Time Series

library(astsa) # SEE THE FOOTNOTE

head(jj)

## [1] 0.71 0.63 0.85 0.44 0.61 0.69

plot(jj, type="o",
ylab="Quarterly Earnings per Share",
main="Johnson & Johnson quarterly earnings per share,
\n84 quarters, 1960-I to 1980-IV.")
grid()

Johnson & Johnson quarterly earnings per share,

84 quarters, 1960−I to 1980−IV.

15
Quarterly Earnings per Share

10
5
0

1960 1965 1970 1975 1980

Time

head(globtemp)

## [1] -0.20 -0.11 -0.10 -0.20 -0.28 -0.31

1
plot(globtemp, type="o",
ylab="Global Temperature Deviations",
main="Yearly average global temperature deviations
\n(1880–2015) in degrees centigrade.")
grid()

Yearly average global temperature deviations

(1880–2015) in degrees centigrade.

0.8
Global Temperature Deviations

0.4
0.0
−0.4

1880 1900 1920 1940 1960 1980 2000 2020

Time

head(speech)

## [1] 1814 1556 1442 1416 1352 1154

plot(speech,
main="Speech recording of the syllable aaa hhh
\nsampled at 10,000 points per second
with n = 1020 points.")
grid()

# library(TTR)
# djia = getYahooData("ˆDJI", start=20060420, end=20160420, freq="daily")
library(xts)

## Loading required package: zoo

##
## Attaching package: ’zoo’

2
## The following objects are masked from ’package:base’:
##
## as.Date, as.Date.numeric

Speech recording of the syllable aaa hhh

sampled at 10,000 points per second

with n = 1020 points.
4000
3000
speech

2000
1000
0

0 200 400 600 800 1000

Time

djiar = diff(log(djia$Close))[-1] # approximate returns

head(djiar,10)

## Close
## 2006-04-21 0.0004019814
## 2006-04-24 -0.0009813081
## 2006-04-25 -0.0046924330
## 2006-04-26 0.0062939559
## 2006-04-27 0.0024646652
## 2006-04-28 -0.0013512402
## 2006-05-01 -0.0021003229
## 2006-05-02 0.0064289317
## 2006-05-03 -0.0014173744
## 2006-05-04 0.0033784210

plot(djiar, main="DJIA Returns", type="n")

3
 DJIA Returns 2006−04−21 / 2016−04−20

0.10 0.10

0.05 0.05

0.00 0.00

−0.05 −0.05

Apr 21 2006 Apr 01 2008 Apr 01 2010 Apr 02 2012 Apr 01 2014 Mar 31 2016

lines(djiar)

4
 DJIA Returns 2006−04−21 / 2016−04−20

0.10 0.10

0.05 0.05

0.00 0.00

−0.05 −0.05

Apr 21 2006 Apr 01 2008 Apr 01 2010 Apr 02 2012 Apr 01 2014 Mar 31 2016

#par(mfrow = c(2,1)) # set up the graphics

head(soi,10)

## [1] 0.377 0.246 0.311 0.104 -0.016 0.235 0.137 0.191 -0.016 0.290

plot(soi, ylab="", xlab="",

main="Southern Oscillation Index")
grid()

5
 Southern Oscillation Index
1.0
0.5
0.0
−0.5
−1.0

1950 1960 1970 1980

head(rec,10)

## [1] 68.63 68.63 68.63 68.63 68.63 68.63 59.16 48.70 47.54 50.91

plot(rec, ylab="", xlab="",

main="Recruitment")
grid()

6
 Recruitment
100
80
60
40
20
0

1950 1960 1970 1980

#par(mfrow=c(2,1))
head(fmri1)

## time cort1 cort2 cort3 cort4 thal1 thal2 cere1 cere2

## [1,] 1 -0.336 -0.088 -0.579 -0.221 -0.222 -0.046 -0.354 -0.028
## [2,] 2 -0.192 -0.359 -0.475 -0.058 0.072 -0.039 -0.346 -0.032
## [3,] 3 0.062 0.062 0.063 0.192 0.145 -0.256 -0.337 0.272
## [4,] 4 0.128 0.221 0.234 -0.004 -0.104 -0.030 0.149 0.042
## [5,] 5 0.358 0.199 0.388 0.255 0.035 -0.081 0.311 -0.080
## [6,] 6 0.342 0.054 0.377 0.430 -0.005 0.047 0.403 -0.016

ts.plot(fmri1[,2:5], col=1:4,
ylab="BOLD", main="Cortex")
grid()

7
 Cortex
0.2 0.4 0.6
BOLD

−0.2
−0.6

0 20 40 60 80 100 120

Time

ts.plot(fmri1[,6:9], col=1:4,
ylab="BOLD", main="Thalamus & Cerebellum")
grid()

8
 Thalamus & Cerebellum
0.6
0.4
0.2
BOLD

−0.2 0.0
−0.6

0 20 40 60 80 100 120

Time

#par(mfrow=c(2,1))
head(EQ5)

## [1] 0.017493160 0.011390780 0.015123990 0.014765020 0.006508857

## [6] -0.002321631

plot(EQ5, main="Earthquake")
grid()

9
 Earthquake
0.4
0.2
EQ5

0.0
−0.4 −0.2

0 500 1000 1500 2000

Time

head(EXP6)

## [1] -0.0018374320 -0.0005537868 -0.0022838710 -0.0003026128 -0.0007212162

## [6] -0.0013909340

plot(EXP6, main="Explosion")
grid()

10
 Explosion
0.4
0.2
EXP6

0.0
−0.4 −0.2

0 500 1000 1500 2000

Time

w = rnorm(500,0,1) # 500 N(0,1) variates

head(w)

## [1] -1.0847192 -0.3184344 -0.2262302 -1.3686771 0.2253452 1.0836716

v = filter(w, sides=2, filter=rep(1/3,3)) # moving average

head(v)

## [1] NA -0.54312792 -0.63778055 -0.45652068 -0.01988675 0.65850431

#par(mfrow=c(2,1))
plot.ts(w, main="white noise")
grid()

11
 white noise
3
2
1
0
w

−1
−2
−3
−4

0 100 200 300 400 500

Time

plot.ts(v, ylim=c(-3,3), main="moving average")

grid()

12
 moving average
3
2
1
0
v

−1
−2
−3

0 100 200 300 400 500

Time

w = rnorm(550,0,1) # 50 extra to avoid startup problems

x = filter(w, filter=c(1,-.9), method="recursive")[-(1:50)] # remove first 50
head(x)

## [1] -3.078438 -1.027532 2.741056 2.817851 0.199729 -2.909757

plot.ts(x, main="autoregression")
grid()

13
 autoregression
5
x

0
−5

0 100 200 300 400 500

Time

set.seed(154) # so you can reproduce the results

w = rnorm(200); x = cumsum(w) # two commands in one line
wd = w +.2; xd = cumsum(wd)

head(xd)

## [1] 0.7571713 -0.9523126 0.4508667 1.6257095 1.4525121 1.6911212

plot.ts(xd, ylim=c(-5,55), main="random walk", ylab='')

lines(x, col=4); abline(h=0, col=4, lty=2); abline(a=0, b=.2, lty=2)
grid()

14
 random walk
50
40
30
20
10
0

0 50 100 150 200

Time

cs = 2*cos(2*pi*1:500/50 + .6*pi); w = rnorm(500,0,1)

#par(mfrow=c(3,1), mar=c(3,2,2,1), cex.main=1.5)

head(cs)

## [1] -0.8515586 -1.0716536 -1.2748480 -1.4579373 -1.6180340 -1.7526134

plot.ts(cs, main=expression(2*cos(2*pi*t/50+.6*pi)))
grid()

15
 2cos(2πt 50 + 0.6π)
2
1
cs

0
−1
−2

0 100 200 300 400 500

Time

head(cs+w)

## [1] -1.0211419 -0.2238271 -0.1746897 -1.6798386 -0.9590438 -3.0467623

plot.ts(cs+w, main=expression(2*cos(2*pi*t/50+.6*pi) + N(0,1)))

grid()

16
 2cos(2πt 50 + 0.6π) + N(0, 1)
4
2
cs + w

0
−2
−4

0 100 200 300 400 500

Time

head(cs+5*w)

## [1] -1.699475 3.167479 4.225944 -2.567444 1.676917 -8.223358

plot.ts(cs+5*w, main=expression(2*cos(2*pi*t/50+.6*pi) + N(0,25)))

grid()

17
 2cos(2πt 50 + 0.6π) + N(0, 25)
15
10
cs + 5 * w

5
0
−5
−15

0 100 200 300 400 500

Time

x = rnorm(100)
y = lag(x, -5) + rnorm(100)
head(y)

## [1] -0.4961779 -0.6146974 -0.2836705 -2.0157873 -2.5087231 1.5612196

ccf(y, x, ylab='CCovF', type='covariance')

18
 y&x
1.0
0.6
CCovF

0.2
−0.2

−15 −10 −5 0 5 10 15

Lag

19