NUEVA VIZCAYA STATE UNIVERSITY

Bayombong, Nueva Vizcaya

College of Engineering
Chapter 4: Continuous Probability Distribution
Continuous Random Variables
A random variable X is continuous if possible values comprise PROBABILITY FROM THE PROBABILITY DENSITY
either a single interval on the number line or a union of disjoint FUNCTION
intervals. Let X be a continuous random variable. Then a probability
Example: If in the study of the ecology of a lake, X, the distribution or probability density function (pdf) of X is a function
random variable may be depth measurements at randomly f(x) such that for any two numbers a and b with a ≤ b, we have
chosen locations. Then X is a continuous random variable. The
range for X is the minimum depth possible to the maximum
depth possible.
In principle variables such as height, weight, and
temperature are continuous, in practice the limitations of our Equation 1
measuring instruments restrict us to a discrete (though
The probability that X is in the interval [a, b] can be calculated
sometimes very finely subdivided) world.
by integrating the pdf of the random variable X.
However, continuous models often approximate real-
world situations very well, and continuous mathematics
(calculus) is frequently easier to work with than mathematics of The probability that X takes on a value in the interval [a, b] is the
discrete variables and distributions. area above this interval and under the graph of the density
function:
Suppose the variable X of interest is the depth of a lake
at a randomly chosen point on the surface.
Let M = the maximum depth (in meters), so that any
number in the interval [0, M] is a possible value of X.
If we “discretize” X by measuring depth to the nearest
meter, then possible values are nonnegative integers less than
or equal to M.
The resulting discrete distribution of depth can be
pictured using a probability histogram.
For f(x) to be a legitimate pdf, it must satisfy the following two
conditions:
If we draw the histogram so that the area of the
rectangle above any possible integer k is the proportion of the
lake whose depth is (to the nearest meter) k, then the total area
of all rectangles is 1:

Example:
1. Consider the reference line connecting the valve stem
on a tire to the center point.
Let X be the angle measured clockwise to the location
If depth is measured much more accurately, each rectangle in of an imperfection. One possible pdf for X is
the resulting probability histogram is much narrower, though the
total area of all rectangles is still 1.

The probability density function is graphed below,

If we continue in this way to measure depth more and more

finely, the resulting sequence of histograms approaches a
smooth curve.
Because for each histogram the total area of all rectangles Clearly f(x) ≥ 0. How can we show that the area of this pdf is
equals 1, the total area under the smooth curve is also 1. equal to 1?
How do we calculate P (90 <= X <= 180)?
The probability that the angle of occurrence is within 90° of the
reference line (reference line is at 0 degrees)?

Because whenever 0 ≤ a ≤ b ≤ 360 in example and

P (a ≤ X ≤ b) depends only on the width b – a of the interval,
X is said to have a uniform distribution.

1|MODULE 4
Prepared by:
VHANESSA LIAN T. MARIANO
Emergency Instructor
 NUEVA VIZCAYA STATE UNIVERSITY
Bayombong, Nueva Vizcaya
College of Engineering
Chapter 4: Continuous Probability Distribution
Therefore, a continuous rv X is said to have a uniform
distribution on the interval [A, B] if the pdf of X is

2. “Time headway” in traffic flow is the elapsed time

between the times that one car finishes passing a fixed
point and the instant that the next car begins to pass
that point.
Let X = the time headway for two randomly chosen For x < A, F(x) = 0, since there is no area under the graph of the
consecutive cars on a freeway during a period of heavy density function to the left of such an x.
flow. For example: For x ≥ B, F(x) = 1, since all the area is accumulated to the left
of such an x. Finally for A ≤ x ≤ B,

This pdf of X is essentially the one suggested in “The Statistical

Properties of Freeway Traffic” (Transp. Res., vol. 11: 221–228)

The graph of f(x) is given in Figure 4.4; there is no density

associated with headway times less than .5, and headway
density decreases rapidly (exponentially fast) as x increases
from .5. The entire cdf is

The graph of this cdf appears in Figure 4.7.

Clearly, f(x) ≥ 0; and

CUMULATIVE DISTRIBUTION FUNCTION

The cumulative distribution function F(x) for a continuous
random variable “X” is defined for every number “x” by
Using F(x) to Compute Probabilities:

For each x, F(x) is the area under the density curve to the left of
x. This is illustrated in Figure 4.5, where F(x) increases smoothly
as x increases.
SAMPLE PROBLEMS:

1. A probability density function is given by:

A graph of this density function is shown in Figure 4.5.

Example:
1. Let X, the thickness of a certain metal sheet, have a uniform
distribution on [A, B]. The density function is shown in Figure
4.6.

2|MODULE 4
Prepared by:
VHANESSA LIAN T. MARIANO
Emergency Instructor
 NUEVA VIZCAYA STATE UNIVERSITY
Bayombong, Nueva Vizcaya
College of Engineering
Chapter 4: Continuous Probability Distribution
It must be 1/15. Then the probability density function must
be given by:
f(x) = 0 for x < 0 (since waiting time can’t be negative).
f(x) 1/15 = for 0 < x < 15
f(x) = 0 for x > 15 (since waiting time can’t be more than 15
minutes)
Let’s check the integral of f(x) for x between 0 and 15, the
only interval for which f(x) is not equal to zero. We have
Figure 4.5
It is not hard to show that f(x) meets the requirements
for a probability density function. First, since x2 is (as required), so the constant
always positive for any real value of x, f(x) is always value, 1/15 is correct.
greater than or equal to zero. Second, the integral of
the probability density function from –∞ to +∞ is equal By comparison to equation 2 the probability that the waiting
to 1, as we can show by integration: time will be less than 5 minutes must be:

2. A student arrives at a bus stop and waits for the bus. He

knows that the bus comes every 15 minutes (which we will
assume is exact), but he doesn’t know when the next bus
will come. Let’s assume the bus is as likely to come in any Using the expressions for the probability density function,
one instant as in any other within the next 15 minutes. Let the general expression for the cumulative distribution
the time the student has to wait for the bus be x minutes. function for this illustration must be:
Let us first explore the probabilities intuitively, and then
apply equation 1 and 2.
a. What is the probability that the waiting time will be
less than or equal to 15 minutes?
Since we know that the bus comes every 15
minutes, this probability must be 1.
b. What is the probability that the waiting time will be
less than 5 minutes?
Since the bus is as likely to come in any one
instant as in any other to a maximum of 15
minutes, the probability that the waiting time is
5 1
less than 5 minutes must be =
15 3
Similarly, the probability that the waiting time is The probability density function and the cumulative
less than 10 minutes must be
10
= .
2 distribution function are shown graphically in Figure 6.3.
15 3
Then we can generalize the expression for
probability. The probability that the “x” waiting time
will be less than x minutes, where 0 ≤ x ≤ 15, must
𝑥
be .
15
c. What is the probability that the waiting time will be
between 5 minutes and 10 minutes?
This must be:

Comparison to equation 1 with a = 5 and b = 10

indicates that:

d. What simple expression for f(x) will integrate with

respect to x to give x/15?
3|MODULE 4
Prepared by:
VHANESSA LIAN T. MARIANO
Emergency Instructor
 NUEVA VIZCAYA STATE UNIVERSITY
Bayombong, Nueva Vizcaya
College of Engineering
Chapter 4: Continuous Probability Distribution
3. A probability density function is given by:
d.

a) What is the value of b?

b) From this obtain the probability that X is between 2 and
c) What is the probability that X is exactly 2?
d) Find the cumulative distribution function of X.
Solutions:
a. To satisfy the equation:

Then to summarize, the cumulative distribution

function of X is:
Then a graph of the density function for this example is
shown below:

b.

c.

4|MODULE 4
Prepared by:
VHANESSA LIAN T. MARIANO
Emergency Instructor
 NUEVA VIZCAYA STATE UNIVERSITY
Bayombong, Nueva Vizcaya
College of Engineering
Chapter 4: Continuous Probability Distribution

EXPECTED VALUES AND VARIANCE OF CONTONUOUS

RANDOM VARIABLES
The expected (or mean) value of a continuous random variable
X with the pdf f(x) is:

The variance of a continuous random variable X with pdf f(x)

and mean value µ is

The standard deviation (SD) of X is

Sample Problems:
1. The random variable of Example 6.1 has the probability
density function given by:

a. Find the probability that X is between 1 and 2.

b. Find the cumulative distribution function of X.
c. Find the expected value of X.
d. Find the variance and standard deviation of X
Solutions:

5|MODULE 4
Prepared by:
VHANESSA LIAN T. MARIANO
Emergency Instructor
 NUEVA VIZCAYA STATE UNIVERSITY
Bayombong, Nueva Vizcaya
College of Engineering
Chapter 4: Continuous Probability Distribution

Then the variance of the waiting time is 18.75 minute^2

, and the standard deviation is √18.75= 4.33 minutes.
c) The interval which is within two standard deviations of
the expected value is

2. The probability density function for the waiting time was

given by

The probability that the waiting time for this particular

probability distribution is within two standard deviations of
a) Find the expected value of the waiting time, X minutes. its expected mean value is 1 or 100%. We will find that other
b) Find the variance and standard deviation of the waiting distributions often give different results. For example, a
time. different result is obtained for the normal distribution, as we
c) What is the probability that the waiting time is within two will see in the next chapter.
standard deviations of its expected mean value?
Solutions:

Then the expected value of the waiting time, or the mean,

µx, of the probability distribution, is 7.5 minutes. This
seems reasonable, as it is halfway between the minimum
waiting time, 0 minutes, and the maximum waiting time, 15
minutes.

6|MODULE 4
Prepared by:
VHANESSA LIAN T. MARIANO
Emergency Instructor
 NUEVA VIZCAYA STATE UNIVERSITY
Bayombong, Nueva Vizcaya
College of Engineering
Chapter 4: Continuous Probability Distribution
NORMAL DISTRIBUTION Standard Normal Distribution
The normal distribution is probably the most important  The standard normal distribution rarely occurs naturally.
distribution in all of probability and statistics.  Instead, it is a reference distribution from which information
about other normal distributions can be obtained via a
Many populations have distributions that can be fit very simple formula.
closely by an appropriate normal (or Gaussian, bell) curve.  These probabilities can then be found “normal tables”.
 This can also be computed with a single command in R.
Examples: height, weight, and other physical Figure below illustrates a standard normal distribution graph.
characteristics, scores on various tests, etc.

A continuous random variable. X is said to have a normal

distribution with parameters µ and σ > 0 (or µ and 𝜎 2 ), if
the pdf of X is

Nonstandard Normal Distributions

When X ~ N(µ, σ 2), probabilities involving X are computed by
“standardizing.” The standardized variable is (X – µ)/σ.
The statement that X is normally distributed with Subtracting µ shifts the mean from µ to zero, and then dividing
parameters µ and 𝜎 2 is often abbreviated X ~ N(µ, 𝜎 2 ). by σ scales the variable so that the standard deviation is 1 rather
than σ.
Clearly f(x; µ, σ) ≥ 0, but a somewhat complicated calculus Proposition
∞
argument must be used to verify that ∫−∞ f(x; µ, σ) dx = If X has a normal distribution with mean µ and standard
1. deviation σ, then

Similarly, it can be shown that E(X) = µ and V(X) = 𝜎 2 , so

the parameters are the mean and the standard deviation of
X. is distributed standard normal.
Why do we standardize normal random variables?
Figure below presents graphs of f(x; µ, σ) for several
different (µ, σ) pairs.

Equality of nonstandard and standard normal curve areas has a

standard normal distribution. Thus

The normal distribution with parameter values µ = 0 and

σ = 1 is called the standard normal distribution.

A random variable with this distribution is called a standard normal

random variable and is denoted by Z. Its pdf is:
Using Tables for the Normal Distribution
Attached Table gives values of z0 along the left-hand side
and right-hand side of the table over two pages. The
The graph of f(z; 0, 1) is called the standard normal curve. numbers along the top of the table give smaller increments.
Its inflection points are at 1 and –1. The cdf of the standard normal The value of z for a particular row and column is the sum
is of the value of z0 for that row (along the sides) plus the
increment, ∆z, for that column (along the top of the table).

To illustrate, see the attached table of normal distribution.

Say we want Φ(–0.76): we look for the row labeled z0 = –
Note we use the special notation Φ(z) for the cdf of Z. 0.7 along the sides and the column labeled ∆z = –0.06

7|MODULE 4
Prepared by:
VHANESSA LIAN T. MARIANO
Emergency Instructor
 NUEVA VIZCAYA STATE UNIVERSITY
Bayombong, Nueva Vizcaya
College of Engineering
Chapter 4: Continuous Probability Distribution
along the top (since –0.76 = (–0.7) + (–0.06)) and read Φ(– The reader should note that other forms of tables for
0.76) = 0.2236. the normal distribution are also in common use. One
The diagram at the top of the table towards the right form gives the probability of a result in one tail of the
indicates that Φ(z) corresponds to the area under the curve distribution, that is Pr [Z > z1] for z1 ≥ 0, or Pr [Z < z1]
to the left of a particular value of z (here z = –0.76). for z1 ≤ 0. A variation gives the probability
Suppose that instead we want Φ(+0.76). This is given on corresponding to both tails together. Another type
the second page of the table. As before, we look for the gives the probability of a result between the mean and
applicable row, labeled z0 = 0.7 along the sides, and the z2 standard deviations from the mean, that is
column labeled ∆z = 0.06 (since 0.76 = 0.7 + 0.06). For this Pr [Z < z2] for z2 ≥ 0, or Pr [Z > z2] for z2 ≤ 0. These
value of z we read from the table that Φ(0.76) = 0.7764. different forms of tables must not be confused.
Because the distribution is symmetrical, there must be a Confusion is reduced because a small graph at the top
simple relation between Φ(–0.76) and Φ(+0.76), or in of a table almost always indicates which area
general between Φ(–z) and Φ(+z). That relation is: corresponds to the values given.
2. A city installs 2000 electric lamps for street lighting.
or in this case Φ(–0.76) = 1 – Φ(+0.76) = 1 – 0.7764 = These lamps have a mean burning life of 1000 hours
0.2236. Of course that means that Φ(–0.00) = Φ(+0.00) = with a standard deviation of 200 hours. The normal
0.5000, so half of the total area under the curve is to the left distribution is a close approximation to this case.
of z = 0, the mean and median and mode of the distribution. a) What is the probability that a lamp will fail in the
If you think about it, that makes sense. first 700 burning hours?
b) What is the probability that a lamp will fail between
Sample Problems: 900 and 1300 burning hours?
1. A. What is the probability that Z for a normal probability c) How many lamps are expected to fail between 900
distribution is between –0.76 and +0.76? and 1300 burning hours?
B. What is the probability that Z for a normal probability d) What is the probability that a lamp will burn for
distribution is smaller than –0.76 or larger than +0.76? exactly 900 hours?
e) What is the probability that a lamp will burn
between 899 hours and 901 hours before it fails?
f) After how many burning hours would we expect
10% of the lamps to be left?
g) After how many burning hours would we expect
90% of the lamps to be left?
Solutions
a.

A sketch such as that shown in Figure 7.6 is very helpful in

visualizing the required integral and finding appropriate values
from the table. Then Pr [burning life < 700 hours] = 0.0668 or 0.067.
Solutions
a) Pr [–0.76 < Z < +0.76] corresponds to the middle area cross-
hatched in Figure 7.6.
The calculation of probabilities is as follows:

b) Pr [(Z < –0.76) ∪ (Z > + 0.76)] corresponds to the outer areas

in the sketch above.
b. .

Check: Between them, parts (a) and (b) cover all possible
results:
Then

Because the normal distribution is used so frequently, it is

important to become familiar with Table.
8|MODULE 4
Prepared by:
VHANESSA LIAN T. MARIANO
Emergency Instructor
 NUEVA VIZCAYA STATE UNIVERSITY
Bayombong, Nueva Vizcaya
College of Engineering
Chapter 4: Continuous Probability Distribution

f. This corresponds to the time at which Pr [burning life

> x1 hours] = 0.10, so Pr [burning life < x1 hours] = 1
– 0.10 = 0.90.

c. This is a continuation of part (b). The expected

number of failures is given by the total number of
lamps multiplied by the probability of failure in that
interval. Then the expected number of failures =
(2000) (0.6247) = 1249.4 or 1250 lamps.
Because the burning life of each lamp is a random
variable, the actual number of failures between 900
and 1300 burning hours would be only approximately
1250.
d. Since the burning life is a continuous random
variable, the probability of a life of exactly 900 burning
hours (not 900.1 hours or 900.01 hours or 900.001
hours, etc.) is zero. Another way of looking at it is that Once again, we could apply linear interpolation but
there are an infinite number of possible lifetimes the accuracy of the calculation probably does not
between 899 and 901 hours, so the probability of any justify it. Since (0.90 – 0.8997) << (0.9015 – 0.90), let
one of them is one divided by infinity, so zero. us take z1 = 1.28. Then we have
e. Since this is an interval rather than a single exact
value, the probability of failure in this interval is not
infinitesimal (although in this instance the probability
is small).

Then after 1256 hours of burning, we would expect

10% of the lamps to be left. And again, because the
burning time is a random variable, performing the
experiment would give a result which would be close
to 1256 hours but probably not exactly that, even if
the normal distribution with the given values of the
mean and standard deviation applied exactly.
g. .

so z2 ≈ –1.28.

We could apply linear interpolation between the

values given in Table. However, considering that in
practice the parameters are not known exactly and
the real distribution may not be exactly a normal
distribution, the extra precision is not worthwhile. After 744 hours we would expect 90% of the lamps to
be left.

9|MODULE 4
Prepared by:
VHANESSA LIAN T. MARIANO
Emergency Instructor
 NUEVA VIZCAYA STATE UNIVERSITY
Bayombong, Nueva Vizcaya
College of Engineering
Chapter 4: Continuous Probability Distribution
3. In another city 2500 electric lamps are installed for
street lighting. The lamps come from a different
manufacturer and have a mean burning life of 1050
hours. We know from past experience that the
distribution of burning lives approximates a normal
distribution. The 250th lamp fails after 819 hours.
Approximately what is the standard deviation of
burning lives for this set of lamps?
Solution:

b. For this part, σ is the unknown. From Table A1 we

look for a value of z for which Φ(z2) = 0.05. We
find Φ(–1.65) = 0.0495 and Φ(–1.64) = 0.0505.
Then z2 must be between –1.65 and –1.64. Since
in this case the desired value of Φ(z2) is halfway
between Φ(–1.65) and Φ(–1.64), interpolation is
very easy, giving z2 = –1.645. Then

If the standard deviation can be reduced to 2.67

while keeping the mean constant, the specification
will just be met.
5. An engineer decides to buy four new snow tires for his
car. He finds that Retailer A is offering a special cash
Then the standard deviation of burning hours is rebate, which depends on how much snow falls during
approximately 180 hours. (As well as random variation, the first winter. If this snowfall is less than 50% of the
the term “approximately” covers a “correction for mean annual snowfall for his city, his rebate will be
continuity” which we will encounter a little later.) 50% of the list price. If the snowfall that winter is more
than 50% but less than 75% of the mean annual
4. The strengths of individual bars made by a certain snowfall, his rebate will be 25% of the list price. If the
manufacturing process are approximately normally snowfall is more than 75% of the mean annual
distributed with mean 28.4 and standard deviation 2.95 snowfall, he will receive no rebate. The engineer finds
(in appropriate units). To ensure safety, a customer from a reference book that the annual snowfall for his
requires at least 95% of the bars to be stronger than city has a mean of 80 cm and standard deviation of 20
24.0. cm and approximates a normal distribution. The list
a. Do the bars meet the specification? price for the brand and size of tires he wants is $80.00
b. By improved manufacturing techniques the per tire.
manufacturer can make the bars more uniform The engineer checks other retailers and finds that
(that is, decrease the standard deviation). What Retailer B sells the same brand and size of tires with
value of the standard deviation will just meet the the same warranty for the same list price but offers a
specification if the mean stays the same? discount of 5% of the list price regardless of snowfall
Solutions: that year.
a. a) Compare the expected costs of the two deals. Which
expected cost is less?
b) How much is the difference for four new snow tires?
Neglect the relative advantages of a cash rebate as
compared to a discount.
Solutions:
a. For Retailer A: µ = 80 cm, σ = 20 cm. 50% of µ is
40 cm, and 75% of µ is 60 cm
The probability that the bars will be stronger than 24.0
is 1 – 0.0681 = 0.9319 or 93.2%. Since this is less than
95%, the bars do not meet the specification.

10 | M O D U L E 4
Prepared by:
VHANESSA LIAN T. MARIANO
Emergency Instructor
 NUEVA VIZCAYA STATE UNIVERSITY
Bayombong, Nueva Vizcaya
College of Engineering
Chapter 4: Continuous Probability Distribution

NORMAL APPROXIMATION TO A BINOMIAL DISTRIBUTION

Using the normal approximation to the binomial distribution simplified
the process. To compute the normal approximation to the binomial
distribution, take a simple random sample from a population. You
must meet the conditions for a binomial distribution:

 There are a certain number n of independent trials

 The outcomes of any trial are success or failure
 Each trial has the same probability of a success p

Recall that if “X” is the binomial random variable, then 𝑋 ∼ 𝐵(𝑛, 𝑝)

. The shape of the binomial distribution needs to be similar to the
shape of the normal distribution. To ensure this, the quantities 𝑛𝑝
and 𝑛𝑞 must both be greater than five ( 𝑛𝑝 > 5 𝑎𝑛𝑑 𝑛𝑞 > 5 );
the approximation is better if they are both greater than or equal to
10). Then the binomial can be approximated by the normal
distribution with mean 𝜇 = 𝑛𝑝 and standard deviation 𝜎 = √𝑛𝑝𝑞
. Remember that 𝑞 = 1 − 𝑝 . In order to get the best
approximation, add 0.5 to x or subtract 0.5 from x (use 𝑥 + 0.5
or 𝑥 − 0.5 ). The number 0.5 is called the continuity correction
factor and is used in the following
Sample Problems:

Discount from Retailer B is 5% of list price, so the discount from

Retailer B is larger than the expected rebate from Retailer A.
Therefore, the expected cost of buying from Retailer B is a little less
than the expected cost of buying from Retailer A.
b. Cost of four new snow tires is as follows.
List price: (4) ($80.00) = $320.00
After rebate from Retailer A, expected cost = (1– 0.0454)
($320.00) = $305.48
After discount from Retailer B, cost = (1 – 0.05) ($320.00)
= $304.00
Then the difference in expected cost for four new snow tires
is $1.48.

NOTE: Review attached additional reference and tables for your

basis.

11 | M O D U L E 4
Prepared by:
VHANESSA LIAN T. MARIANO
Emergency Instructor