Lecture 23

Introduction to Statistics
Imran Nasir

1 / 20
Learning Objectives
In this lecture, we will cover following notions:
1. Poisson Probability Distribution.1
2. Poisson Approximation to the Binomial
Distribution.2
3. Normal Distribution and its properties.3

1
Anderson, Page 258 – 261
2
Weiss, Page 276 – 280
3
Anderson, Page 287 – 289.
2 / 20
Poisson Probability Distribution
Introduction The Poisson probability distribution is often useful
in estimating the number of occurrences over a
specified interval of time or space.
Example The random variable of interest might be the num-
ber of arrivals at a car wash in one hour.
Properties Following two properties are satisfied by the ran-
dom variable described by the Poisson probability
distribution:
1 The probability of an occurrence is the same
for any two intervals of equal length.
2 The occurrence or nonoccurrence in any inter-
val is independent of the occurrence or nonoc-
currence in any other interval.

3 / 20
Poisson Probability Distribution (Contd.)
Formula The Poisson probability function is given as:

µx e−µ
f (x) = , where x = 0, 1, 2, 3, · · ·
x!
where,
f (x) = the probability of x occurrences in an in-
terval
µ =expected value or mean number of occurrences
e = 2.71828
Mean Mean or expected value of Poisson random variable
is µ
Variance Variance of Poisson random variable is also µ.

4 / 20
Example: Poisson Probability Distribution
Assume that the number of patients who arrive at the emer-
gency room of a large hospital every hour follow Poisson dis-
tribution. historical data shows that the average number of
patients arriving in an hour is 10.
Find the probability that exactly 5 patients arrive in an hour
i.e., P (x = 5).
Solution Using Poisson probability dist. where µ = 10,

µx e−µ 105 e−10

f (x) = =
x! 5!

f (x) = 0.0378

5 / 20
Example: Poisson Probability Distribution (Contd.)
For convenience, Poisson probability tables are available for
quick calculations,

6 / 20
Re-scaling the Mean of Poisson Distribution
Suppose we are interested in the occurence of major defect
in highway after one month of resurfacing.
We learn that major defects one month after resurfacing
occur at the average rate of two per kilometer i.e., on
average in one kilometer sections there are two defects.
Since we are interested in an interval with a length of three
kilometers, µ = (2 defects/kilometer)(3 kilometers) = 6
represents the expected number of major defects over the
three-kilometer section of highway

7 / 20
Exercises
Solve exercise 44 to 51 from Anderson page 260.

8 / 20
Exercise 1
Consider a Poisson distribution with µ = 3.
a. Write the appropriate Poisson probability function.
b. Compute f (2).
c. Compute f (1).
d. Compute P (x ≥ 2).

9 / 20
Exercise 2
Consider a Poisson distribution with a mean of two
occurrences per time period.
a. Write the appropriate Poisson probability function.
b. What is the expected number of occurrences in three time
periods?
c. Write the appropriate Poisson probability function to deter-
mine the probability of x occurrences in three time periods.
d. Compute the probability of two occurrences in one time
period.
e. Compute the probability of six occurrences in three time
periods.
f. Compute the probability of five occurrences in two time
periods.

10 / 20
Exercise 3
Phone calls arrive at the rate of 48 per hour at the reservation
desk for Regional Airways.
a. Compute the probability of receiving three calls in a 5
minute interval of time.
b. Compute the probability of receiving exactly 10 calls in 15
minutes.
c. Suppose no calls are currently on hold. If the agent takes
5 minutes to complete the current call, how many callers
do you expect to be waiting by that time? What is the
probability that none will be waiting?
d. If no calls are currently being processed, what is the prob-
ability that the agent can take 3 minutes for personal time
without being interrupted by a call?

11 / 20
Poisson Approximation to Binomial
Recall that the binomial probability formula is
n!
f (x) = px (1 − p)n−x
x!(n − x)!

Because of computational difficulties, the binomial proba-

bility formula can be difficult or impractical to use when n
is large.
We can use a Poisson distribution to approximate a bino-
mial distribution when n is large and p is small.

12 / 20
Poisson Approximation to Binomial (Contd.)
The steps involved in Poisson approximation to Binomial
distribution are:
Step 1 Find n, the number of trials, and p, the success
probability.
Step 2 Continue only if n ≥ 100 and np ≤ 10.
Step 3 Approximate the required binomial probabilities
by using the Poisson probability formula,

e−np (np)x
P (X = x) =
x!

13 / 20
Example
The infant mortality rate (IMR) is the number of deaths of
children under 1 year old per 1000 live births during a cal-
endar year. It is known that the IMR in Finland is 3.4 i.e.,
p = 3.4/1000 = 0.0034. Use the Poisson approximation to
determine the probability that, of 500 randomly selected live
births in Finland, there are: (a) no infant deaths, and (b) at
most three infant deaths.
Solution For Poisson approximation
np = 500(0.0034) = 1:
e−1.7 1.7x
P (X = x) =
x!
e−1.7 1.70
Part a. P (X = x) = 0!
= 0.183
Part b. P (X ≤ 3) = P (X = 0) + P (X = 1) + P (X =
2) + P (X = 3) =
e−1.7 1.70 −1.7 1 −1.7 2 −1.7 3
0!
+ e 1!1.7 + e 2!1.7 + e 3!1.7 = 0.907
14 / 20
Exercise 1
A survey reveals that 1 in every 200 Americans are in prison.
Use this information and the Poisson distribution to determine
the approximate probability that at most three people in a
random sample of 500 Americans are currently in prison.

15 / 20
Exercise 2
It is observed that roughly 1 in every 30 million lobsters hatched
is yellow. Apply the Poisson approximation to the binomial
distribution to answer the following questions:
a. Of 50 million lobsters hatched, what is the probability
that between 1 and 5, inclusive, are yellow?
b. Roughly how many lobsters must be hatched in order to
be at least 95% sure that at least one is yellow?

16 / 20
Normal Probability Distribution
Introduction The most commonly used probability distribution
for describing a continuous random variable is the
normal probability distribution.
Applications It is used in a wide variety of practical applica-
tions in which the random variables are heights
and weights of people, test scores, scientific mea-
surements, amounts of rainfall, and other similar
values.
Formula The probability density function is given as:
1 1 (x−µ)
2
f (x) = √ e− 2 σ2 (1)
2π
where, µ = mean, σ = standard deviation, π =
3.14159, and e = 2.71828.
17 / 20
Normal Probability Distribution (Contd.)
Normal distribution satisfy these properties:
1. The normal distribution is symmetric across the mean.
Normal curve to the left of the mean a mirrors the nor-
mal curve to the right of the mean. Highest point on the
normal curve is mean=median=mode.
2. The standard deviation determines how flat and wide the
normal curve is. Larger values of the standard deviation
result in wider, flatter curves, showing more variability.
3. The percentage of values in some commonly used intervals
are:
68.3% of the values are within plus or minus one
standard deviation.
95.4% of the values are within plus or minus two
standard deviations.
99.7% of the values are within plus or minus three
standard deviations.
18 / 20
Normal Probability Distribution (Contd.)
The normal distributions with different means and same
SD can be visualized as:

Two normal distributions with the same mean but with

different standard deviations:

19 / 20
Standard Normal Probability Distribution
Definition A normal distribution with a mean of zero and a
standard deviation of one is said to have a standard
normal probability distribution (Z).
Formula Since Z has µ = 0 and σ = 1, probability f (z) is:
1 z2
f (z) = √ e− 2
2π

20 / 20