Chapter 1: Market Indexes, Financial Time Series and their Characteristics • What is time series (TS) analysis? Observe the following two data sets: Hang Seng 12877 12850 13023 ··· Index Date 30.8.04 31.8.04 01.9.04 ··· Student’s 130kg 200kg 45kg ··· Weights Students A B C ··· What is the difference between these two data sets? • Definition: A time series (TS) is a sequence of random variables labeled by time t. Time series data are observations of TS. 1
35
Embed
Chapter 1: Market Indexes, Financial Time Series and their ...
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Chapter 1: Market Indexes, Financial Time
Series and their Characteristics
• What is time series (TS) analysis?
Observe the following two data sets:
Hang Seng 12877 12850 13023 · · ·IndexDate 30.8.04 31.8.04 01.9.04 · · ·
Student’s 130kg 200kg 45kg · · ·WeightsStudents A B C · · ·
What is the difference between these two data
sets?
• Definition:
A time series (TS) is a sequence of random
variables labeled by time t.
Time series data are observations of TS.
1
TSA History
• Linear TSA: The beginning/babyhood 1927
• George Udny Yule (1871-1951), a British statis-
tician.
• Eugen Slutsky (1880-1948), a Russian/Soviet
mathematical statistician, economist and po-
litical economist.
• Herman Ole Andreas Wold ( 1908– 1992)
• Peter Whittle (1927-) (ARMA model)
• Linear TSA in 1970’s
• George Edward Pelham Box (1919–2013), a
British statistician (quality control, TSA, de-
sign of experiments, and Bayesian inference).
He has been called “one of the great statistical
minds of the 20th century”.
• Sir Ronald Aylmer Fisher (1890 –1962)
• Box & Jenkins (1976) Time Series Analysis:
Forecasting and Control
• Nonlinear TSA in 1950’s
• Patrick Alfred Pierce Moran (1917–1988), an
Australian statistician (probability theory, pop-
ulation and evolutionary genetics).
• Peter Whittle (1927-, New Zealand), stochas-
tic nets, optimal control, time series analysis,
stochastic optimisation and stochastic dynam-
ics.
• Nonlinear TSA in 1980’s
• Howell Tong (1944–, in Hong Kong) (TAR
model).
• Robert Fry Engle III (1942–) is an American
economist and the winner of the 2003 Nobel
Memorial Prize.
• What is financial time series (FTS)?
Examples
1. Daily log returns of Hang Sang Index .
2. Monthly log return of exchange rates of
Japan-USA.
3. China life daily stock data.
4. HSBC daily stock data.
0 2000 4000 6000 8000
020
0040
00Nasdaq daily closing price
0 100 200 300 400
020
0040
00
Nasdaq monthly closing price
Nasdaq daily and monthly closing price from Sep
1, 1980 to Sep 1, 2016.
Special features of FTS
1. Theory and practice of asset valuation over
time.
2. Added more uncertainty. For example, FTS
must deal with the changing business and eco-
nomic environment and the fact that volatility is
not directly observed.
General objective of the course
to provide some basic knowledge of financial time
series data
to introduce some statistical tools and economet-
ric models useful for analyzing these series.
to gain empirical experience in analyzing FTS
to study methods for assessing market risk
to analyze high-dimensional asset returns.
Special objective of the course
Past data =⇒TS r.v. Zt=⇒ future of TS.
(a) E(Zn+l|Z1, · · · , Zn
),
(b) P (a ≤ Zn+l ≤ b|Z1, · · · , Zn) for some a < b.
1.1 Asset Returns
Let Pt be the price of an asset at time t, and
assume no dividend. One-period simple return or
simple net return:
Rt =Pt − Pt−1
Pt−1=
Pt
Pt−1− 1.
Gross return
1 +Rt =Pt
Pt−1or Pt = Pt−1(1 +Rt).
Multi-period simple return or the k−period simple
net return:
Rt(k) =Pt − Pt−k
Pt−k=
Pt
Pt−k− 1.
Gross return
1 +Rt(k) =Pt
Pt−k=
Pt
Pt−1×
Pt−1
Pt−2× · · · ×
Pt−k+1
Pt−k
= (1+Rt)(1 +Rt−1)× · · · × (1 +Rt−k+1)
=k−1∏j=0
(1 +Rt−j).
Example: Suppose the daily closing prices of astock are
Day 1 2 3 4 5Price 37.84 38.49 37.12 37.60 36.30
1. What is the simple return from day 1 to day 2?
Ans: R2 = 38.49−37.8437.84 = 0.017.
2. What is the simple return from day 1 to day 5?
Ans: R5(4) = 36.30−37.8437.84 = −0.041.
3. Verify that
1 + R5(4) = (1+R2)(1 +R3)(1 +R4)(1 +R5).
Time interval is important! Default is one year.
Annualized (average) return:
Annualized[Rt(k)] =
k−1∏j=0
(1 +Rt−j)
1/k − 1.
An approximation:
Annualized[Rt(k)] ≈1
k
k−1∑j=0
Rt−j.
Continuous compounding
Assume that the interest rate of a bank deposit is
10% per annum and the initial deposit is $1.00.
If the bank pays interest m times a year, then the
interest rate for each payment is 10%/m, and the
net value of the deposit become
$1×(1+
0.1
m
)m.
Illustration of the power of compounding (int. rate