03

Risky Asset

1
Focus

Concerned with common stock

Treat the prices of assets as random

2
Dynamics of Stock Prices
• The price of stock at time t will
be denoted by S(t). It is assumed
to be strictly positive for all t.
• We take t = 0 to be the present
time, S(0) being the current
stock price, known to all
investors.
• The future prices S(t) for t > 0
remainunknown, in general.

3
Dynamics of Stock Prices
• The probability space Ω consists
of all feasible price movement
‘scenarios’ ω ∈ Ω.
• We shall write S(t, ω) to denote
the price at time t if the market
follows scenario ω ∈ Ω

4
Example 3.1

These price movements can be represented as a tree,

5
Exercise 3.2
• Suppose that the stock price on any given day can
either be 5% higher or4% lower than on the previous
day. Sketch a tree representing possible stock price
movements !
• Gunakan data GGRM

6
7
Return
• The rate of return, or briefly the
return K(n, m) over a time
interval [n, m] (in fact [mτ, nτ]),
is defined to be the random
variable
• The return over a single time
step [n − 1, n] will be denoted by
K(n),

8
Example 3.3
• In the situation considered in Exercise 3.2 (Slide Ke-7) the returns are
random variables taking the following values:

9
Remark 3.1
• If the stock pays a dividend of
div(n) at time n, then the
definition of return has to be
modified.

10
 Cek … apakah benar rumusnya?
1. Buka data historis pergerakan harga saham PT
Gudang Garam (GGRM.JK)
2. Download data 5 tahun terakhir untuk daily prices +
dividen
3. Bandingkan nilai antara closing price dan adj close!

11
Non-additivity (Deterministics) of returns

t is common practice to compute the average of recorded past returns as a

prediction for the future. This may result in misrepresenting the information,
12
Simulasi Forecast dengan MA5, MA20, MA100

13
Simulasi SE dengan MA5, MA20, MA100

14
Membandingkan dengan Indices

15
Logarithmic
return

16
Membandingkan antar Perhitungan Return

17
Proof

18
Expected Return
• Suppose that the probability distribution of the return K over
a certain time period is known. Then we can compute the
mathematical expectation E(K), called the expected return
• We estimate the probabilities of recession, stagnation and
boom to be 1/4,1/2, 1/4, respectively. If the predicted annual
returns on some stock in these scenarios are −6%, 4%, 30%,
respectively, then the expected annual return is

19
Silahkan Cek Worksheet Scenario
SD_S0 SD_S_Boom SD_S_Recession
5049.066181 5301.519491 4847.103534
5.00% -4.00%

AVG_S0 AVG_S_Boom AVG_S_Recession

49,637.04 52,118.89 47,651.56
5.00% -4.00%

Ketika f(x) dikalikan suatu konstanta,

maka distribution nya tidak berubah! 20
Konsep Probabilitas

21
Proof

Expectation of a sum of random

variables is the sum of expectations

Functions of random variables are

also random
22
Binomial Tree Model

23
Binomial Tree Model

24
Two-step binomial tree of stock prices

25
Three-step binomial tree of stock prices

26
 Risk-Neutral Probability
the expected one-step return

The expected stock prices for n = 0, 1, 2,

27
Comparing Risk Free Securities in Stock and
Bond
• If the amount S(0) were to be invested risk-free at
time 0, it would grow to S(0)(1 + r)n after n steps.
Clearly, to compare E(S(n)) and S(0)(1 + r)n we only
need to compare E(K(1)) and r.
• An investment in stock always involves an element of
risk, simply because the price S(n) is unknown in
advance. A typical risk-averse investor will require that
E(K(1)) > r,
28
Risk-Neutral Probability

p∗ E∗
•probability •expectation

29
Risk-Neutral Probability

30
31
Martingale Property

32
Example 3.6
• Consider a two-step binomial
tree model such that S(0) = 100
dollars, u = 0.2, d = −0.1 and r =
0.1. Then p∗ = 2/3 is the risk-
neutral probability, and the
expected stock price after two
steps is

Konsep yang sama dapat diterapkan untuk Trinomial Tree Model

33
Trinomial Tree Model

34
Trinomial Tree Model

35
Risk-neutral probabilities p∗, q∗

36
Remark

Konsep binomial tree model dapat

diterapkan untuk
Continuous-
Trinomial Tree
Time Limit
Model
Model
37
Density of the distribution In Continous Model

38
“Detail untuk Continous Time Model
tidak dibahas lebih jauh”

39
Terima Kasih

40