6.

Continuous Probability
Distribution
Adapted From :
Probability & Statistics for Engineers & Scientists, 8th Ed.
Walpole/Myers/Myers/Ye (c)2007
Introduction to Business Statistics, 5e
Kvanli/Guynes/Pavur (c)2000
South-Western College Publishing
Statistics for Managers
Using Microsoft Excel 4th Edition
 Probability Distributions
Probability
Distributions

Discrete Continuous
Probability Probability
Distributions Distributions

Binomial Uniform

Poisson Normal

Hypergeometric Exponential
Continuous Probability Distributions
A continuous random variable is a variable that
can assume any value on a continuum (can
assume an infinite number of values)
thickness of an item
time required to complete a task
temperature of a solution
height, in inches

These can potentially take on any value,

depending only on the ability to measure
accurately.
The Uniform Distribution
Probability
Distributions

Continuous
Probability
Distributions

Uniform

Normal

Exponential
Continuous Uniform Distribution

The uniform distribution is a

probability distribution that has equal
probabilities for all possible outcomes
of the random variable

Also called a rectangular distribution

 Continuous Uniform Distribution

The continuous uniform distribution is the simplest of the

continuous distributions. It models the situation where the
probability is uniform in the interval [A,B].
The density function is

1
f ( x; A, B ) , A x B
B A
0 elsewhere.

This density function is a rectangle with base B - A. The height of

the rectangle is?
The height is 1 / (B - A).
 The Uniform Distribution
(continued)

The Continuous Uniform Distribution:

AB
f(X)

2

ab
( B A) 2

A2
B X 2
12
where
f(X) = value of the density function at any X value
A = minimum value of X
B = maximum value of X
 Uniform Distribution Example
Example: Uniform Probability Distribution
Over the range 2 X 6:

1
f(X) = 6 - 2 = .25 for 2 X 6

f(X)
AB 26
4
.25 2 2

(B - A) 2 (6 - 2) 2
2 6 X 12

12
1.1547
The Normal Distribution
Probability
Distributions

Continuous
Probability
Distributions

Normal

Uniform

Exponential
 Normal Distribution Examples
The normal distribution is the most important and widely used
distribution in statistics. Some examples:
This bell-shaped curve, sometimes called the Gaussian distribution,
explains many natural phenomena.
Average age of the world's population.
Physical measurements like blood pressure.
Standardized test scores.
Average precipitation levels.
Average price of certain stocks in the stock market.
The thickness of metal plates from a factory
The Central Limit Theorem in statistics indicates that random
variables that are the sum of a number of component
variables follow the normal distribution.
 The Normal Distribution
Bell Shaped
Symmetrical f(X)
Mean, Median and Mode
are Equal
Location is determined by the
mean, X
Spread is determined by the
standard deviation,
Mean
The random variable has an = Median
infinite theoretical range: = Mode
+ to
 Many Normal Distributions

By varying the parameters and , we obtain

different normal distributions
 The Normal Probability
Density Function

The formula for the normal probability density

function is

1 x
2

1
n( x; , ) e 2
x
2

Where e = the mathematical constant approximated by 2.71828

= the mathematical constant approximated by 3.14159
= the population mean
= the population standard deviation
X = any value of the continuous variable
 Normal Distribution

As before, determines the center of the bell-

shaped curve, while determines the spread.
Notes:
The curve is symmetric about the mean.
As expected, the the total area under the curve
equals 1. However, the function cannot be integrated
in closed form.
The mode (where the curve is at a maximum) is at x
= .
The curve approaches the y axis as x moves away
from .
The curve has a point of inflection at x = .
 The Normal Distribution
Shape

f(X) Changing shifts the

distribution left or right.

Changing increases
or decreases the
spread.

X
 Standard Normal Distribution

Since it's not feasible to publish tables for every possible value of
and , we define the standard normal distribution to be a normal
distribution with
= 0 and = 1, and publish a table for that.
Then, every normal probability question can be reduced to an
equivalent question about the standard normal distribution.
A standard normal random variable can be from any normal
random variable with a simple transformation:
X
Z

Intuitively, Z shows the number of standard deviations above or
below (if negative) the mean.
 Standard Normal Distribution

Also known as the Z distribution

Mean is defined to be 0
Standard Deviation is 1
f(Z)

1
Z
0
Values above the mean have positive Z-values,
values below the mean have negative Z-values
 Example

If X is distributed normally with mean of 100

and standard deviation of 50, the Z value for
X = 200 is

X 200 100
Z 2.0
50
This says that X = 200 is two standard
deviations (2 increments of 50 units) above
the mean of 100.
 Comparing X and Z units

100 200 X ( = 100, = 50)

0 2.0 Z ( = 0, = 1)

Note that the distribution is the same, only the

scale has changed. We can express the problem in
original units (X) or in standardized units (Z)
 Probability as
Area Under the Curve
The total area under the curve is 1.0, and the curve is
symmetric, so half is above the mean, half is below

f(X) P( X ) 0.5
P( X ) 0.5

0.5 0.5

X
P( X ) 1.0
 Finding Normal Probabilities

Probability is the
Probability is measured by the area
area under the
curve! under the curve
f(X) P (a X b)
= P (a < X < b)
(Note that the
probability of any
individual value is zero)

a b X
 The Standard Normal Table

The Standard Normal table in the textbook

gives the probability less than a desired
value for Z (i.e., from negative infinity to Z)

.9772
Example:
P(Z < 2.00) = .9772

0 2.00 Z
 The Standard Normal Table (A.3)
(continued)

The column gives the value of

Z to the second decimal point
z 0.00 0.01 0.02

0.1
The row shows
the value of Z 0.2
. The value within the
to the first .
decimal point . table gives the
2.0 .9772 probability from Z =
up to the desired Z
2.0
value
P(Z < 2.00) = .9772
 Finding Normal Probabilities

Draw the normal curve for the problem in

terms of X
Suppose X is normal with mean 8.0 and
standard deviation 5.0
Find P(X < 8.6)

X
8.0
8.6
 Upper Tail Probabilities
Suppose X is normal with mean 8.0 and
standard deviation 5.0.
Now Find P(X > 8.6)
P(X > 8.6)=1- P(X < 8.6)

X
8.0
8.6
 Probability Between
Two Values

Suppose X is normal with mean 8.0 and

standard deviation 5.0. Find P(8 < X < 8.6)
= P(X < 8.6)- P(X < 8)

8 8.6
X

P(8 < X < 8.6)

 Additional Exercise

To use the table, first convert the normal

random variable to a standard normal random
variable.
Ex: If a normal random variable X has = 50 and = 25, find
P(X > 12).
Converting to standard normal, we have P(X > 12) =
P(Z > -1.52). (12 is 1.52 standard deviations below the mean.)
By table A.3, F(-1.52) = .0643. So P(Z > -1.52) = 1 - .0643 =
.9357.
Or, by symmetry, P(Z > -1.52) = P(Z < +1.52) = .9357.
So, P(X > 12) = .9357.
 Normal Distribution
Examples
1. Sebuah pabrik limun menjual limun dalam kaleng. Volume limun per kaleng
terdistribusi normal dengan rata-rata 330 mldan standard deviasi 10 ml.
Sebuah kaleng diambil dan diukur volumenya. Berapakah peluang kaleng
mempunyai volume :
a. Antara 325 340 ml ? 0.19146 0.34134
b. Kurang dari 345 ml ?
c. Lebih dari 348 ml ?
JAWAB :
a. P(325 x 340) =

-0.5 1.0

325 330 340 - 330

Z1 = = - 0,5 ; Z2 = =+1
10 10
Maka P(325 x 340) = 0,19146 + 0, 34134 = 0,5328
 Normal Distribution

b. P(x 345) =
345 330
Z= = + 1,5
10
0.5000 0.43319

1.5

Maka P(x 345) = 0,5 + 0,43319 = 0,93319

 Normal Distribution

c. P(x 338) =

338 330
Z=
10
0.28814

= +0.8

0.8

Maka. P(x 338) = 0,5 - 0,28814 = 0,21186

 More Normal Distribution
Calculations

Use properties of a cumulative distribution to calculate the

probability of being within a given range.
Ex: If a normal random variable X has = 50 and = 25, find P(62 > X
> 32). First step?
Convert to standard normal.
P(62 > X > 32) = P(0.48 > Z > -0.72). Next?
P(0.48 > Z > -0.72) = P(Z 0.48) - P(Z -0.72) = ?
P(Z 0.48) - P(Z -0.72) = 0.6844 - 0.2358 = .4486.
Reverse calculation: starting with a probability, find X.
Using and above, what values of X centered above and below the
mean have p = .80 of falling between them. First?
Find Z values with 80% of the area between them. z = 1.28.
Next convert from standard normal back to X.
So, the limits are x = 50 1.28(25) = (18, 82).
 Assessing Normality

Not all continuous random variables are

normally distributed
It is important to evaluate how well the data set
is approximated by a normal distribution
 Assessing Normality
(continued)
Construct charts or graphs
For small- or moderate-sized data sets, do a stem-and-
leaf display and box-and-whisker plot look symmetric?
For large data sets, does the histogram or polygon
appear bell-shaped?
Compute descriptive summary measures
Do the mean, median and mode have similar values?
Is the interquartile range approximately 1.33 ?
Is the range approximately 6 ?
Evaluate normal probability plot
The Normal Probability Plot
(continued)

A normal probability plot for data

from a normal distribution will be
approximately linear:

X
90

60

30

-2 -1 0 1 2 Z
 Normal Probability Plot for
Non-Normal Distributions
(continued)

Left-Skewed Right-Skewed
X 90 X 90
60 60
30 30
-2 -1 0 1 2 Z -2 -1 0 1 2 Z

Rectangular
X 90 Nonlinear plots
indicate a deviation
60
from normality
30
-2 -1 0 1 2 Z
 Distribution Approximation
Notes
Continuity correction: Suppose a population of resistors follows a
normal distribution, but that resistance measurements are in integer
values of ohms.
Here we assume that any resistance from 42.5 to 43.5 = 43.
So the probability of any outcome can be calculated using the
normal distribution.
This example uses a continuity correction to approximate a
discrete distribution with a continuous distribution.
If n is large and p is very small (or very large), the binomial
distribution can be approximated by what?
The Poisson distribution.
What is and for the binomial distribution?
= np.
2 = npq.
 Normal Approximation to
Binomial
If X binomial with parameters n and p, then

x 0.5 np
P( X x ) P Z
npq
for n . This is a good approximation:
If n is large and p is not too close to 0 or 1.
Or, if p is reasonably close to 1/2, even when n is small.
To find the probability that x = k?
Use the normal distribution for the area x = k (1/2).
For k = 0, we use P(x +0.5) so probability will sum to 1.
Approximation works well if both np and nq 5.
The larger n is, the better the approximation will be.
 The Exponential Distribution

Used to model the length of time between two

occurrences of an event (the time between
arrivals)

Examples:
Time between trucks arriving at an unloading dock
Time between transactions at an ATM Machine
Time between phone calls to the main operator
 Exponential Distributions
Describes time or distance between events

Density function f(X)

= 0.5
f (t ) e t for t 0 = 2.0
0 elsewhere

Parameters X
=1/ = 1/
Exponential distribution notes:
The mean equals the standard deviation.
Note that = (1/), where is the parameter used in the book for the
exponential distribution.
 Exponential and Poisson
Distributions

For a Poisson process, if is the mean event arrival rate, what is

the distribution of the number of events occurring in a time interval
of length t?
It is a Poisson distribution with mean t.
It can also be shown for a Poisson process that the distribution of
the time until the next event occurs is exponential with parameter .
Similarly, an Erlang (gamma) distribution with parameter is the
distribution of the time until events occur.
Exponential distribution is a gamma distribution with = 1.
There are many important applications of the exponential
distribution (and the gamma distribution) in the areas of reliability
and queuing theory.
 Exponential Dist'n -
Memoryless Property

What was the memoryless property for a Poisson process?

The number of occurrences in one time interval is independent
of the number in any other disjoint time interval.
Thus future arrivals are completely independent of the past
history of arrivals.
How does the memoryless concept apply to the exponential
distribution of the time between arrivals?
The memoryless property of the exponential distribution implies
that
P( X t0 t | X t0 ) P( X t )

Or, the probability of waiting longer than t time units for the next
arrival is independent of how long we've already waited.
 Exponential Distribution
The exponential random variable x ( X > x ) has a
probability :
P ( X > x) = e -x
where is the mean number of occurrences per unit time,
x is the number of time units until the next occurrence, and
e = 2.71828
f(X)

x X = time between arrival

 Exponential Distribution
f(X)
P(0 X x)=P (X 0.5) = 1 e -x

0.5 X = time between arrival

The distribution has mean 1/ and variance 1/2.

 Exponential Distribution
Example 1
Example: Customers arrive at the service counter at
the rate of 15 per hour. What is the probability that the
arrival time between consecutive customers is less
than three minutes?

The mean number of arrivals per hour is 15, so = 15

Three minutes is .05 hours
P(arrival time < .05) = 1 e-X = 1 e-(15)(.05) = .5276
So there is a 52.76% probability that the arrival time
between successive customers is less than three
minutes
 Exponential Distribution
Example 2

Suppose that a study of certain computer system

reveals that the response time, in seconds,
has an exponential distribution with a mean of
3 seconds.
a. What is the probability that response time
exceeds 5 seconds? (answer = 0.1889)
b. What is the probability that response time
exceeds 10 seconds? (answer = 0.0357)
 Exponential Distribution
Example 3

The time (in hours) required to repair a machine is

an exponentially distributed random variable
with parameter = 0.5
a. What is the probability that repair time
exceeds 2 hours?
b. What is the conditional probability that a repair
takes at least 10 hours, given that its duration
exceeds 9 hours?
 Answers

P(X > 2) = 0.3679

P(X t0+t | X t0) = P(X t) = P(X 1) 0.6065