Mathematics
Chapter
Discrete Distributions
Important Discrete
Probability Distributions
Discrete Probability
Distributions
Binomial
Hypergeometric
Poisson
Binomial Probability
Distribution
n identical trials
Binomial Probability
Distribution
(continued
)
Binomial Probability
Distribution Function
n!
n X
X
P X
p 1 p
X ! n X !
P(X)
1/4 = .25
2/4 = .50
1/4 = .25
n x n x
n
a
b
(
a
b
)
x 0 x
n
Proof :
n x
n x
p
(
x
)
p
(
1
p
)
x 0
x
n
( p ( 1 p ))n
Binomial Distribution
Characteristics
Mean
E X np
E.g. np 5 .1 .5
Variance and
Standard Deviation
2 np 1 p
np 1 p
.6
.4
.2
0
P(X)
n = 5 p = 0.1
X
E.g.
np 1 p 5 .1 1 .1 .6708
Expectation
n
E ( X ) x p x (1 p ) n x
x 0
x
n
( n x )!n(! x 1)! p x (1 p ) n x
x 1
np
x 1
np
n 1
k 0
np
( n 1)!
( n x )!( x 1)!
p x 1 (1 p ) n x
( n 1)!
( n 1 k )!( k )!
p k (1 p ) n k 1
Variance
n x
E ( X ( X 1)) x( x 1) p (1 p ) n x
x 0
x
n
( n x )!n(!x 2 )! p x (1 p ) n x
x 2
n(n 1) p
x2
n(n 1) p 2
n2
k 0
n(n 1) p 2
( n 2 )!
( n x )!( x 2 )!
p x 2 (1 p ) n x
( n 2 )!
( n 2 k )!( k )!
p k (1 p ) n k 2
Sample size
Probability of success
0,1
Mean
0,5
Variance
0,45
Standard deviation
X
P(X)
0,671
P(<=X)
P(<X)
P(>X)
P(>=X)
0,59049
0,59
0,40951
0,32805
0,919
0,59049
0,08146
0,40951
0,0729
0,991
0,91854
0,00856
0,08146
0,0081
0,99144
0,00046
0,00856
0,00045
0,99954
1E-05
0,00046
0,00001
0,99999
1E-05
Binomial Distribution in
PHStat
Example
Solution
4 x
4 x
2
2
3
4
p
1
6
p
(
1
p
)
4
p
(
1
p
)
x
x2
x p 1 p 2 p (1 p ) p
x 1
Solution
6 p (1 p) 4 p (1 p) p 2 p(1 p) p
2
3p 2 0
p
2
3
Poisson Distribution
Poisson Process:
P( X x |
x!
Poisson Probability
Distribution Function
e
P X
X!
P X : probability of X "successes" given
X
e 3.6 3.64
P X
.1912
4!
Poisson Distribution in
PHStat
Average/Expected number of
successes:
P(<=X)
3,6
P(X)
P(<X)
P(>X)
P(>=X)
0,027324
0,027324
0,000000
0,972
1,0000
0,098365
0,125689
0,027324
0,8743
0,9726
0,177058
0,302747
0,125689
0,6972
0,8743
0,212469
0,515216
0,302747
0,4847
0,6972
0,191222
0,706438
0,515216
0,2935
0,4847
0,137680
0,844119
0,706438
0,155
0,2935
0,082608
0,926727
0,844119
0,0732
0,1558
0,042484
0,969211
0,019118
0,988329
0,007647
0,995976
10
0,002753
0,998729
11
0,000901
0,999630
12
0,000270
0,999900
13
0,000075
0,999975
14
0,000019
0,999994
15
0,000005
0,999999
16
0,000001
1,000000
Poisson Distribution
Characteristics
Mean
E X
N
XiP Xi
.6
.4
.2
0
= 0.5
P(X)
X
0
i 1
Standard Deviation
and Variance
.6
.4
.2
0
= 6
P(X)
X
0
10
Approximate a binomial to
poisson
Proof
P( X i)
n!
( n i )!i! n
n ( n 1)...( n i 1) i 1 / n n
i! (1 / n ) i
ni
1 / n
n i
n
i
i!
e ; (1 / n) 1;
i
n ( n 1)...( n i 1)
n
Expectation
E( X )
xe
x!
x 0
x 1
e e
x 1
x1
( x 1)!
e x1
( x 1)!
Variance
E ( X ( X 1))
x 0
1 e
x x
x ( x 1) e
x!
x2
1 e e
1
x 2
( x 2 )!
x 2
e x 2
( x 2 )!
Hypergeometric Distribution
Hypergeometric Distribution
Function
A N A
X
n
P X
N
n
4 6
2 1
P 2
.30
10
A : number of "successes" in population
3
X : number of "successes" in sample
X 0,1, 2,L
, n
Hypergeometric Distribution
Characteristics
Mean
A
E X n
N
nA N A N n
2
N2
N 1
nA N A
2
N
N n
N 1
Finite
Populatio
n
Correctio
n
Factor
Hypergeometric Distribution
in PHStat
p ( x, y )
p ( x)
f x, y dy
p ( x, y )
p( y)
f x, y dx
Expectation
E( X Y )
x y f ( x, y)dxdy
f
(
x
,
y
)
dy
dx
xf ( x)dx yf ( y )dy
E ( X ) E (Y )
E ( X 1 ... X n ) E ( X 1 ) ... E ( X n )
dy
f
(
x
,
y
)
dx
Example
1, succes
Xi
; E ( X i ) p ; V ( X i ) pq
0, failed
X
X 1 ... X n
E ( X ) E ( X 1 ) ... E ( X n ) np
V ( X ) V ( X 1 ) ... V ( X n ) npq
Example
Solution
Independent R.V
X and Y are
independent if
E ( XY )
xyf ( x, y)dxdy
xyf ( x) f ( y )dxdy
xf ( x)dx yf ( y )dy
p ( x, y ) p ( x ) p ( y )
f ( x, y ) f ( x ) f ( y )
E ( X ) E (Y )
Properties of Covariance
Cov(x,X) = Var(X)
Cov(cX,Y) = c Cov(X,Y)
Cov(X,Y+Z)= E[X(Y+Z)]-E[X]E[Y+Z]
= E[XY]-E[X]E[Y] + E[XZ]E[X]E[Z]
= (Cov(X,Y) + Cov(X,Z)
The last property easily generalizes to
give
Cov X , Y
Cov(X , Y )
Var
X
i 1
Cov
X , X
i 1
j 1
Cov ( X i , X j )
i 1 j 1
n
Cov ( X i , X i ) Cov( X i , X j )
i 1
n
i 1 j i
V ( X i ) 2 Cov ( X i , X j )
i 1
i 1 j i
Proposition
2
n
2
n
Example
P ( X Y n) P{ X k , Y n k }
k 0
n
P{ X k }P{Y n k}
k 0
n
e
k 0
1 1k
k!
1 2
n!
e 12
n!
n2k
( n k )!
k 0
n!
k !( n k )!
1 2
k
1
nk
2