Probability Distributions

Probability Distributions
• Earlier, we understood about the frequency distribution to summarize the variation in the
observed data.
• A probability distributions can be thought as a theoretical frequency distribution, describing
how outcomes are expected to vary in a random experiment.
• It is a listing of probabilities of all possible outcomes that could result if the experiment were
done.

Example: You have a fair coin (equal probability of heads or tails). You will toss it two times.
Formulate a probability distribution of the number of heads that could possibly come
when we toss the coin twice.
Probability Distribution
Example: Possible outcomes from two tosses of a fair coin
First Toss Second Toss Number of Heads on Probability of the Four
two Tosses Possible Outcomes
H H 2 0.5
H T 1 0.5
T H 1 0.5
T T 0 0.5
Total = 1.00

NOTE: The outcomes in the table is not actual outcomes of tossing a fair coin but it is
theoretical outcome. That means it presents the way in which we expect two toss coin
experiment to behave over time.
Probability Distribution
Example: Probability Distribution of the possible number of heads from two tosses of a fair coin
Number of Tosses Probability of Outcome
Heads H P(H)

0 (T, T)
1 (T, H) + (H, T) 0.50
2 (H, H)

NOTE: The outcomes in the table is not actual outcomes of tossing a fair coin but it is
theoretical outcome. That means it presents the way in which we expect two toss coin
experiment to behave over time.
Frequency Distribution vs Probability
Distribution
• Frequency Distribution is listing of all the frequencies of all the outcomes of an experiment that
actually occurred when the experiment was done.
• Probability distribution is listing of the probabilities of all the possible outcomes that could result
if the experiment was done.

Note: Probability distribution can be based on theoretical consideration (toss of a fair dice) or
depending on the subjective judgement of the likelihood of certain outcomes based on experience.
Defining Random Variables
A variable is random, if it takes on different values as a result of the outcomes of a random
experiment.

Example 1: In “coin toss”, we define a random variable as the number of Heads.

This random variable can take values of .
Example 2: In an Eye hospital, there is no way of knowing howe many patients will be screened for
cataract in a given day. So, tomorrows number of patients is a random variable.

Note:
• The probability that the random variable takes a given value can be computed using the rules
governing probability.
• For example, the probability that means we get 1 head when we tossed the coin for two
times is 0.50. Symbolically, it is denoted as P(X=1) = 0.50.
Types of Random Variables
• A random variable can be either discrete or continuous:
 A discrete random variable can assume a countable number of values.
Example: Number of steps to the top of the Eiffel Tower*

 A continuous random variable can assume any value along a given interval of a number line.
Example: The time a tourist stays at the top once s/he gets there

*Believe it or not, the answer ranges from 1,652 to 1,789. See Great Buildings
Types of Random Variables
Discrete random variables
• Number of sales
• Number of calls
• People in line
• Mistakes per page

• Continuous random variables

• Length
• Depth
• Volume
• Time
• Weight
Classification of Probability Distributions
Discrete Probability Distribution can take on only limited number of values, which can be listed.
 Tossing a dice (It can take only 6 possible values)
 Probability that you were born in a given month because it can take only 12 possible values

In a Continuous Probability Distribution, the variable under consideration is allowed to take any
value within a given range, all values cannot be listed.
 Weight of the students in your class

Note: Continuous distribution are very convenient ways to represent discrete distribution that have
many possible outcomes, all very close to each other.
Discrete Probability Distributions
• The discrete probability distribution (probability distribution of a discrete random
variable X) is a list of each possible value of X together with the probability that X takes in
one trial of the experiment.
• The probabilities in the probability distribution of a random variable X must satisfy the
following two conditions:
 Each probability P(x) must be between 0 and 1:
1 ≥ p(x) ≥ 0
 The sum of all the possible probabilities is 1:
p(x) = 1

10
Discrete Probability Distributions
Example: Probability Distribution of the Possible number of heads from two tosses of a fair coin

Number of Tosses Probability of Outcome

Heads H P(H)

0 (T, T)
1 (T, H) + (H, T) 0.50
2 (H, H)
Expected Values of Discrete Random Variables

• The mean, or expected value, of a discrete random variable is

• The variance of a discrete random variable x is

• The standard deviation of a discrete random variable x is

12
•Construct a probability distribution based
on the following frequency distribution.

• Draw a graph of the hypothetical Outcome 102 105 108 111 114 117
probability distribution.
• Compute the expected value of the Frequency 10 20 45 15 20 15
outcome.
Outcome Frequency P(Outcome)
(1) (2) (3) (1)  (3)

102 10 0.08 8.16

105 20 0.16 16.80

108 45 0.36 38.88

111 15 0.12 13.32

114 20 0.16 18.24

117 15 0.12 14.04

125 1.00 109.44  Expected outcome

Bob Walters, who frequently invests in the stock market, carefully studies any potential investment. He is currently examining the
possibility of investing in the Trinity Power Company. Through studying past performance, Walters has broken the potential
results of the investment into five possible outcomes with accompanying probabilities. The outcomes are annual rates of return
on a single share of stock that currently costs $150. Find the expected value of the return for investing in a single share of
Trinity Power.
Return on investment ($) 0.00 10.00 15.00 25.00 50.00

Probability 0.20 0.25 0.30 0.15 0.10

If Walters purchases stock whenever the expected rate of return exceeds 10 percent, will he purchase the stock, according to
these data?
 Return P(Return)
(1) (2) (1)  (2)

0 0.20 0.00

10 0.25 2.50

15 0.30 4.50

25 0.15 3.75

50 0.10 5.00

1.00 15.75  Expected return

Bob will purchase the stock because the expected return of $15.75 is greater than 10 percent of
the $150 purchase price.
Taxonomy of Probability Distributions
Discrete probability distributions
•Binomial distribution
•Multinomial distribution
•Poisson distribution
•Hypergeometric distribution

Continuous probability distributions

•Normal distribution
•Standard normal distribution
•Gamma distribution
•Exponential distribution
•Chi square distribution
•Lognormal distribution
•Weibull distribution
Discrete Probability Distributions

19
Binomial Distribution
• In many situations, an experiment has only two outcomes: success and failure.
• Such outcome is called dichotomous outcome.
• An experiment when consists of repeated trials, each with dichotomous outcome is called
Bernoulli process. Each trial in it is called a Bernoulli trial.
• The binomial distribution describes discrete probability distribution, resulting from a
Bernoulli process experiment.
• Conditions/Requirements of Bernoulli process:
 Each trial has only two possible (dichotomous) outcomes.
 Probability of the outcome of any trial remains fixed over time.
 Trials are statistically independent.
Binomial Distribution
Example: Tossing a fair coin 3 times
 Each trial has only two possible
(dichotomous) outcomes. Outcomes are Heads or Tails
 Probability of the outcome of any trial
remains fixed over time. Coin is fair
 Trials are statistically independent. A head on flip i doesn’t change P(H)
of flip i + 1

21
Binomial Distribution
Example: Firing bullets to hit a target.
• Suppose, in a Bernoulli process, we define a random variable X number of successes in
trials.
• Such a random variable obeys the binomial probability distribution as follows:
 The experiment consists of n trials.
 Each trial results in one of two mutually exclusive outcomes, "success” and “failure”.
 The probability of a success on a single trial is equal to . The value of remains constant
throughout the experiment.
 The trials are independent.

22
Binomial Distribution
• Binomial distribution is the discrete probability distribution of the number of successes in
a sequence of n independent dichotomous experiments, each of which yields success with
probability p.
• Binomial distribution is frequently used to model the number of successes in a sample of
size n drawn with replacement from a population of size N.
• Parameters of binomial distribution:
 n (number of trials)
 p (probability of success)
 q = 1-p (probability of failure)
 r number of successes desired
• The function for computing the probability of r successes in n trials using the binomial
formula is given by
for r = 0, 1, 2, …., n
Binomial Distribution Example
Example: Tossing a coin
X = number of heads a success
p = 0.5, the probability that we get head when we toss a coin
n = 2, number of times the coin is tossed.

Thus,

24
 Suppose 40% of the class is female.
Question What is the probability that 6 of the first 10
students walking in will be female?

25
Binomial Distribution Problem
Problem: Suppose 40% of the class is female.
What is the probability that 6 of the first 10 students walking in will be female?

Solution:

26
Binomial Distribution
• The mean (expected value), variance, and standard deviation of a Binomial Distribution
is as follows:

Mean

Variance

Standard Deviation

27
Binomial Distribution Example
Example: Consider a packaging machine that produces 20 percent defective packages. Take a
random sample of 10 packages and find the mean and standard deviation of the process.

Solution:

28
The latest nationwide political poll indicates that for Americans who are randomly selected, the probability that they are conservative is
0.55, the probability that they are liberal is 0.30, and the probability that they are middle-of-the-road is 0.15. Assuming that
these probabilities are accurate, answer the following questions pertaining to a randomly chosen group of 10 Americans. (Do
not use Appendix Table 3.)
(a) What is the probability that four are liberal?
(b) What is the probability that none are conservative?
(c) What is the probability that two are middle-of-the-road?
(d) What is the probability that at least eight are liberal?
(a) n  10, p  0.30, P(r  4) (0.30)4(0.70)6  0.2001

(b) n  10, p  0.55, P(r  0) (0.55)0(0.45)10  0.0003

(c) n  10, p  0.15, P(r  2) (0.15)2(0.85)8  0.2759

(d) n  10, p  0.30, P(r – 8)  P(r  8) + P(r  9) + P(r  10)

(0.30)8(0.70)2 + (0.30)9(0.70)1 (0.30)10(0.70)0

  0.00145 + 0.00014 + 0.00001  0.0016

The Poisson Distribution
• Poisson distribution is a discrete probability distribution that evaluates the probability of a
(usually small) number of occurrences out of many opportunities in a …
 Period of time
 Area
 Volume
 Weight
 Distance
 Other units of measurement
Example: 1. Number of clients visiting a ticket selling counter in a metro station.
2. The number of cases of a disease in different towns.
• These events occur with a known average rate, and independent of the time since the last event.
• Here, our concern is only upon the happening (success) of an event.
The Poisson Distribution
Properties of Poisson process
• The number of outcomes in one-time interval is independent of the number that occurs in
any other disjoint interval [Poisson process has no memory]
• The probability that a single outcome will occur during a very short interval is
proportional to the length of the time interval and does not depend on the number of
outcomes occurring outside this time interval.
• The probability that more than one outcome will occur in such a short time interval is
negligible.
The Poisson Distribution
• Parameters of Poisson distribution: λ (Lambda: the mean number of occurrences per
interval of time).

The probability distribution of the Poisson random variable , representing the number of outcomes
occurring in per unit time is

where mean number of occurrences in the given unit of time, area, volume, etc. and

• Poisson as an approximation of the binomial distribution: when n >= 20 and p <= 0.05
such that their product, is finite.
The Poisson Distribution Example
Example: Suppose in a given stream there are an average of 3 striped trout per 100 yards.
What is the probability of seeing 5 striped trout in the next 100 yards, assuming a Poisson
distribution?

34
The Poisson Distribution Example
Example: Suppose in a given stream there are an average of 3 striped trout per 100 yards.
• What is the probability of seeing 5 striped trout in the next 100 yards, assuming a Poisson
distribution?
• How about in the next 50 yards, assuming a Poisson distribution?
Solution: Since the distance is only half as long, λ is only half as large.

35
Given λ  4.2, for a Poisson distribution, find
(a) P(x  2).
(b) P(x  5).
(c) P(x  8).
(a) P(x  2)  P(x  0) + P(x  1) + P(x  2)

 0.0150 + 0.0630 + 0.1323  0.2103

(b) P(x  5)  1 – P(x  4)  1 – P(x  4) – P(x  3) – P(x  2)

 1 – 0.1944 – 0.1852 – 0.2103  0.4101

(c)
Continuous Probability Distributions

38
 The Normal Distribution…
The normal distribution is the most important of all probability distributions. The
probability density function of a normal random variable is given by:

It looks like this:

Bell shaped,
Symmetrical around the mean …

Copyright © 2009m Cengage Learning 8.39

 The Normal Distribution…
Important things to note:
The normal distribution is fully defined by two parameters:
its standard deviation and mean

The normal distribution is bell shaped and

symmetrical about the mean

Unlike the range of the uniform distribution (a ≤ x ≤ b)

Normal distributions range from minus infinity to plus infinity
Copyright © 2009m Cengage Learning 8.40
 Standard Normal Distribution…
A normal distribution whose mean is zero and standard deviation is one is called
the standard normal distribution.
0
1

As we shall see shortly, any normal distribution can be converted to a standard

normal distribution with simple algebra. This makes calculations much easier.

Copyright © 2009m Cengage Learning 8.41

 Normal Distribution…
The normal distribution is described by two parameters:
its mean and its standard deviation . Increasing the mean shifts the curve to
the right…

Copyright © 2009m Cengage Learning 8.42

 Normal Distribution…
The normal distribution is described by two parameters:
its mean and its standard deviation . Increasing the standard deviation
“flattens” the curve…

Copyright © 2009m Cengage Learning 8.43

 Normal Distribution
• The normal (or Gaussian) distribution is a continuous probability distribution that has a bell-
shaped probability density function, known as the Gaussian function or informally the bell
curve.
• There are basic reasons why the normal distribution occupies such a prominent place in
statistics.
First, it has some properties that make it applicable to a great many situations in which it is
necessary to make inferences by taking samples. Such a curve approximately describes many
phenomenon occur in nature, industry and research.
o Physical measurement in areas such as meteorological experiments, rainfall studies and
measurement of manufacturing parts are often more than adequately explained with
normal distribution.
Second, the normal distribution comes close to fitting the actual observed frequency
distributions of many phenomena (Central limit theorem). So, it is also known as “mother of all
distribution”.

Copyright © 2009m Cengage Learning

 Normal Distribution
• Characteristics of normal probability distribution (normal curve):
 The curve has single peak; thus it is unimodal.
 It has bell shaped symmetrical curve.
 The mean of a normally distributed population lies at the centre of its normal curve.
 The mean, median and mode coincide in a normal curve.
 The two tails of normal curve extends indefinitely and never touch horizontal axis.

– The mathematical equation for the probability distribution of the normal variable depends
upon the two parameters and , its mean and standard deviation.

Copyright © 2009m Cengage Learning

 Area Under the Normal Curve

Irrespective of the values of and for a normal probability distribution:

• The total area under the curve and above the horizontal axis is equal to 1.
• At least 68 of the values in a normally distributed population lie within one standard deviations
of the mean, that is, in the interval with endpoints ;
• At least 95 of the values in a normally distributed population lie within two standard deviations
of the mean, that is, in the interval with endpoints ;
• At least 99.7 of the values in a normally distributed population lie within three standard
deviations of the mean, that is, in the interval with endpoints for populations.

Copyright © 2009m Cengage Learning

 Area Under the Normal Curve

Copyright © 2009m Cengage Learning

 Calculating Normal Probabilities…
We can use the following function to convert any normal random variable to a
standard normal random variable…

Some advice: always

draw a picture!

Copyright © 2009m Cengage Learning 8.48

 Calculating Normal Probabilities…
We can use the following function to convert any normal random variable to a
standard normal random variable…
This shifts the mean
of X to zero…

Copyright © 2009m Cengage Learning 8.49

 Calculating Normal Probabilities…
We can use the following function to convert any normal random variable to a
standard normal random variable…

This changes the

shape of the curve…

Copyright © 2009m Cengage Learning 8.50

 Example
Suppose that at another gas station the daily demand for regular gasoline is
normally distributed with a mean of 1,000 gallons and a standard deviation of 100
gallons.

The station manager has just opened the station for business and notes that there
is exactly 1,100 gallons of regular gasoline in storage.

The next delivery is scheduled later today at the close of business. The manager
would like to know the probability that he will have enough regular gasoline to
satisfy today’s demands.

Copyright © 2009m Cengage Learning 8.51

 Example
The demand is normally distributed with mean µ = 1,000 and standard deviation
σ = 100. We want to find the probability
P(X < 1,100)
Graphically we want to calculate:

Copyright © 2009m Cengage Learning 8.52

 Example
The first step is to standardize X. However, if we perform any operations on X we
must perform the same operations on 1,100. Thus,

X   1,100  1,000 
P(X < 1,100) = P   = P(Z < 1.00)
  100 

Copyright © 2009m Cengage Learning 8.53

 Example
The figure below graphically depicts the probability we seek.

Copyright © 2009m Cengage Learning 8.54

 Example
The values of Z specify the location of the corresponding value of X.

A value of Z = 1 corresponds to a value of X that is 1 standard deviation above

the mean.

Notice as well that the mean of Z, which is 0 corresponds to the mean of X.

 

Copyright © 2009m Cengage Learning 8.55

 Example
If we know the mean and standard deviation of a normally distributed random
variable, we can always transform the probability statement about X into a
probability statement about Z.

Consequently, we need only one table, the standard normal probability table.

Copyright © 2009m Cengage Learning 8.56

 Table 3…
This table is similar to the ones we used for the binomial and Poisson
distributions.

That is, this table lists cumulative probabilities P(Z < z) for values of z ranging
from −3.09 to +3.09
 

Copyright © 2009m Cengage Learning 8.57

 Table 3…
Suppose we want to determine the following probability.
P(Z < −1.52)
 
We first find −1.5 in the left margin. We then move along this row until we find
the probability under the
.02 heading. Thus,
P(Z < −1.52) = .0643

Copyright © 2009m Cengage Learning 8.58

 Table 3…
P(Z < −1.52) = .0643

Copyright © 2009m Cengage Learning 8.59

 Table 3…
we can also determine the probability that the standard normal random variable is
greater than some value of z.

For example, we find the probability that Z is greater than 1.80 by determining
the probability that Z is less than 1.80 and subtracting that value from 1.

Applying the complement rule we get

P(Z > 1.80) = 1 – P(Z < 1.80) = 1 − .9641 = .0359

Copyright © 2009m Cengage Learning 8.60

 Table 3…
P(Z > 1.80) = 1 – P(Z < 1.80) = 1 − .9641 = .0359

Copyright © 2009m Cengage Learning 8.61

 Table 3…
We can also easily determine the probability that a standard normal random variable lies
between 2 values of z. For example, we find the probability
P(−1.30 < Z < 2.10)
By finding the 2 cumulative probabilities and calculating their difference. That is
P(Z < −1.30) = .0968
and
P(Z < 2.10) = .9821
Hence,
P(−1.30 < Z < 2.10) = P(Z < 2.10) − P(Z < −1.30)
= .9821 −.0968 = .8853

Copyright © 2009m Cengage Learning 8.62

 Table 3…
P(−1.30 < Z < 2.10) = .8853

Copyright © 2009m Cengage Learning 8.63

 Example
Consider an investment whose return is normally distributed with a mean of 10%
and a standard deviation of 5%.
a. Determine the probability of losing money.
b. Find the probability of losing money when the standard deviation is equal to
10%.

Copyright © 2009m Cengage Learning 8.64

 Example
a The investment loses money when the return is negative. Thus we wish to
determine

P(X < 0)

The first step is to standardize both X and 0 in the probability statement.

P(X < 0) = = P(Z < – 2.00)

Copyright © 2009m Cengage Learning 8.65

 Example
From we find

P(Z < − 2.00) = .0228

Therefore the probability of losing money is .0228

Copyright © 2009m Cengage Learning 8.66

 Example 8.2
b. If we increase the standard deviation to 10% the probability of suffering a loss
becomes

P(X < 0) =

= P(Z < –1.00)

= .1587

Copyright © 2009m Cengage Learning 8.67

Dennis Hogan is the supervisor for the Conowingo Hydroelectric Dam. Mr. Hogan knows that the dam’s
turbines generate electricity at the peak rate only when at least 1,000,000 gallons of water pass
through the dam each day. He also knows, from experience, that the daily flow is normally
distributed, with the mean equal to the previous day’s flow and a standard deviation of 200,000
gallons. Yesterday, 850,000 gallons flowed through the dam. What is the probability that the
turbines will generate at peak rate today?
For today,   850,000,   200,000

 0.5 – 0.2734  0.2266