Chapter 6

Continuous Probability Distributions

Continuous Random Variables and their
Probability Distributions
• A random variable 𝑋 is said to be continuous if it can take on the
infinite number of possible values associated with intervals of real
numbers.
• A function 𝑓(𝑥) of a random variable 𝑋 is called the probability
density function if
1. 𝑓 𝑥 ≥ 0 𝑓𝑜𝑟 𝑎𝑙𝑙 𝑥
∞
2. ‫׬‬−∞ 𝑓 𝑥 𝑑𝑥 = 1
𝑏
3. 𝑝 𝑎 ≤ 𝑋 ≤ 𝑏 = ‫𝑓 𝑎׬‬ 𝑥 𝑑𝑥
• If a random variable 𝑋 is continuous with probability density function
𝑓(𝑥), then the distribution function is

𝑏
•𝐹 𝑏 =𝑝 𝑋≤𝑏 = ‫׬‬−∞ 𝑓 𝑥 𝑑𝑥

• Note that 𝐹′ 𝑥 = 𝑓 𝑥
6.2
• Suppose a random variable 𝑋 has a probability density function given
𝑘𝑥 1 − 𝑥 0≤𝑥≤1
by 𝑓 𝑥 = ቊ
0 𝑒𝑙𝑠𝑒𝑤ℎ𝑒𝑟𝑒
• A) Find the value of 𝑘 that makes this a probability density function
• B) Find 𝑝 0.4 ≤ 𝑋 ≤ 1
• C) Find 𝑝 𝑋 ≤ 0.4|𝑋 ≤ 0.8
• D) Find the distribution function
Solution
1 1 1
• A) ‫׬‬0 𝑓 𝑥 𝑑𝑥 = 1→ ‫׬‬0 𝑘𝑥 1 − 𝑥 𝑑𝑥 = 1 → 𝑘 ‫׬‬0 𝑥 − 𝑥 2 𝑑𝑥 = 1
𝑥2 𝑥3 1 1 1
• 𝑘( − |0 = 1 →𝑘 − = 1; 𝑘 = 6
2 3 2 3

1 𝑥2 𝑥3 1
• B) 𝑝 0.4 ≤ 𝑋 ≤ 1 = ‫׬‬0.4 6𝑥 1 − 𝑥 𝑑𝑥 = 6( − |0.4 =0.648
2 3

𝑝 𝑋≤0.4
• C) 𝑝 𝑋 ≤ 0.4|𝑋 ≤ 0.8 = = 0.3928
𝑝 𝑋≤0.8
Continue

•𝐹 𝑏 =𝑝 𝑋≤𝑏 =
0 𝑏≤0
𝑏2 𝑏3
൞ 𝑏 𝑓 𝑥 𝑑𝑥 = 6 −
‫׬‬0 2 3 0<𝑏<1
1 𝑏≥1
6.8
• The proportion of impurities X in certain copper ore samples is a
random variable having probability density function
2
•𝑓 𝑥 =ቊ 12𝑥 1−𝑥 0≤𝑥≤1
0 𝑒𝑙𝑠𝑒𝑤ℎ𝑒𝑟𝑒
• If four such samples are independently selected, find the probability
that Exactly one has a proportion of impurities exceeding 0.5
• 𝑋1 , 𝑋2 , 𝑋3 , 𝑋4
• 𝑌: Nb of samples out of four for which the proportion of impurities
exceeding 0.5
• Y: Binomial with parameters 𝑛 = 4 𝑎𝑛𝑑 𝑝 = 𝑝(𝑋 > 0.5)
Solution
1
• 𝑝 𝑋 > 0.5 = ‫׬‬0.5 12𝑥 2 1 − 𝑥 𝑑𝑥 = 0.6875

• Y: Nb of samples out of four with proportion of impurities exceeding

0.5. Binomial: n=4, p=0.6875

4 3
•𝑝 𝑌=1 = 1
𝑝 1−𝑝 = 0.0839
Expected values of Continuous random
variables
∞
•𝜇=𝐸 𝑋 = ‫׬‬−∞ 𝑥𝑓 𝑥 𝑑𝑥

∞
• 𝜎2 =𝑉 𝑋 =𝐸 𝑋−𝜇 2 = ‫׬‬−∞ 𝑥 − 𝜇 2 𝑓 𝑥 𝑑𝑥 = 𝐸 𝑋 2 − 𝜇2

• 𝐸 𝑎𝑋 + 𝑏 = 𝑎𝐸 𝑋 + 𝑏 and 𝑉 𝑎𝑋 + 𝑏 = 𝑎2 𝑉 𝑋

1
• Tchebysheff’s theorem: 𝑝 𝑋 − 𝜇 < 𝑘𝜎 ≥ 1 − (𝑘 > 1)
𝑘2
10
• The proportion of time X that an industrial robot is in operation
during a 40-hour work week is a random variable with probability
2𝑥 0≤𝑥≤1
density function 𝑓 𝑥 = ቊ
0 𝑒𝑙𝑠𝑒𝑤ℎ𝑒𝑟𝑒
• A) Find the mean and the variance of 𝑋.
• B) For the robot under study, the profit 𝑌 for a week is given by 𝑌 =
200𝑋 − 60. Find the mean and variance of 𝑌.
• C) Find an interval in which the profit should lie for at least 75% of the
weeks that the robot is in use.
Solution
1
• A) 𝜇 = 𝐸 𝑋 = ‫׬‬0 2𝑥 2 𝑑𝑥 = 2/3
2 1 3 1
• 𝐸 𝑋 = ‫׬‬0 2𝑥 𝑑𝑥 = 2
• 𝑉 𝑋 = 𝜎 2 = 𝐸 𝑋 2 − 𝜇2 = 1/18
400 400−180
• B) 𝐸 𝑌 = 200𝐸 𝑋 − 60 = − 60 = = 220/3
3 3
• V(Y)=200^2V(X)=200^2/18
1
• C) Tchebyshev: 1 − 2 = 0.75 → 𝑘 = 2
𝑘
• Interval: 𝑢𝑌 − 𝑘𝜎𝑌 , 𝑢𝑌 + 𝑘𝜎𝑌 = (−20.947,167.614)
13
• The pH of water samples from a specific lake is a random variable X
3
7−𝑥 2 5≤𝑥≤7
with probability density function 𝑓 𝑥 = ൝8
0 𝑒𝑙𝑠𝑒𝑤ℎ𝑒𝑟𝑒
• A) Find E(X) and V(X). (5.5, 0.15)

• B) Find an interval shorter than (5,7) in which at least ¾ of the pH

measurements must lie. (4.725, 6.2746)

• C) Would you expect to see a pH measurement below 5.5 very often?

Why?
The Exponential distribution
1 −𝑥/𝜃
𝑒 𝑥>0
•𝑓 𝑥 =൝ 𝜃
0 𝑒𝑙𝑠𝑒𝑤ℎ𝑒𝑟𝑒

•𝐸 𝑋 =𝜃

• 𝑉 𝑋 = 𝜃2
30
• Suppose Y has an exponential density function with mean 𝜃. Show
that 𝑝 𝑌 > 𝑎 + 𝑏|𝑌 > 𝑎 = 𝑝 𝑌 > 𝑏 . This is referred to as the
memoryless property of the exponential distribution.

∞ ∞ 1 −𝑥/𝜃 −𝑥/𝜃 ∞
•𝑝 𝑌>𝑏 = ‫𝑓 𝑏׬‬ 𝑥 𝑑𝑥 = ‫𝑒 𝜃 𝑏׬‬ 𝑑𝑥 = −𝑒 𝑏
= 𝑒 −𝑏/𝜃

𝑝 𝑌>𝑎+𝑏 𝑒 − 𝑎+𝑏 /𝜃
• 𝑝 𝑌 > 𝑎 + 𝑏|𝑌 > 𝑎 = = = 𝑒 −𝑏/𝜃
𝑝 𝑌>𝑎 𝑒 −𝑎/𝜃
31
• The magnitudes of earthquakes recorded in a region of North
America can be modeled by an exponential distribution with mean
2.4 as measured on the Richter scale. Find the probability that the
next earthquake to strike this region will
• A) Exceed 3 on the Richter scale
• B) Fall between 2 and 3 on the Richter scale
∞ 1 −𝑥/2.4
• A) 𝑝 𝑋 > 3 = ‫׬‬3 𝑒 𝑑𝑥 = (−𝑒 −𝑥/2.4 |∞
3 = 𝑒 −3/2.4
2.4
3 1 −𝑥/2.4
• B) 𝑝 2 < 𝑋 < 3 = ‫׬‬2 𝑒 𝑑𝑥 = (−𝑒 −𝑥/2.4 |32 = −𝑒 −3/2.4 +
2.4
𝑒 −2/2.4
32
• Refer to 31. Of the next 10 earthquakes to strike this region, find the
probability that at least one will exceed 5 on the Richter scale.

• 𝑝 𝑋 > 5 = 𝑒 −5/2.4

• Y: nb of earthquakes out of 10 with magnitude exceeding 5 on the

Richter scale. Binomial: n=10, 𝑝 = 𝑒 −5/2.4
• 𝑝 𝑌 ≥ 1 = 1 − 𝑝 𝑌 = 0 = 1 − 1 − 𝑝 10
33
• A pumping station operator observes that the demand for water at a
certain hour of the day can be modeled as an exponential random
variable with a mean of 100 cfs (cubic feet per second)
• A) Find the prob that the demand will exceed 200 cfs on a randomly
selected day.
• B) What is the maximum water-producing capacity that the station
should keep on line for this hour so that the demand will exceed this
production capacity with a prob of only 0.01?
Solution
• A)p 𝑋 > 200 = 𝑒 −200/100 = 𝑒 −2

• B) 𝑝 𝑋 > 𝑎 = 0.01 → 𝑒 −𝑎/100 = 0.01 → 𝑎 = 460.52

Relationship between the Poisson and the
exponential distribution
• If Y=number of occurrences of an event in time interval of length t
• X=waiting time until occurrence of first event (or length of time
between two successive occurrences of that event)
• Then,
• Y follows a Poisson distribution with parameter λ if and only if
• X follows an exponential distribution with parameter 𝜃, where
• λ = 1/𝜃
34
• Suppose customers arrive at a certain checkout counter at the rate of
two every minute.
• A) Find the mean and variance of the waiting time between
successive customer arrivals.
• B) if a clerk takes three minutes to serve the first customer arriving at
the counter, what is the prob that at least one more customer is
waiting when the service of the first customer is completed?
solution
1
• A) λ=2 per minute; 𝜃 = ; mean and variance are respectively ½ and
2
¼

• B) Poisson with mean λ=6. 𝑝 𝑌 ≥ 1 = 1 − 𝑝 0 = 1 − 𝑒 −6

1
• X: Exponential, 𝜃 =
2
3
• 𝑝 𝑋 < 3 = ‫׬‬0 2𝑒 −2𝑥 𝑑𝑥 = 1 − 𝑒 −6
42
• The service times at teller windows in a bank were found to follow an
exponential distribution with a mean of 3.2 minutes. A customer
arrives at a window at 4:00 PM.
• A) Find the prob that he will still be there at 4:02 PM.
• B) Find the prob that that he will still be there at 4:04 PM given that
he was there at 4:02 PM
Solution
• A) X: service time
• 𝑝 𝑋 > 2 = 𝑒 −2/3.2

• B)𝑝 𝑋 > 4|𝑋 > 2 = 𝑝 𝑋 > 2 (memoryless property)

Normal Distribution
Normal Distribution

• The probability density function for the normal distribution:

1 𝑥−μ 2
1 −2 σ
𝑓 𝑥 = 𝑒
σ 2π

• 𝐸 𝑋 = 𝜇, 𝑉 𝑋 = 𝜎 2

Normal Distribution 25
Normal Distribution

Note that the normal distribution is defined by two parameters, μ and

σ . There is one normal distribution, Z, that is special. It has a μ = 0 and
a σ = 1. This is the Z distribution, also called the standard normal
distribution

Normal Distribution 26
Z-Distribution
• Any normal distribution can be converted into a standard normal
distribution by transforming the normal random variable into the
standard normal random variable:
𝑋−μ
𝑍=
σ
• The areas under the curve for the Standard Normal Distribution (Z)
has been computed and tabled. The table we use here gives you the
area under the curve from 0 to z.

Normal Distribution 27
Normal Distribution

Normal Distribution 28
Examples
• 𝑝 0 < 𝑍 < 0.1 = 0.0398
• 𝑝 0 < 𝑍 < 0.12 = 0.0478
• 𝑝 𝑍 > 0.5 = 0.5 − 𝑝 0 < 𝑍 < 0.5 = 0.5 − 0.1915
• 𝑝 1 < 𝑍 < 1.3 = 𝑝 0 < 𝑍 < 1.3 − 𝑝 0 < 𝑍 < 1 = 0.4032 −
0.3413
• 𝑝 𝑍 > 1.03 = 0.5 − 𝑝 0 < 𝑍 < 1.03 = 0.5 − 0.3485
• 𝑝 −0.2 < 𝑍 < 0.6 = 𝑝 −0.2 < 𝑍 < 0 + 𝑝 0 < 𝑍 < 0.6 =
𝑝 0 < 𝑍 < 0.2 + 𝑝(0 < 𝑍 < 0.6)

Two Sample Z Test 29

Example: Salary
Suppose that the average salary of college graduates is N.D. with
μ=$40,000 and σ=$10,000.
(a) What proportion of college graduates will earn $24,800 or less?
(b) What proportion of college graduates will earn $53,500 or more?
(c) What proportion of college graduates will earn between $45,000 and
$57,000?

Normal Distribution 30
Example: Salary

.4357

$24,800 $40,000 X

-1.52 0 Z

a)
24800 − 40000
𝑝 𝑋 < 24800 = 𝑝 𝑍 < = 𝑝 𝑍 < −1.52
10000
= 𝑝 𝑍 > 1.52 = 0.5 − 𝑝 0 < 𝑍 < 1.52 = 0.5 − 0.4357 = 0.0643
Answer: 6.43% of college graduates will earn less than $24,800.
Normal Distribution 31
Example: Salary
(b) What proportion of
college graduates will earn .4115

$53,500 or more? $40,000

.0885
$53,500

0 +1.35 Z

Solution:
𝑝 𝑋 ≥ 53500 = 𝑝 𝑍 ≥ 1.35
= 0.5 − 𝑝 0 < 𝑍 < 1.35 = 0.5 − 0.4115 = 0.0885
Answer: .0885. Thus, 8.85% of college graduates will
earn $53,500 or more.

Normal Distribution 32
Example: Salary

.1915
(c) What proportion of college
graduates will earn between $40k $45k $57k

0 .5 1.7 Z
$45,000 and $57,000?

𝑝 45000 < 𝑋 < 57000 = 𝑝 0.5 < 𝑍 < 1.7 = 0.4554 − 0.1915
= 0.2639

Normal Distribution 33
56
• For a standard normal random variable Z, find a number 𝑧0 such that
• 𝑝 𝑍 ≤ 𝑧0 = 0.5; 𝑧0 = 0
• 𝑝 𝑍 ≤ 𝑧0 = 0.8749; p Z < 0 + 𝑝 0 < 𝑍 < 𝑧0 = 0.8749 →
𝑝 0 < 𝑍 < 𝑧0 = 0.3749 → 𝑧0 = 1.15
• 𝑝 𝑍 ≥ 𝑧0 = 0.117; 𝑝 0 < 𝑍 < 𝑧0 = 0.383 → 𝑧0 = 1.19
• 𝑝 𝑍 ≥ 𝑧0 = 0.617 → 𝑝 𝑧0 < 𝑍 < 0 = 0.117 → 𝑝(0 < 𝑍 <
−𝑧0 ) = 0.117 → 𝑧0 = −0.295
• 𝑝 −𝑧0 ≤ 𝑍 ≤ 𝑧0 = 0.95 → 2𝑝 0 < 𝑍 < 𝑧0 = 0.95 → 𝑝(0 < 𝑍 <
𝑧0 )=0.475→ 𝑧0 = 1.96

Two Sample Z Test 34

57
• The weekly amount spent for maintenance and repairs in a certain
company has approximately a normal distribution with a mean of
$400 and a standard deviation of $20. If $450 is budgeted to cover
repairs for next week, what is the probability that the actual costs will
exceed the budgeted amount?

Two Sample Z Test 35

Solution
450−400
• 𝑝 𝑋 > 450 = 𝑝 𝑍 >
20
• = 𝑝 𝑍 > 2.5
• = 0.5 − 𝑝 0 < 𝑍 < 2.5
• = 0.5 − 0.4938
• = 0.0062

Two Sample Z Test 36

61
• Wires manufactured for use in a certain computer system are
specified to have resistances between 0.12 and 0.14 ohm. The actual
measured resistances of the wires produced by Company A have a
normal probability distribution with a mean of 0.13 ohm and a
standard deviation of 0.005 ohm.
• A) What is the prob that a randomly selected wire from company A’s
production will meet the specifications.

Two Sample Z Test 37

continue
• B) If four such wires are used in the system and all are selected from
company A, what is the prob that all four will meet the specifications?

Two Sample Z Test 38

Solution
• 𝐴) 𝑝 0.12 < 𝑋 < 0.14 = 𝑝 −2 < 𝑍 < 2
• = 2𝑝 0 < 𝑍 < 2 = 2 ∙ 0.4772 = 0.9544

• B)Y: Nb of wires out of four which meet the specifications.

• Y: Binomial with parameters n=4 and p=0.9544
• P(Y=4)=0.9544^4=0.83

Two Sample Z Test 39

65
• Sick-leave time used by employees of a firm in one month has
approximately a normal distribution with a mean of 200 hours and a
variance of 400.
• A) Find the prob that total sick leave for next month will be less than
150 hours.
• B) In planning schedules for next month, how much time should be
budgeted for sick leave if that amount is to be exceeded with a prob
of only 0.1?

Two Sample Z Test 40

Solution
• 𝐴) 𝑝 𝑋 < 150 = 𝑝 𝑍 < −2.5 = 𝑝 𝑍 > 2.5 = 0.5 − 𝑝(0 < 𝑍 <
2.5) = 0.5 − −.4938 = 0.0062

𝑎−200
• B) 𝑝 𝑋 > 𝑎 = 0.1 → 𝑝 𝑍 > = 0.1
20
𝑎−200
•→𝑝 0<𝑍< = 0.4
20
𝑎−200
•→ = 1.285
20
• → 𝑎 = 225.7

Two Sample Z Test 41