread',type='l')
abline(h=c(0),col=2)

2010

1.5
1.0
0.5
0.0
1.0

0.5

spread

1960

1970

1980

1990
year

data=read.table("q-ko-earns8309.txt",header=T)
index=c(1:dim(data)[1])/12+1983
plot(index,data[,3],xlab='year',ylab='earnings',type='l')
title(main='EPS of Coca Cola: 1983-2009')
points(index,data[,3])

2000

2010

0.6
0.4
0.0

0.2

earnings

0.8

1.0

EPS of Coca Cola: 19832009

1984

1986

1988

1990

year

data=read.table("d-exuseu.txt",header=T) # Load USEU exchange rates


index=c(1:dim(data)[1])/252+1999
plot(index,data[,4],xlab='year',ylab='eu',type='l')
title(main='Dollars per Euro')

1992

1.2
0.8

1.0

eu

1.4

1.6

Dollars per Euro

2000

2002

2004

2006

2008

year

logrt=diff(log(data[,4])) # Compute log returns


plot(index[2:3567],logrt,xlab='year',ylab='rtn',type='l')
title(main='ln-rtn: US-EU')

2010

2012

0.00
0.02

rtn

0.02

0.04

lnrtn: USEU

2000

2002

2004

2006
year

hist(logrt,nclass=50,main='hist of ln-rtn: US-EU')

10

2008

2010

2012

100 200 300 400 500


0

Frequency

hist of lnrtn: USEU

0.02

0.00

0.02

0.04

logrt

Reference:
Tsay, Ruey S. Analysis of financial time series. Vol. 543. John
Wiley & Sons, 2005.

11

You might also like