Lecture 11.8 - Poisson Distribution
Lecture 11.8 - Poisson Distribution
Usha Mohan
1/ 27
Statistics for Data Science -1
2/ 27
Statistics for Data Science -1
Learning objectives
3/ 27
Statistics for Data Science -1
Learning objectives
3/ 27
Statistics for Data Science -1
Learning objectives
3/ 27
Statistics for Data Science -1
Learning objectives
3/ 27
Statistics for Data Science -1
Learning objectives
3/ 27
Statistics for Data Science -1
Introduction to Poisson distribution
Introduction
I The Poisson probability distribution gives the probability of a
number of events occurring in a fixed interval of time or
space.
I We assume that these events happen with a known average
rate, λ, and independently of the time since the last event.
I Let X denote the number of times an event occurs in an
interval of time (or space).
I We say X ∼ Poisson(λ), in other words, X is a random
variable that follows Poisson distribution with parameter λ.
I The Poisson distribution may be used to approximate the
Binomial distribution if the probability of success is “small”
and the number of trials is “large” .
4/ 27
Statistics for Data Science -1
Introduction to Poisson distribution
Motivation example
Consider a researcher who is observing the number of vehicles that
pass a busy traffic intersection in a day. She collects data
comprising of 1000 one minute intervals and tabulates the same in
form of a frequency table given below.
Number of vehicles 0 1 2 3 4 5 >6
Count 80 225 260 225 110 70 30
0.260
0.225 0.225
0.110
0.085
0.070
0.03
0 1 2 3 4 5 6
5/ 27
Statistics for Data Science -1
Introduction to Poisson distribution
Tabular summary
I Mean= 2.39
I Variance = 7.88 − 2.392 = 2.16
6/ 27
Statistics for Data Science -1
Introduction to Poisson distribution
Observations
7/ 27
Statistics for Data Science -1
Probability mass function of Poisson
Derivation
8/ 27
Statistics for Data Science -1
Probability mass function of Poisson
9/ 27
Statistics for Data Science -1
Probability mass function of Poisson
Derivation- contd
x
λ n−x
λ
n
= x 1−
n n
λ −x
x
λ n
n(n − 1) . . . (n − x + 1) λ
= 1− 1−
x! n n n
λ −x
x
x n
λ n(n − 1) . . . (n − x + 1) λ
= 1− 1−
x! n n n
1 (x − 1)
x
λx n (1 − n ) . . . (1 − ) λ n λ −x
= n 1−
1−
x! nx n n
Derivation- contd
x
λ n−x
n λ
= lim 1−
n→∞ x n n
λx nx (1 − n1 ) . . . (1 − (x −n 1) ) λ n λ −x
= lim 1− 1−
n−→∞ x! nx n n
| {z } | {z } | {z }
→ 1 as n → ∞ → e −λ as n → ∞ → 1 as n → ∞
λx
= e −λ
x!
11/ 27
Statistics for Data Science -1
Probability mass function of Poisson
e −λ λx
P(X = x) = , x = 0, 1, 2, . . .
x!
12/ 27
Statistics for Data Science -1
Probability mass function of Poisson
x freq Prob
0 80 0.092
1 225 0.219
2 260 0.262
3 225 0.208
4 110 0.125
5 70 0.060
6 30 0.024
13/ 27
Statistics for Data Science -1
Probability mass function of Poisson
Observed
0.260
0.225 0.225
0.110
0.085
0.070
0.03
0 1 2 3 4 5 6
Poisson
0.262
0.219 0.208
0.125
0.092
0.0670
0.024
0 1 2 3 4 5 6
14/ 27
Statistics for Data Science -1
Probability mass function of Poisson
15/ 27
Statistics for Data Science -1
Probability mass function of Poisson
0.3
0.2
0.1
0
0 5 10 15
16/ 27
Statistics for Data Science -1
Probability mass function of Poisson
0.2
0.15
0.1
5 · 10−2
0
0 5 10 15
17/ 27
Statistics for Data Science -1
Probability mass function of Poisson
0.1
5 · 10−2
0
0 5 10 15
18/ 27
Statistics for Data Science -1
Probability mass function of Poisson
Section summary
19/ 27