Lecture - 3

Instructor: Dr. Arabin Kumar Dey

Examples of Probability Distribution family:

Denition 1.1. The uniform Distribution: The uniform distribution is the distribution of numbers equally likely to fall into dierent intervals as long as the lengths of those intervals are equal.

The density of the uniform distribution on the interval [a, b] is given by the formula :

fa,b (x) =

1 ba

if a x b otherwise

The corresponding cumulative distribution function is given by :

Fa,b (x) =

0 1

xa ba

if x < a if a x b if x > b

The probability distribution is denoted by U (a, b). The uniform distribution over the unit interval [0, 1] is frequently used. Result: If U follows U [0, 1], and V = a + (b a)U Proof: P (V x) = P (a + (b a)U x) = P (U this implies that V follows uniform distribution. 1 then V follows U (a, b).
xa ) ba

xa ba

for

a x b. Clearly

Denition 1.2. Normal Distribution: The univariate normal distribution, also called the Gaussian distribution, is most often dened by means of its density function.

It depends upon two parameters and 2 , and is given by the formula :

f,2 (x) =

1 2 1 e 22 (x) ; x R R > 0. 2

The two parameter and 2 are the mean and variance of the distribution respectively. Indeed, if X is a random variable with such a distribution (in which case we use the notation X N (, 2 ) we have : The corresponding c.d.f.
x

E(X) = and V (X) = 2 .

F,2 (x) =

f,2 (x)dx

cannot be given by a formula in closed form involving standard function. For this we introduce a special notation ,2 for this function. when = 0 and 2 = 1 we call it a standard normal distribution and we use the notation for this probability distribution as N (0, 1). Note that, X N (, 2 ) Z = X N (0, 1)

Because of this fact, most computations are done with the N (0, 1) distribution only. We can observe from the above scaling property, P [ X ] = P [1 Z 1] = (1) (1) = 0.683 P [2 X 2] = P [2 Z 2] = (2) (2) = 0.955 P [3 X 3] = P [3 Z 3] = 0.997

These facts can be restated in words on :

The probability that a normal r.v. is one standard deviation, or less away from its mean is 0.683 The probability that normal r.v. is two standard deviation, or less away from its mean is 0.955 The probability that normal r.v. is three standard deviation, or less away from its mean is 0.997

In other words, gaussian variation are essentially always found within three standard deviations of their mean. Denition 1.3. Log-Normal Distribution: Y is log normal if X = ln Y is normal. If X N (, 2 ), then Y = exp(X) is log-normal with mean an variance E(Y ) = e+
2 /2

V (Y ) = exp(2 + 2 )[exp( 2 ) 1]

2 Conversely if Y is lognormal with mean y and variance y , then X = ln Y is normal

with mean and variance

E(X) = ln

y 1+
2 y 2 y

V (X) = ln 1 + Application :

2 y 2 y

If the log-return of an asset is normally distributed with mean 0.0119

and standard deviation 0.0663, Then what is the mean and standard deviation of its simple return ? 3

Answer : Step 1 :

Solve this problem in two steps. Based on the prior results, the mean and variance of Yt = exp(rt ) are E(Y ) = exp 0.0119 + 0.06632 2 = 1.014

V (Y ) = exp(2 0.0119 + 0.06632 )[exp(0.06632 ) 1] = 0.0045 Step 2 : Simple return is Rt = exp(rt ) 1 = (Yt 1). Therefore,

E(R) = E(Y ) 1 = 0.014 V (R) = V (Y ) = 0.0045, Standard deviation = V (R) = 0.067.