Ho Chi Minh City Faculty of Applied Sciences

University of Technology and Education Department of Mathematics

MATHEMATICAL STATISTICS FOR ENGINEERS

(MATH132901E)

CONTINUOUS RANDOM VARIABLES

Nguyễn Ngọc Tứ

Nguyễn Ngọc Tứ CONTINUOUS RANDOM VARIABLES 1 / 26

Lecture outline

ˆ Continuous random variables and PDFs

ˆ Uniform distribution
ˆ Cumulative distribution functions
ˆ Normal distribution
ˆ Exponential distribution

Nguyễn Ngọc Tứ CONTINUOUS RANDOM VARIABLES 2 / 26

Random variables

Definition – Random variable

- A random variable X : Ω → R is a function.
- A random variable is continuous if both of the following apply:
1. Its set of possible values consists either of all numbers in a single
interval on the number line or all numbers in a disjoint union of
such intervals.
2. No possible value of the variable has positive probability, that
is, P(X = c) = 0 for any possible value c.

Nguyễn Ngọc Tứ CONTINUOUS RANDOM VARIABLES 3 / 26

Continuous r.v.’s and pdf’s

Definition
A continuous r.v. is described by a probability density function fX

Z b
P(a ≤ X ≤ b) = fX (x)dx
a
For f (x) to be a pdf, it must satisfy the following two conditions:
(i) fX (x) ≥ 0, ∀x ∈ R
R∞
(ii) −∞ fX (x)dx = 1

Nguyễn Ngọc Tứ CONTINUOUS RANDOM VARIABLES 4 / 26

Continuous r.v.’s and pdf’s

1. The current in a certain cir- f (x)

cuit as measured by an amme-
ter is a continuous random vari-
able X with the following density 0.43
function
(
0.075x + 0.2 3 ≤ x ≤ 5
f (x) =
0 otherwise

a. Calculate P(X ≤ 4.5). How

does this probability compare to 3 5
P(X < 4.5).
b. Calculate P(3.5 ≤ X ≤ 4.5)
and also P(4 < X ).

Nguyễn Ngọc Tứ CONTINUOUS RANDOM VARIABLES 5 / 26

Examples
2. A bus never departs before its scheduled time and always leaves within 4 minutes
after the scheduled departure. Let X denote the delay (in minutes) beyond the
scheduled departure time. Suppose that the probability density function (pdf) of X
is given by (
k (x 2 + x), 0 ≤ x ≤ 4,
f (x) =
0, otherwise.
a. Find the value of the constant k.
b. Compute the probability that the bus departs within 2 minutes after the sched-
uled time, i.e., calculate P(X ≤ 2).

Nguyễn Ngọc Tứ CONTINUOUS RANDOM VARIABLES 6 / 26

Mean and Variance

The expected or mean value of a continuous r.v. X with pdf f (x) is

Z ∞
E (X ) = xfX (x)dx
−∞

If X is a continuous r.v. with pdf f (x) and g (X ) is any function of X , then

Z ∞
E [g (X )] = g (x)fX (x)dx
−∞

The variance of a continuous r.v. X with pdf f (x) is

Z ∞
2
Var (X ) = σX = (x − E (X ))2 fX (x)dx = E (X 2 ) − E 2 (X )
−∞
p
The standard deviation of X is σX = V (X ).

Nguyễn Ngọc Tứ CONTINUOUS RANDOM VARIABLES 7 / 26

Mean and Variance - Example

The pdf of X is 
 3 (1 − x 2 ) 0 ≤ x ≤ 1,
f (x) = 2
0 otherwise.
Then Z ∞ Z 1
3 3
E (X ) = x · f (x)dx = x · (1 − x 2 )dx =
−∞ 0 2 8
Z ∞ Z 1
3 1
E (X 2 ) = x 2 · f (x)dx = x 2 · (1 − x 2 )dx =
−∞ 0 2 5
and  2
1 3 19
Var (X ) = − = and σX = 0.244
5 8 320

Nguyễn Ngọc Tứ CONTINUOUS RANDOM VARIABLES 8 / 26

Exercises
15. Let Y be a random variable whose probability density function (pdf) is given
by (
k y 3 (1 − y ), 0 ≤ y ≤ 1,
g (y ) =
0, otherwise.

a. Determine the value of k that makes g (y ) a valid pdf. Then compute the
probabilities:

P(Y ≤ 0.5) and P 0.2 < Y ≤ 0.5 .

b. Let µ and σ denote

the mean and standard deviation of Y . Compute
P |Y − µ| > σ , i.e., the probability that Y is more than one standard
deviation away from its mean.

Nguyễn Ngọc Tứ CONTINUOUS RANDOM VARIABLES 9 / 26

Cumulative distribution function (CDF)
∗ CDF for continuous r.v.’s:
Z x
FX (x) = P(X ≤ x) = fX (y )dy , ∀x ∈ R
−∞

1 + 3x 0 ≤ x ≤ 2
Example. Suppose the pdf of X is given by f (x) = 8 8
0 otherwise
Find the CDF of X . Rx
Solution. If x < 0 then F (x) = −∞ f (y )dy = 0.
For any number x ∈ [0, 2],
Z x Z x 
1 3 x 3
F (x) = f (y )dy = + y dy = + x 2
−∞ 0 8 8 8 16
 
Rx R2 1 3
If x > 2 then F (x) = −∞ f (y )dy = 0 + y dy = 1.
8 8
Nguyễn Ngọc Tứ CONTINUOUS RANDOM VARIABLES 10 / 26
Cumulative distribution function (CDF) - Example
Thus 

0 x <0
x 3

F (x) = + x2 0≤x ≤2
 8 16


1 x >2
∗ For any number a, P(X > a) = 1 − F (a), and for any two numbers a and
b with a < b,
P(a ≤ X ≤ b) = F (b) − F (a).
The probability that X is between 1 and 1.5 is
   
1 3 2 1 3 2 19
P(1 ≤ X ≤ 1.5) = F (1.5)−F (1) = 1.5 + 1.5 − 1 + 1 =
8 16 8 16 64
and the probability that X exceeds 1 is
 
1 3 2 11
P(X > 1) = 1 − P(X ≤ 1) = 1 − F (1) = 1 − 1 + 1 = .
8 16 16
Nguyễn Ngọc Tứ CONTINUOUS RANDOM VARIABLES 11 / 26
Exercises
11. Let X denote the amount of time a book on two-hour reserve is actually
checked out, and suppose the cdf is


 0 x <0
 2
x
F (x) = 0≤x ≤2
4


1 2≤x
a. Calculate P(X ≤ 1.5), P(0.6 ≤ X ≤ 1.2), P(X > 1).
b. The median checkout duration µ
e (solve 0.5 = F (e
µ)).
c. Calculate EX , V (X ), σX . [Hint: f (x) = F ′ (x).]

Nguyễn Ngọc Tứ CONTINUOUS RANDOM VARIABLES 12 / 26

Exercises

Nguyễn Ngọc Tứ CONTINUOUS RANDOM VARIABLES 13 / 26

Gaussian (normal) PDF

Definition
A continuous rv X is said to have a normal distribution with pa-
rameters µ and σ, where −∞ < µ < ∞ and 0 < σ, if the pdf of X
is
1 2 2
f (x; µ, σ) = √ e −(x−µ) /(2σ ) , ∀x ∈ R
σ 2π
Notation: X ∼ N(µ, σ 2 ) with E (X ) = µ, Var (X ) = σ 2 .

• If µ = 0 and σ = 1, then we have standard normal distribution

1 2
X ∼ N(0, 1) with pdf fX (x) = √ e −x /2
2π

Nguyễn Ngọc Tứ CONTINUOUS RANDOM VARIABLES 14 / 26

Calculating normal probabilities
• Let Y = aX + b. Then E (Y ) = aµ + b, Var (Y ) = a2 σ 2 . Thus, Y ∼ N(aµ +
• Notation. CDF of standard normal distribution
Z x
1 2
P(X ≤ x) :=Φ(x) = √ e −t /2 dt.
2π −∞

Proposition

X −µ
If X ∼ N(µ, σ 2 ), then ∼ N(0, 1). Thus,
σ
   
b−µ a−µ
P(a ≤ X ≤ b) = Φ −Φ ,
σ σ
 
a−µ
P(X ≤ a) = Φ .
σ

Nguyễn Ngọc Tứ CONTINUOUS RANDOM VARIABLES 15 / 26

Calculating normal distribution

Example

Let X ∼ N(1.25; 0.462 ). Calculate: a) P(1 ≤ X ≤ 1.75) b) P(X > 2)

Solution.
 
1.00 − 1.25 X − 1.25 1.75 − 1.25
a) P(1.00 ≤ X ≤ 1.75) = P ≤ ≤
0.46 0.46 0.46
   
1.75 − 1.25 1.00 − 1.25
=Φ −Φ
0.46 0.46
=
 
2 − 1.25
b) P(X > 2) = 1 − P(X ≤ 2) = 1 − Φ = 0.0516
0.46

Nguyễn Ngọc Tứ CONTINUOUS RANDOM VARIABLES 16 / 26

Use calculators to find function Φ
 
2 − 1.25
EX 1. Calculate Φ =?
0.45
fx570 or VINACAL 570
MODE → 3:STAT → 1:Var →AC 
2 − 1.25
SHIFT → 1 → 5:Distr → 1:P = 0.95221
0.45
fx580
MODE → 6 → AC  
2 − 1.25
OPTN → ⇓ → 4 (Norm Dist) → 1:P = 0.95221
0.45
EX 2. Let Φ(c) = 0.975. Calculate c
fx570 VN or VINACAL 570 VN
MODE → ⇓ → 3 → 3 → 0.975 = = = 1.96
fx580
MODE → 7 → 3 → 0.975 = = = 1.96

Nguyễn Ngọc Tứ CONTINUOUS RANDOM VARIABLES 17 / 26

Normal distribution - Exercises
34. The article "Reliability of Domestic-Waste Biofilm Reactors" (J.

of Envir. Engr.,
1995: 785-790) suggests that substrate concentration mg/cm3 of influent to a
reactor is normally distributed with µ = 0.35 and σ = 0.06.
a. What is the probability that the concentration exceeds 0.25?
b. What is the probability that the concentration is at most 0.10?
c. How would you characterize the largest 5% of all concentration values?

Nguyễn Ngọc Tứ CONTINUOUS RANDOM VARIABLES 18 / 26

Normal distribution - Exercises
49. Consider babies born in the "normal" range of 37 − 43 weeks gestational age.
Extensive data supports the assumption that for such babies born in the United
States, birth weight is normally distributed with mean 3430 g and standard devia-
tion 490 g.
a. What is the probability that the birth weight of a randomly selected baby of this
type exceeds 4000 g? Is between 3000 and 4000 g ?
b. What is the probability that the birth weight of a randomly selected baby of this
type is either less than 2000 g or greater than 5000 g ?
c. How would you characterize the largest 0.1% of all birth weights?

Nguyễn Ngọc Tứ CONTINUOUS RANDOM VARIABLES 19 / 26

Exponential distribution

Definition
X is said to have an exponential distribution with parameter λ (λ >
0) if the pdf of X is
(
λe −λx x ≥ 0,
fX (x) =
0 otherwies.

• The CDF of X is
(
1 − e −λx x ≥ 0,
F (x) =
0 x <0

1 1
Notation. X ∼ Exp(λ), E (X ) = ; Var (X ) = 2
λ λ
Nguyễn Ngọc Tứ CONTINUOUS RANDOM VARIABLES 20 / 26
Exponential distribution

Example

Let X ∼ Exp(λ) with E (X ) = 6.

Calculate: a) P(X ≤ 10) b) P(5 ≤ X ≤ 10)
Solution.

1
We have 6 = EX = . Thus, λ = 0.1667.
λ
a) P(X ≤ 10) = F (10) = 1 − e −(0.1667)(10) = 1 − 0.189 = 0.811

b) P(5 ≤ X ≤ 10) = F (10) − F (5)

= (1 − e −1.667 ) − (1 − e −8.335 ) = 0.246

Nguyễn Ngọc Tứ CONTINUOUS RANDOM VARIABLES 21 / 26

Exponential distribution - Exercises
60. Let X denote the distance (m) that an animal moves from its birth site to the
first territorial vacancy it encounters. Suppose that for banner-tailed kangaroo rats,
X has an exponential distribution with parameter λ = 0.0135 (as suggested in the
article "Competition and Dispersal from Multiple Nests,” Ecology, 1997).
a. What is the probability that the distance is at most 100 m? At most 200 m?
Between 100 and 200 m?
b. What is the probability that distance exceeds the mean distance by more than
2 standard deviations?

Nguyễn Ngọc Tứ CONTINUOUS RANDOM VARIABLES 22 / 26

Homework
1. Let X (in grams) denote the weight of a product of type A. Its probability density
function is given by
 
 3 −x 2 + 6x − 8 , 2 ≤ x ≤ 4,

f (x) = 4
0, otherwise.
a. Suppose that products are selected one by one until a product with weight less
than 3.5 grams is found. What is the probability that exactly 5 products must be
selected?
b. If 4 products are selected independently, what is the probability that at least one
product has a weight exceeding 3.8 grams?

Nguyễn Ngọc Tứ CONTINUOUS RANDOM VARIABLES 23 / 26

Homework
2. Suppose that the weight (in pounds) of a certain species of dog is normally
distributed with mean µ = 40 and σ = 8.
a. What is the probability that the weight of a randomly selected dog exceeds
45 pounds?
b. What is the probability that the weight of a randomly selected dog is
between 35 and 45 pounds?
c. Find the value c such that the interval (40 − c, 40 + c) contains 95% of
all weight values.
d. If three dogs are independently selected, what is the probability that at
least one weighs more than 45 pounds?

Nguyễn Ngọc Tứ CONTINUOUS RANDOM VARIABLES 24 / 26

Homework
3. The compressive strength X (in psi) of a concrete sample is normally distributed
with mean µ = 3000 and σ = 200. (Compressive strength is measured on a con-
tinuous scale.)
a. A concrete sample is considered acceptable if its compressive strength lies be-
tween 2850 psi and 3150 psi. What is the probability that a randomly selected
sample is acceptable?
b. Suppose the acceptable range is given by (3000 − c, 3000 + c). Find the value
of c such that 95% of all samples have an acceptable compressive strength.
c. If 12 samples are independently selected, what is the expected number of ac-
ceptable samples among these 12?
d. Let Y denote the number of samples among the 12 that have a compressive
strength less than 3100 psi. What is the probability that at most 10 samples have
a compressive strength less than 3100 psi? (Hint: Y is a binomial variable; first
compute p = P(X < 3100).)

Nguyễn Ngọc Tứ CONTINUOUS RANDOM VARIABLES 25 / 26

Homework
61. Data collected at Toronto Pearson International Airport suggests that an ex-
ponential distribution with mean value 2.735 hours is a good model for rainfall
duration.
a. What is the probability that the duration of a particular rainfall event at this
location is at least 2 hours? At most 3 hours? Between 2 and 3 hours?
b. What is the probability that rainfall duration exceeds the mean value by more
than 2 standard deviations?

Nguyễn Ngọc Tứ CONTINUOUS RANDOM VARIABLES 26 / 26