Scribd
Upload
63 views

Lecture - 20: 1 Beta Distribution

The document discusses the beta distribution, gamma distribution, and cumulative distribution functions (CDFs). It defines the probability density function of the beta distribution and lists its key properties including its expected value and variance. It also defines the probability density function of the gamma distribution and lists its properties. It then discusses important properties of CDFs, including that a random variable is continuous if its CDF is continuous, discrete if its CDF is discrete, or a mixture if the variable is. It provides definitions of CDFs for continuous and discrete random variables. Examples are given to illustrate CDFs for specific distributions like the standard normal and exponential. Key properties of CDFs like being right-continuous and non-decreasing are outlined.

Uploaded by

Ajay Pratap Singh
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
63 views

Lecture - 20: 1 Beta Distribution

The document discusses the beta distribution, gamma distribution, and cumulative distribution functions (CDFs). It defines the probability density function of the beta distribution and lists its key properties including its expected value and variance. It also defines the probability density function of the gamma distribution and lists its properties. It then discusses important properties of CDFs, including that a random variable is continuous if its CDF is continuous, discrete if its CDF is discrete, or a mixture if the variable is. It provides definitions of CDFs for continuous and discrete random variables. Examples are given to illustrate CDFs for specific distributions like the standard normal and exponential. Key properties of CDFs like being right-continuous and non-decreasing are outlined.

Uploaded by

Ajay Pratap Singh
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 4

Lecture - 20

Beta Distribution :

The probability density function of the beta distribution, for 0 x 1, and


shape parameters > 0 and > 0, as follows:

f (x; , ) = constant x1 (1 x)1


= R1
0

x1 (1 x)1

u1 (1 u)1 du

( + ) 1
x
(1 x)1
()()

1
x1 (1 x)1
B(, )

() is gamma function.
Properties:

E(X) =

(1)

V (X) =

(+)2 (++1)

Gamma Distribution:

f (x; 1 , 1 ) = (1 )1

1
x1 1 e1 x
(1 )

for x 0and1 , 1 > 0

(2)

Properties:

E(X) =

1
1

V (X) =

1 1
(1 +1 )2 (1 +1 +1)

Cumulative Distribution Function :

Cumulative density function are already discussed in previous lectures.


Important Statement:

X is continuous iff F (X) is continuous.


X is discrete iff F (X) is discrete.
X is mixture of continuous and discrete random variable, F (X) is
mixture of continuous and discrete random variable.

Definition 3.1 F (x) is said to be a cumulative distribution function for a


Rx
continuous random variable X iff F (x) = f (y)dy.
2

Definition 3.2 F (x) is said to be a cumulative distribution function for a


X
P (X = y).
discrete random variable X iff F (x) =
y|yx

Example 3.3 P (X = 1) = 1. What is F (X) ?

F (x) =

0 x<1
1 x1

Example 3.4 A coin is tossed and a head will occur with probability p.
Find out the distribution function.

Suppose X = 1 if head occurs and X = 0 if tail occurs. Then P (X =


0) = (1 p) and P (X = 1) = p

0
F (x) = (1 p)

if x < 0
if 0 x < 1
if x 1

For standard normal distribution,


F (x) = (x) =

z2
1
e 2 dz
2

For exponential distribution, we can obtained,


(
0
x0
F (x) =
x
(1 e ) x > 0
Properties:
3

1. F () = 0
Proof: Suppose as n , bn , therefore Bn = (, bn ] tends
to , Using continuity theorem,
F () = lim P (X bn ) = P ( lim Bn ) = P (X < ) = 0
n

2. F () = 0
Proof: Suppose, An = {X bn },

n 1, are increasing events whose

union is the event X < . Therefore using continuity theorem,


lim P (X bn ) = P ( lim An ) = P (X < ) = 1

3. F () is non-decreasing random variable.


Proof: If a < b. The event X a is contained in the event X b
and so can not have a larger probability. P (X a) P (X b) or
F (a) F (b).
4. F () is right-continuous.
We need to prove limn F (x + n1 ) = F (x).
Mn = (, x +

1
n]

is decreasing sequence of sets converges to the

intersection of such sets which is equals to (, x].


Therefore, by continuity theorem, limn P (X x+ n1 ) = limn F (x+
1
n)

= P (limn Mn ) = P ( < X x) = F (x)

You might also like