Beruflich Dokumente
Kultur Dokumente
Random Variable [m-w.org] : a variable that is itself a function of the result of a statistical experiment in which each outcome has a definite probability of occurrence
X : S SX
domain range SX is called the image of X
Sx
1 2 3 4 5 6
X : S SX
X(s)
1 Sx
Mixed random variables: have an image which contains continuous and discrete parts
Sx = {0} U (0, 1]
pX (ak ) = Pr {X = ak }, k = 1, 2, , n
pX( k) (a
X
10
Properties of a PMF
P1: 0 pX (ak ) 1 P2:
ak S X
(ak ) = 1
pX(ak)
11
FX (t ) = Pr {X t } = pX (x )
x t
pX(x) pmf
FX(x) CDF
12
Pr {a < X b } = Pr {X b } Pr {X a } = FX (b ) FX (a )
pX(x) pmf FX(x) CDF
X
13
Properties of a CDF
F1: 0 FX (x ) 1 F2: a b
pX(x) pmf
< x < FX (a ) FX (b )
FX(x) CDF
14
Properties of a CDF
F3:
limx FX (x ) = 0 lim li x FX (x ) = 1
F4: FX (x i +1 ) = FX (x i ) + pX (x i +1 )
pX(x) pmf FX(x) CDF
X
15
16
17
{X } = X =
ak S X
Pr {X = ak }
In some cases the expected value does not converge cases, In such cases, we say that the expected value does not exist
19
0.033 1 6 7 9 13 X
0.1 1 6 7 9 13 X
20
21
var {X } = =
2 X
ak S X
(a
{X }) P {X = ak } Pr
22
E{X}=5.2 var{X}=15.36
var{X}=9.91 0.033 9 13 X
9
2
13
var {X } = (1 5.2) 0.4 + (6 5.2) 0.2 + (7 5.2) 0.2 + (9 5.2) 0.1 + (13 5.2) 0.1 = 15 36 15.36
2 2 2 2
(6 3.87) 0.4 + (7 3.87) 0.033 + (9 3.87) 0.033 + (13 3.87) 0.033 = 9 91 9.91
2 2
23
X = var {X }
24
X=3.14 0.033 1 6 7 9 13 X
13
25
1/n x1 x2 x3 xn
What do you think are the expected value and standard deviation of this random variable?
26
X(s)
Sx
27
X(s)
A=Pak wins
R
Ac=Pak losses
Sample Space
Image Courtesies of http://www.tribuneindia.com and images.google.com
28
Variable
R
Ac=Pak losses
Sample Space
Image Courtesies of http://www.tribuneindia.com and images.google.com
29
30
0
Copyright Syed Ali Khayam 2009
31
Pr{I=k} 0.5 I
32
0
Copyright Syed Ali Khayam 2009
33
Pr{I=k} 0.9
0.1 0 1 I
34
I
35
36
X = Ij
j =1
37
X = Ij
j =1
38
X = Ij
j =1
n k p (1 p )n k Pr P {X = k } = k
39
n k p (1 p )n k b (k ; n, p ) = P {X = k } = Pr k
This pmf gives the probability that exactly k out of a total of n Bernoulli trials were successes Be very careful about the definition of a success
40
k
Image courtesy of Wikipedia article on Binomial Distribution
Copyright Syed Ali Khayam 2009 41
42
Pr {(X = 1) (X = 2) (X = 3) (X = n )}
43
44
45
Binomial RV
46
48
pZ (k ) = Pr {Z = k } = (1 p )
OR
k 1
pZ (k ) = P {Z = k } = (1 p ) p Pr
Depending on whether the success trial is included in the total count or not
49
Pr {Z = k } = (1 p ) p n k p (1 p )n k Pr {Z = k } = k
Geometric
Binomial
51
k p1 1 p k 1 Pr {X = k } = ( ) 1 Pr {X = k } = (1 p )
k 1
k 1
p = Pr {Z = k }
52
53
54
Memoryless Property
It can be shown that the Geometric rv satisfies the memoryless property The memoryless property is satisfied when:
Pr {Z = j + k Z k } = Pr {Z = j }
This property is also called the Markov Property
55
Memoryless Property
The memoryless property is satisfied when:
Pr {Z = j + k Z k } = Pr {Z = j }
For the Geometric rv, RHS of the above equation is:
Pr P {Z = j } = (1 p ) p
Thus to prove that the Geometric rv satisfies the memoryless property, we need to show that
Pr {Z = j + k Z k } = (1 p ) p
j
56
Memoryless Property
To prove that the Geometric rv satisfies the memoryless property, we need to show that
Pr {Z = j + k Z k } = (1 p ) p
j
Pr {Z = j + k } = Pr {Z k }
(1 p ) p = k k +1 k +2 (1 p ) p + (1 p ) p + (1 p ) p +
57
j +k
Memoryless Property
Continued from last page
(1 p ) p Pr {Z = j + k Z j } = k k +1 k +2 (1 p ) p + (1 p ) p + (1 p ) p +
=
j +k
(1 p )
k 0 j +k
j +k 1
p
2
(1 p ) ((1 p ) p + (1 p ) p + (1 p ) p + )
(1 p ) p = k (1 p )
= (1 p ) p
Summation over all possible values of the Geometric pmf
j
58
Memoryless Property
It can also be shown that the Geometric rv is the only discrete random variable that satisfies the memoryless property Because of the memoryless property, the Geometric rv can be thought of as the number of failures between two successes OR the inter-arrival time between successes
59