1
The Poisson Experiment
 • Used to find the probability of a rare event
 • Randomly occurring in a specified interval
    – Time
    – Distance
    – Volume
 • Measure number of rare events occurred in the
   specified interval

                                                   2
The Poisson Experiment - Properties
 • Counting the number of times a success occur in
   an interval
 • Probability of success the same for all intervals
   of equal size
 • Number of successes in interval independent of
   number of successes in other intervals
 • Probability of success is proportional to the size
   of the interval
 • Intervals do not overlap
                                                    3
The Poisson Experiment - Properties
 • Some of the properties for a Poisson experiment
   can be hard to identify.
 • Generally only have to consider whether:-
    – The experiment is concerned with counting number of
      RARE events occur in a specified interval
    – These RARE events occur randomly
    – Intervals within which RARE event occurs are
      independent and do not overlap


                                                            4
The Poisson Experiment

 Typical cases where the Poisson experiment
   applies:
    – Accidents in a day in Soweto
    – Bacteria in a liter of water
    – Dents per square meter on the body of a car
    – Viruses on a computer per week
    – Complaints of mishandled baggage per 1000
      passengers
                                                    5
The Poisson Experiment
Calculating the Poisson Probability
  Determining x successes in the interval:

                                e
                                 x 
P( X  x)  P( x) 
                                  x!
where,  = mean number of successes in interval
       e = base of natural logarithm  2.71828

                                                  6
The Poisson Experiment - Example
• On average the anti-virus program detects 2 viruses
  per week on a notebook


Are the conditions required for the Poisson experiment met?

•   Time interval of one week
•   μ = 2 per week
•   Occurrence of viruses are independent
•   Can calculate the probabilities of a certain number of viruses
    in the interval
                                                               7
The Poisson Experiment - Example
• Let X be the Poisson random variable indicating the
  number of viruses found on a notebook per week
Calculate the probability that threeviruses occur
                               one viruses occur
                               zerovirus occur
                                      x e 
              P ( X  x)  P( x) 
                                        x!
                        e2 20
   P( X  0)  P(0)      0!
                                  0.1353
                        e2 21
   P( X  1)  P(1)      1!
                                  0.2707
                           e2 23
   P( X  3)  P(3)         3!
                                     0.1804
                          e2 27
  P( X  7)  P(7)                  0.0034        8
  .                         7!
  .
The Poisson Experiment - Example
• Let X be the Poisson random variable indicating the
  number of viruses found on a notebook per week
                                              X     P(X)
                     e2 20
P( X  0)  P(0)      0!
                                0.1353       0    0.1353
                                              1    0.2707
                     e2 21
P( X  1)  P(1)      1!
                               0.2707        2    0.2707
                                              3    0.1804
                        e2 23
P( X  3)  P(3)             3!
                                    0.1804   ↓       ↓
                                              7    0.0034
                        e2 27
P( X  7)  P(7)                   0.0034   ↓       ↓
.                         7!
.
.                                                 ∑P(X) ≈ 19
The Poisson Experiment - Example
 • Calculate the probability that two or less than two
   viruses will be found per week
                                         X      P(X)
  P(X ≤ 2)                               0     0.1353
                                         1     0.2707
  = P(X = 0) + P(X = 1) + P(X = 2)       2     0.2707
                                         3     0.1804
  = 0.1353 + 0.2707 + 0.2707
                                         ↓        ↓
  = 0.6767                               7     0.0034
                                         ↓        ↓

                                              ∑P(X) ≈ 10
                                                      1
The Poisson Experiment - Example
 • Calculate the probability that less than three
   viruses will be found per week
                                         X      P(X)
  P(X < 3)                               0     0.1353
                                         1     0.2707
  = P(X = 0) + P(X = 1) + P(X = 2)       2     0.2707
                                         3     0.1804
  = 0.1353 + 0.2707 + 0.2707
                                         ↓          ↓
  = 0.6767                               7     0.0034
                                         ↓          ↓

                                              ∑P(X) ≈ 11
                                                      1
The Poisson Experiment - Example
 • Calculate the probability that more than three
   viruses will be found per week
                                        X      P(X)
  P(X > 3)                              0     0.1353
                                        1     0.2707
  = P(X = 4) + P(X = 5) + ………           2     0.2707
                                        3     0.1804
  = 1 – P(X ≤ 3)
                                        ↓        ↓
  = 1 - 0.8571                          7     0.0034
                                        ↓        ↓
  =0.1429
                                             ∑P(X) ≈ 12
                                                     1
The Poisson Experiment - Example
 • Calculate the probability that four viruses will be
   found in four weeks
 • μ = 2 x 4 = 8 in four weeks

     P ( X  4)
        e 8 84
     
           4!
      0.0573
                                                     13
The Poisson Experiment - Example
 • Calculate the probability that two or less than two
   viruses will be found in two weeks
 • μ = 2 x 2 = 4 in two weeks
     P( X  2)
      P( X  0)  P( X  1)  P( X  2)
        4 0    4 1    4 2
       e 4 e 4 e 4
                   
         0!      1!      2!
      0.0183  0.0733  0.2381
      0.2381                                      14
The Poisson Experiment

 • Mean and standard deviation of Poisson
   random variable

      E( X )  

         Var ( X )  
             2




                                            15
The Poisson Experiment - Example

  – What is the expected number of viruses on the
    notebook per week?

          E( X )    2

  – What is the standard deviation for the number of
    viruses on the notebook per week?

             Var ( X )    2  1.41
                 2

                                                    16

Poisson lecture

  • 1.
  • 2.
    The Poisson Experiment • Used to find the probability of a rare event • Randomly occurring in a specified interval – Time – Distance – Volume • Measure number of rare events occurred in the specified interval 2
  • 3.
    The Poisson Experiment- Properties • Counting the number of times a success occur in an interval • Probability of success the same for all intervals of equal size • Number of successes in interval independent of number of successes in other intervals • Probability of success is proportional to the size of the interval • Intervals do not overlap 3
  • 4.
    The Poisson Experiment- Properties • Some of the properties for a Poisson experiment can be hard to identify. • Generally only have to consider whether:- – The experiment is concerned with counting number of RARE events occur in a specified interval – These RARE events occur randomly – Intervals within which RARE event occurs are independent and do not overlap 4
  • 5.
    The Poisson Experiment Typical cases where the Poisson experiment applies: – Accidents in a day in Soweto – Bacteria in a liter of water – Dents per square meter on the body of a car – Viruses on a computer per week – Complaints of mishandled baggage per 1000 passengers 5
  • 6.
    The Poisson Experiment Calculatingthe Poisson Probability Determining x successes in the interval:  e x  P( X  x)  P( x)  x! where,  = mean number of successes in interval e = base of natural logarithm  2.71828 6
  • 7.
    The Poisson Experiment- Example • On average the anti-virus program detects 2 viruses per week on a notebook Are the conditions required for the Poisson experiment met? • Time interval of one week • μ = 2 per week • Occurrence of viruses are independent • Can calculate the probabilities of a certain number of viruses in the interval 7
  • 8.
    The Poisson Experiment- Example • Let X be the Poisson random variable indicating the number of viruses found on a notebook per week Calculate the probability that threeviruses occur one viruses occur zerovirus occur  x e  P ( X  x)  P( x)  x! e2 20 P( X  0)  P(0)  0!  0.1353 e2 21 P( X  1)  P(1)  1!  0.2707 e2 23 P( X  3)  P(3)  3!  0.1804 e2 27 P( X  7)  P(7)   0.0034 8 . 7! .
  • 9.
    The Poisson Experiment- Example • Let X be the Poisson random variable indicating the number of viruses found on a notebook per week X P(X) e2 20 P( X  0)  P(0)  0!  0.1353 0 0.1353 1 0.2707 e2 21 P( X  1)  P(1)  1!  0.2707 2 0.2707 3 0.1804 e2 23 P( X  3)  P(3)  3!  0.1804 ↓ ↓ 7 0.0034 e2 27 P( X  7)  P(7)   0.0034 ↓ ↓ . 7! . . ∑P(X) ≈ 19
  • 10.
    The Poisson Experiment- Example • Calculate the probability that two or less than two viruses will be found per week X P(X) P(X ≤ 2) 0 0.1353 1 0.2707 = P(X = 0) + P(X = 1) + P(X = 2) 2 0.2707 3 0.1804 = 0.1353 + 0.2707 + 0.2707 ↓ ↓ = 0.6767 7 0.0034 ↓ ↓ ∑P(X) ≈ 10 1
  • 11.
    The Poisson Experiment- Example • Calculate the probability that less than three viruses will be found per week X P(X) P(X < 3) 0 0.1353 1 0.2707 = P(X = 0) + P(X = 1) + P(X = 2) 2 0.2707 3 0.1804 = 0.1353 + 0.2707 + 0.2707 ↓ ↓ = 0.6767 7 0.0034 ↓ ↓ ∑P(X) ≈ 11 1
  • 12.
    The Poisson Experiment- Example • Calculate the probability that more than three viruses will be found per week X P(X) P(X > 3) 0 0.1353 1 0.2707 = P(X = 4) + P(X = 5) + ……… 2 0.2707 3 0.1804 = 1 – P(X ≤ 3) ↓ ↓ = 1 - 0.8571 7 0.0034 ↓ ↓ =0.1429 ∑P(X) ≈ 12 1
  • 13.
    The Poisson Experiment- Example • Calculate the probability that four viruses will be found in four weeks • μ = 2 x 4 = 8 in four weeks P ( X  4) e 8 84  4!  0.0573 13
  • 14.
    The Poisson Experiment- Example • Calculate the probability that two or less than two viruses will be found in two weeks • μ = 2 x 2 = 4 in two weeks P( X  2)  P( X  0)  P( X  1)  P( X  2) 4 0 4 1 4 2 e 4 e 4 e 4    0! 1! 2!  0.0183  0.0733  0.2381  0.2381 14
  • 15.
    The Poisson Experiment • Mean and standard deviation of Poisson random variable   E( X )       Var ( X )   2 15
  • 16.
    The Poisson Experiment- Example – What is the expected number of viruses on the notebook per week?   E( X )    2 – What is the standard deviation for the number of viruses on the notebook per week?     Var ( X )    2  1.41 2 16