Lecture 8: Some Probability
Distributions
1
Recall:
Random variables can be discrete or continuous
• Discrete random variables have a countable
number of outcomes
• Examples: Dead/alive, male/female, dice, counts, etc.
• Continuous random variables have an infinite
continuum of possible values.
• Examples: time to install a program, weight, internet
speed, the real numbers from 1 to 6.
2
Probability
Distribution
3
• A continuous random variable and their associated
probability distribution arise when data are defined over a
continuous sample space.
• Any non-negative function defined over an interval, can be
continuous probability distribution.
• The extra requirement needed to make it a continuous
distribution, or a probability density function (pdf), is that
the total area under the curve is equal to 1.
Recall that for the discrete function, the extra requirement is
that the sum of all values of the function is 1.
4
Some Continuous
Distributions
1. Normal Distribution
2. Exponential
Distribution
5
Some Continuous Distributions
The Normal
Distribution
6
Normal Distribution
- also known as Gaussian
distribution, in honor of Carl
Friedrich Gauss (1777-1855)
7
Some properties are
1. It is symmetric with respect to a vertical
axis passing through the mean .
2. The mean, median, and mode are equal.
3. The tails are asymptotic relative to the
horizontal line.
4. The total area under the normal curve
and above the horizontal axis is 1 or
100%.
8
9
10
AREA UNDER THE NORMAL CURVE
The area under the probability
density curve between two
endpoints of an interval represents Range of Values
f(x)
the probability of a certain event.
P(a<X<b)
• In a normal distribution, the
probability of an event can be
represented graphically by a shaded
region.
• Since the total area under the normal
curve is 1, the area in the shaded
region is a value between 0 and 1. a b x
11
To find the area under the normal curve, knowledge of calculus
and numerical integration are required. The area between and
of the standard normal distribution is obtained by evaluating
the following integral
𝒛𝟐 𝟏 𝟐
𝟏 − 𝒛
𝑷 ( 𝒛 𝟏 < 𝒁 < 𝒛 𝟐 )=∫ 𝒆 𝟐
𝒅𝒛
𝟏 𝒛 √𝟐 𝝅
However, probability tables are furnished in Appendix B that
gives the results of such integration for different values of z.
12
13
Areas under
Areas under the
the curve
curve
X~N(μ, σ2)
2
1 1 x
f (x ) exp
2 2
a b
7 - 14 14
Areas under
Areas under the
the curve
curve
Z~N(0, 1)
z2 1 2
1 z
P ( z1 Z z2 )
z1 2
e 2 dz
z1 z2
To make it
easier…. Use standard normal table
15
P ( Z z0 )
16
P ( Z z0 ) 1 P ( Z z0 )
P ( z1 Z z 2 ) P ( Z z 2 ) P ( Z z1 )
17
The Standard
Normal Probability Distribution
EXAMPLE 1:
Let Z be a standard normal
random variable. Find the
following probabilities
using the standard normal
curve table
a.
18
= 0.9778
19
P ( z1 Z z 2 ) P ( Z z 2 ) P ( Z z1 )
c.
=
=
= 0.6107
20
The Standard
Normal Probability Distribution
EXAMPLE 2:
Find the value of k, if:
a. P(Z<k)=0.4562
b. P(Z>k)=0.9713
c. P(Z<k)=0.5076
d. P(Z<k)=0.05
e. P(-k<Z<k)=0.95
21
Hence,
22
NOTE:
When there is no
exact value in the
standard normal
table use the value
closest to it.
Using the closest value,
23
Probability z score
0.0505 -1.64
0.0495 -1.65
Note:
0.0505-0.05=0.0005
0.05-0.0495=0.0005
Thus,
24
e
The probability implies that (or ) of the values lie within
standard deviations of the mean.
This leaves 5% (or
0.05) of the area
outside this interval,
split equally in the tails:
2.5% in each tail.
(1-0.95)/2=0.025 (Area of the UNSHADED region)
This means that the tails below –k and above k, each has an area of 0.025. From
the standard normal table, . Therefore, .
OR
Then, (Find this value in the standard normal table)
Thus,
25
• It is emphasized that the standard normal curve table
(Appendix B) is only for the standard normal curve,
i.e., and .
• It would be an inconceivable task to attempt to set up
separate tables for normal curves for every value for
and . However, the standard normal curve table can still
be utilized even if the normal distribution has a mean
and . By using TRANSFORMATION.
26
Transformation
X
Z (Equation 1)
By using transformation any normal random variable is
converted to a standard normal variable. Eq’n 1 is also
called z-score.
The standard normal curve table can then be used for the
transformed variable.
27
Transformation
To get the original value of X from the transformed value
Z, we solve for X in terms of using eq’n 1, to get
X Z
28
EXAMPLE 3:
Let X be normally distributed with a mean of 72 and
a standard deviation of 15. Find the Z - scores
corresponding to: a.) 72 and b.) 70
X 72 72
a.
a. Z 0
15
X 70 72
b.
b. Z 0.13
15
29
EXAMPLE 4:
Given a normal distribution with and , find
a) the probability that X assumes a value greater than 50;
SOLUTION:
1. Calculate Z score by transformation.
X 50 40
Z 1.67
6
2. Calculate the probability.
P ( X 50) P ( Z 1.67) 40 50
1 P ( Z 1.67) 1 0.9525
0.0475
30
Given a normal distribution with and , find
b) the value of X that has 38% of the area below it.
SOLUTION:
1. Find the z score.
P ( Z z ) 0.38 z 0.31
2. Calculate the X value. z 40
X Z 38% or 0.38
( 0.316) 40 38.14
31
EXAMPLE 5:
If the weights of 600 students are normally distributed with a
mean of 50 kilograms and a variance of 16 kilograms,
a. determine the percentage of students with weights lower
than 55kgs.
SOLUTION:
1. Calculate Z score by transformation.
X 55 50
Z 1.25
4
2. Calculate the probability. 50 55
P ( X 55) P ( Z 1.25) 0.8944
Thus, 89.44% of the students weigh lower than 55kgs.
32
If the weights of 600 students are normally distributed with a
mean of 50 kilograms and a variance of 16 kilograms,
b. How many students with weights between 50kgs and 55kgs.
SOLUTION:
1. Calculate Z score by transformation.
55 50 50 50
Z2 1.25 and Z1 0
4 4
2. Calculate the probability. 50 55
P (50 X 55) P (0 Z 1.25)
P ( Z 1.25) P ( Z 0) 0.8944 0.5 0.3944
Thus, there are students who weigh from 50kgs to 55kgs.
33
EXERCISE:
An electrical firm manufactures
light bulbs that have a life, before
burn-out, that is normally
distributed with mean equal to
800 hours and a variance of 1600
hours. Two hundred bulbs were
randomly selected. How many
bulbs burnt between 778 and 834
hours.
34
Normal Approximation
to the Binomial Distribution
A binomial random variable X can be approximated
by a normal random variable by using the
transformation
X np
z
npq
35
EXAMPLE 6:
A pair of dice is rolled 180 times.
What is the probability that a total of
seven (7) dots on the top face occurs
a.) less than 25 times?
b.) between 33 and 41 times inclusive?
36
a.) less than 25 times?
SOLUTION: ,
If represents the number of times that a total of 7 occurs, then the exact probability is
found by computing [recall binomial distribution].
The mean and variance of the distribution are respectively:
1
𝜇=𝑛𝑝 =180 × =30
6
and 𝜎 = √ 𝑛𝑝𝑞= (180)
√
1 5
6 6
=5 ( )( )
Adjusting for continuity, the quantity becomes . The Z value corresponding to 24.5 is .
Hence,
( )
24
1
𝑃 ( 𝑋 <25 )= ∑ 𝑏 𝑥 ;180 , ≅ 𝑃 ( 𝑍 <−1.1 )=𝟎 .𝟏𝟑𝟓𝟕 .
𝑥=0 6
37
Some CONTINUOUS PROBABILITY DISTRIBUTION
normal probability distribution
- a family of distributions (an infinite number of distributions
with differing means () and standard deviations ()
Student t Probability Distribution
- like the normal distribution, the t-distribution is a family of
distributions that varies based on the degrees of freedom
Beta distribution
- represent outcomes for percentages or proportions
Cauchy distribution
- resemble the normal distribution family of curves but has a
taller peak than a normal and it’s fat tails decay much more slowly
38
Some CONTINUOUS PROBABILITY DISTRIBUTION
Exponential distribution
- represent outcomes for percentages or proportions
Gamma distribution
- mostly used for testing product reliability; for building
continuous-time Markov chains; often models waiting times
Logistic distribution
- used for modeling growth, and also for logistic regression
Weibull distribution
-models a broad range of random variables, largely in the
nature of a time to failure or time between events
39
