03_R_intro - Time
Series
Analysis
 AMS
316


Info iconThis preview shows page 1. Sign up to view the full content.

View Full Document Right Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: Time
Series
Analysis
 AMS
316
 Programming
language
and
software
environment
 for
data
manipulation,
calculation
and
graphical
 display.
 Originally
created
by
Ross
Ihaka
and
Robert
 Gentleman
at
University
of
Auckland,
and
now
 developed
by
the
R
Development
Core
Team.
  T
IS
FREE
 I   re-compiled
binary
versions
are
provided
for
Microsoft
 P Windows,
Mac
OS
X,
and
several
other
Linux/Unix-like
 operating
systems
   pen
source
code
available
freely
available
on
GNU
 O General
Public
License
   or
computationally-intensive
tasks,
C,
C++
and
Fortran
 F code
can
be
linked
and
called
at
run
time
   n
effective
data
handling
and
storage
facility
 A   
suite
of
operators
for
calculations
on
arrays,
in
 A particular
matrices
   
large,
coherent,
integrated
collection
of
intermediate
 A tools
for
data
analysis
   raphical
facilities
for
data
analysis
and
display
either
 G directly
at
the
computer
or
on
hardcopy
 >help.start() > help(solve) > ?solve // get more information on “solve” > help(“[[“) > help.start()   // help for special characters and “if”, “for”… // launch a Web browser 1. R is case sensitive. 2. Commands can be executed by calling an external file. > source(“commands.R”) 3. The following functions can be used to display the names of (most of) the objects which are currently stored within R. > objects() > ls() 4. Objects can be removed by the following function. > rm(x, y, z) 1.  Vectors and asignments > x<- c(10.4, 5.6, 4.1) > assign(“x”, c(10.4, 5.6, 4.1) ) > y <- c(x, 0, 1/x) 2. 3. Vector arithmetic > v<-2*x + y +1 > sum( (x-mean(x))^2/length(x)-1) > sort(x) // returns a vector of the same size as x // with the elements arranged in increasing order. > max(x) > min(x) Sequence generation > z <- seq(-5, 5, by=0.2) > z <- rep(x, times=5) File
types
that
can
be
imported
into
R:




 
 
 .data,
.txt,
.xls,
.xlsx,
.html,
.xml,
etc.
 Example
of
importing
text
files
into
R:
 data<-read.table(“C:/……/data.txt”,
header=TRUE,
sep=“\t”)
 Other
data
import
commands:
scan()
……
 For
data
import/export:

 http://cran.r-project.org/doc/manuals/R-data.html
 Writing your own functions attach(dummy)
 
 //Make
the
columns
in
the
data
frame
visible
as
variables//

 lrf
<-
lowess(x,
y)
 
 //Make
a
nonparametric
local
regression
function//
 plot(x,
y)
 
 
 //Standard
point
plot//
 lines(x,
lrf$y)
 
 //Add
in
the
local
regression//
 abline(0,
1,
lty=3)
 
 //The
true
regression
line:
(intercept
0,
slope
1)//
 abline(coef(fm))
 
 //Unweighted
regression
line//
 abline(coef(fm1),
col
=
"red")
 //Weighted
regression
line//
 detach()
 
 
 //Remove
data
frame
from
the
search
path//
 plot(fitted(fm),

resid(fm), 
 








xlab="Fitted values", ylab="Residuals", 
 








main="Residuals vs Fitted")

 
 
 
 /*A
standard
regression
diagnostic
plot
to
check
for

 
 qqnorm(resid(fm),
main="Residuals
Rankit
Plot")
 
 
 
 /*A
normal
scores
plot
to
check
for
skewness,
kurtosis
and

 
 rm(fm,
fm1,
lrf,
x,
dummy)
 //Clean
up
again//
 Plot
Types:
Line
Charts,
Bar
Charts,
Histograms,
Pie
Charts,
Dot
 Charts,
etc.
 Format:
 >PLOT-TYPE(PLOT-DATA,
DETAILS)
 PLOT-TYPE:
plot,
plot.xy,
barplot,
pie,
dotchart,
etc.
 PLOT-DATA:
Data,
Data$XXX,
as.matrix(Data),
etc.
 Details:
axes,
col,
pch,
lty,
ylim,
type,
xlab,
ylab,
etc.
 For
graphics
plot:
 http://www.harding.edu/fmccown/R/
 A
comparison
of
GM
monthly
returns
&
SP500
 monthly
returns.
GM
and
SP500
monthly
return
 data
during
the
period
of
Jan.
2002
to
Jun.
2007
 are
taken.
Plotted
in
R,
they
will
be
analyzed
and
 compared.
 Data
from:
http://www.stanford.edu/~xing/ statfinbook/data.html
 GM<-read.table("C:/R
Data/GM.txt",
header=TRUE,
sep=“")
 SP<-read.table("C:/R
Data/SP.txt",
header=TRUE,
sep="")
 plot(GM)
 lines(GM$logret,
lty=1)
 lines(SP$logret,
type="o",
lty=1,
pch="+",
col="red")
 x<-1:66
 GML<-lm(GM$logret~x)
 SPL<-lm(SP$logret~x)
 abline(coef(GML),
type="h",
lwd=3)
 abline(coef(SPL),
col="red",
type="h",
lwd=3)
 Introduction to packages All
R
functions
and
datasets
are
stored
in
packages.
Only
when
a
 package
is
loaded
are
its
contents
available.
This
is

down
both
for
 efficiency,
and
to
aid
package
developers.
 To
see
which
packages
are
installed
at
your
site,
issue
the
 command
 >library(boot)
 Users
connected
to
the
Internet
can
use
install.packages()
and
 update.packages()
to
install
and
update
packages.
 To
see
packages
currently
loaded,
use
search().
 An easier way: use TS functions to plot time series. US unemployment rate from 1987 to 2007 are taken as a time series for analysis. Data from http://www.stanford.edu/~xing/statfinbook/data.html 2004~2006 1948~2007 An easier way: use TS functions to plot time series. US unemployment rate from 1987 to 2007 are taken as a time series for analysis. Data from http://www.stanford.edu/~xing/statfinbook/data.html ...
View Full Document

Ask a homework question - tutors are online