Scribd
Upload
7 views17 pages

Lecture 11.7 - Expectation and Variance of Hypergeometric Distribution

Uploaded by

Classic Gaming
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
7 views17 pages

Lecture 11.7 - Expectation and Variance of Hypergeometric Distribution

Uploaded by

Classic Gaming
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/ 17

Statistics for Data Science -1

Expectation and Variance of Hypergeometric distribution

Expectation

Let X follow a hypergeometric distribution in which n objects are


selected from N objects with m of the objects being one type, and
N − m of the objects being a second type. What is the expected
value of X ?

18/ 31
Statistics for Data Science -1
Expectation and Variance of Hypergeometric distribution

Expectation

Let X follow a hypergeometric distribution in which n objects are


selected from N objects with m of the objects being one type, and
N − m of the objects being a second type. What is the expected
value of X ?
nm
E (X ) =
N

18/ 31
Statistics for Data Science -1
Expectation and Variance of Hypergeometric distribution

Expectation- proof
 
N −m m
P n−x x
E (X ) = x  
x N
  n  
m m! N N!
Now, = , and, = =
x x!(m − x)! n n!(N − n)!  
N(N − 1)! N (N − 1)! N N −1
= · = ·
n · (n − 1)!(N − n)! n (n − 1)!(N − 1− (n − 1))! n n−1
m · (m − 1)! N − m
P x!(m − x)! n − x
Hence, E (X ) = x   =
x N N −1
·
n n −1 
(m − 1)! (N − 1) − (m − 1)
P nm (x − 1)!(m − 1 − (x − 1))! (n − 1) − (x − 1) nm
  =
x N N −1 N
n−1
19/ 31
Statistics for Data Science -1
Expectation and Variance of Hypergeometric distribution

Variance

Let X follow a hypergeometric distribution in which n objects are


selected from N objects with m of the objects being one type, and
N − m of the objects being a second type. What is the variance of
X?

20/ 31
Statistics for Data Science -1
Expectation and Variance of Hypergeometric distribution

Variance

Let X follow a hypergeometric distribution in which n objects are


selected from N objects with m of the objects being one type, and
N − m of the objects being a second type. What is the variance of
X?
mN −mN −n
Var (X ) = n
N N N −1

20/ 31
Statistics for Data Science -1
Graph of pmf of the Hypergeometric distribution

N = 20, m = 4, n = 5

0.50

0.40

0.30

0.20

0.10

0.00
0 1 2 3 4
21/ 31
Statistics for Data Science -1
Graph of pmf of the Hypergeometric distribution

N = 20, m = 10, n = 5

0.30

0.20

0.10

0.00
0 1 2 3 4 5
22/ 31
Statistics for Data Science -1
Graph of pmf of the Hypergeometric distribution

N = 20, m = 16, n = 5

0.50

0.40

0.30

0.20

0.10

0.00
0 1 2 3 4 5
23/ 31
Statistics for Data Science -1
Graph of pmf of the Hypergeometric distribution

N = 20, m = 10, n = 10

0.30

0.20

0.10

0.00
0 2 4 6 8 10
24/ 31
Statistics for Data Science -1
Graph of pmf of the Hypergeometric distribution

N = 100, m = 50, n = 10

0.20

0.10

0.00
0 2 4 6 8 10
25/ 31
Statistics for Data Science -1
Graph of pmf of the Hypergeometric distribution

N = 500, m = 250, n = 10

0.25

0.20

0.15

0.10

0.05

0.00
0 2 4 6 8 10
26/ 31
Statistics for Data Science -1
Graph of pmf of the Hypergeometric distribution
Binomial versus Hypergeometric distribution

Expectation and variance


▶ X ∼ Hypergeometric(N, m, n)
nm
▶ E (X ) =
N
▶ Var (X ) = n m N−m N−n
N N N−1
 m
▶ Y ∼ Bin n,
N
nm
▶ E (X ) =
N
▶ Var (X ) = n m N−m
N N
▶ N−n
N−1 is known as finite population correction
▶ For n = 1, replacement has no effect both are Bernoulli trial
▶ For n = N, the whole population is sampled- hence variance is
zero.
▶ If the population N is very large compared to the sample size
n (i.e. N >> n) then Hypergeometric(N, m, n) is about
m
Binomial(n, ).
N 27/ 31
Statistics for Data Science -1
Graph of pmf of the Hypergeometric distribution
Binomial versus Hypergeometric distribution

Binomial versus Hyergeometric distribution


n = 5, p = 0.5
N = 500, m = 250, n = 5, n/N = 1%
0.3

0.2

0.1

0 1 2 3 4 5
28/ 31
Statistics for Data Science -1
Graph of pmf of the Hypergeometric distribution
Binomial versus Hypergeometric distribution

Binomial versus Hyergeometric distribution


n = 25, p = 0.5
N = 500, m = 250, n = 25, n/N = 5%
0.2

0.1

0.1

0.0

0 5 10 15 20 25
29/ 31
Statistics for Data Science -1
Graph of pmf of the Hypergeometric distribution
Binomial versus Hypergeometric distribution

Binomial versus Hyergeometric distribution


n = 50, p = 0.5
N = 500, m = 250, n = 50, n/N = 10%

0.1

0.1

0.0

0 10 20 30 40 50
30/ 31
Statistics for Data Science -1
Graph of pmf of the Hypergeometric distribution
Binomial versus Hypergeometric distribution

Binomial versus Hypergeometric distribution


·10−2 n = 250, p = 0.5
N = 500, m = 250, n = 250, n/N = 50%

6.0

4.0

2.0

0.0

100 110 120 130 140 150


31/ 31
Statistics for Data Science -1
Graph of pmf of the Hypergeometric distribution
Binomial versus Hypergeometric distribution

Section summary

▶ Binomial versus Hypergeometric

32/ 31

You might also like