JOINT PROBABILITY

DISTRIBUTION
MATH142
Engineering Data Analysis
 Outcomes
Compute the probability distribution of a random variable for both discrete and continuous data.

• At the end of the lesson, the students are

expected to
• Use joint probability mass functions and joint
probability density functions to calculate
probabilities;
• Calculate marginal and conditional probability
distributions from joint probability
distributions; and
• Interpret and calculate covariance and
correlation between random variables.
 Joint Probability Mass Function
The joint probability mass function of the The marginal probability mass functions of X alone
discrete random variables X and Y, denoted as and of Y alone are
fXY(x, y), satisfies 𝑓𝑋 𝑥 = ෍ 𝑓 𝑥, 𝑦 𝑓𝑌 𝑦 = ෍ 𝑓 𝑥, 𝑦
(1) fXY(x, y) ≥ 0 𝑦 𝑥

(2) σ𝑥 σ𝑦 𝑓𝑋𝑌 𝑥, 𝑦 = 1
(3) fXY(x, y) = P(X = x, Y = y) 5-1/156 Mobile Response Time The response time
is the speed of page downloads and it is critical for a
(5-1) mobile Web site. As the response time increases,
customers become more frustrated and potentially
Sometimes referred to as the bivariate
abandon the site for a competitive one. Let X denote
probability distribution or bivariate the number of bars of service, and let Y denote the
distribution of the random variables X and Y. response time (to the nearest second) for a particular
P(X = x and Y = y) is usually written as user and site
P(X = x, Y = y).
The individual probability distribution of a random
variable
By specifying the probability of each of the points in The marginal probability distribution for X is found by
Fig. 5-1, we specify the joint probability distribution summing the probabilities in each column, whereas
of X and Y. Similarly to an individual random
variable, we define the range of the random the marginal probability distribution for Y is found by
variables (X, Y) to be the set of points (x, y) in two- summing the probabilities in each row. The results
dimensional space for which the probability that X = are shown in Fig. 5-6.
x and Y = y is positive.
x=1 x=2 x=3 fy

4 0.15 0.1 0.05 0.3

3 0.02 0.1 0.05 0.17
2 0.02 0.03 0.2 0.25
5-3/159 Marginal Distribution The joint probability
distribution of X and Y in Fig. 5-1 can be used to 1 0.01 0.02 0.25 0.28
find the marginal probability distribution of X. For
example, fx 0.2 0.25 0.55
fX(3) = P(X = 3) =
P(X=3, Y=1) + P(X=3, Y=2) + P(X=3, Y=3) + P(X=3, Y=4)
fX(3) = 0.25 + 0.2 + 0.05 + 0.05 = 0.55
 Guided Learning Activity
3.16/98 Show that the column and row totals 3.50/106 Suppose that X and Y have the
of Table 3.1 give the marginal distribution of 𝑋 following joint probability distribution:
alone and of 𝑌 alone. f(x, y) x
x Row 2 4
f(x, y) 0 1 2 Totals
y 1 0.10 0.15
0 3/28 9/28 3/28 15/28 3 0.20 0.30
y 1 3/14 3/14 0 3/7 5 0.10 0.15
2 1/28 0 0 1/28
Column Totals 5/14 15/28 3/28 1
(a) Find the marginal distribution of X.
Table 3.1: Joint Probability Distribution for (b) Find the marginal distribution of Y.
Example 3.16
 Joint Probability Distribution
3.14/95 Two refills for a ballpoint pen are
selected at random from a box that contains 3
blue refills, 2 red refills, and 3 green refills. If X
is the number of blue refills and Y is the
number of red refills selected, find
(a) the joint probability function f(x, y), and
(b) P[(X, Y) ∈ A], where A is the region
{(x, y)|x + y ≤ 1}.
 Joint Probability Density Function
A joint probability density function for the 5-2/158 Server Access Time Let the random variable
continuous random variables X and Y, denoted as X denote the time until a computer server connects to
fXY(x, y), satisfies the following properties:
your machine (in milliseconds), and let Y denote the
(1) fXY(x, y) ≥ 0 for all x, y time until the server authorizes you as a valid user (in
∞ ∞ milliseconds). Each of these random variables
(2) ‫׬‬−∞ ‫׬‬−∞ 𝑓𝑋𝑌 𝑥, 𝑦 𝑑𝑥 𝑑𝑦 = 1
measures the wait from a common starting time and X
(3) For any region R of two-dimensional space, < Y. Assume that the joint probability density function
𝑃 𝑋, 𝑌 ∈ 𝑅 = න න 𝑓𝑋𝑌 𝑥, 𝑦 𝑑𝑥 𝑑𝑦 for X and Y is
𝑅 fXY(x, y) = 6 × 10−6e−0.001x − 0.002y for x < y.
(5-2)
If the joint probability density function of random
variables X and Y is 𝑓𝑋𝑌 𝑥, 𝑦 , the marginal
probability density functions of X and Y are
𝑓𝑋 𝑥 = ‫𝑥 𝑌𝑋𝑓 𝑦׬‬, 𝑦 𝑑𝑦 and 𝑓𝑌 𝑦 = ‫𝑥 𝑌𝑋𝑓 𝑥׬‬, 𝑦 𝑑𝑥
(5-3)
where the first integral is over all points in the range of
𝑋, 𝑌 for which X = x and the second integral is over
all points in the range of 𝑋, 𝑌 for which Y = y.
 Joint Density Function
The region with nonzero probability is shaded
in Fig. 5-4. The property that this joint
probability density function integrates to 1 can
be verified by the integral of fXY(x, y) over his
region as follows:
∞ ∞
‫׬‬−∞ ‫׬‬−∞ 𝑓𝑋𝑌 𝑥, 𝑦 𝑑𝑦 𝑑𝑥 The probability that X < 1000 and Y < 2000 is
determined as the integral over the darkly shaded
= region in Fig 5-5.
∞ ∞
‫׬‬0 ‫ 𝑥׬‬6 × 10−6 𝑒 −0.001𝑥−0.002𝑦 𝑑𝑦 𝑑𝑥 1000 2000
𝑋 ≤ 1000, 𝑌 ≤ 2000 = ‫׬‬0 ‫𝑥׬‬ 𝑓𝑋𝑌 𝑥, 𝑦 𝑑𝑦 𝑑𝑥
= 6× 1000 2000 −0.002𝑦
∞
10−6 ‫׬‬0
∞ = 6 × 10−6 ‫׬‬0 ‫𝑥׬‬ 𝑒 𝑑𝑦 𝑒 −0.001𝑥 𝑑𝑥
‫ 𝑒 𝑥׬‬−0.002𝑦 𝑑𝑦 𝑒 −0.001𝑥
𝑑𝑥
−0.002𝑥 1000 𝑒 −0.002𝑥 −𝑒 −4
−6 ∞ 𝑒 =6 × 10−6 ‫׬‬0 𝑒 −0.001𝑥 𝑑𝑥
= 6𝑥10 ‫׬‬0 𝑒 −0.001𝑥 𝑑𝑥 0.002
0.002 1000 −0.003𝑥
∞ −0.003𝑥 = 0.003 ‫׬‬0 𝑒 − 𝑒 −4 𝑒 −0.001𝑥 𝑑𝑥
= 0.003 ‫׬‬0 𝑒 𝑑𝑥
1−𝑒 −3 −4 1−𝑒 −1
∞ ∞ 1 = 0.003 0.003 − 𝑒
‫׬‬−∞ ‫׬‬−∞ 𝑓𝑋𝑌 𝑥, 𝑦 𝑑𝑦 𝑑𝑥 = 0.003 0.003 = 1 0.001
=0.003(316.738 − 11.578)
P(X ≤ 1000, Y ≤ 2000 = 0.915
 Joint Density Distributions
3.15/96 A privately owned business operates a
drive-in facility and a walk-in facility. On a randomly
selected day, let X and Y, respectively, be the
proportions of the time that the drive-in and the
walk-in facilities are in use, and suppose that the
joint density function of these random variables is
2
2𝑥 + 3𝑦 , 0 ≤ 𝑥 ≤ 1, 0 ≤ 𝑦 ≤ 1,
𝑓 𝑥, 𝑦 = ൝5
0, elsewhere.
(a) Verify condition 2.
(b) Find P[(X, Y) ∈ A],
where A = {(x, y)|0 < x < ½, ¼ < y < ½}.
 Marginal Probability Density Function
2000 ∞
Examples:
𝑃 𝑌 > 2000 = න න 6 × 10−6 𝑒 −0.001𝑥−0.002𝑦 𝑑𝑦 𝑑𝑥
5-4/160 Server Access Time For the random 0 2000
variables that denote times in Example 5-2, ∞ ∞

calculate the probability that Y exceeds 2000 + න න 6 × 10−6 𝑒 −0.001𝑥−0.002𝑦 𝑑𝑦 𝑑𝑥

milliseconds. 2000 𝑥

This probability is determined as the integral of The first integral is

2000 ∞
fXY(x, y) over the darkly shaded region in Fig. 5-7. 𝑒 −0.002𝑦
The region is partitioned into two parts and different 6 × 10−6 න อ 𝑒 −0,001𝑥 𝑑𝑥
−0.002
limits of integration are determined for each part. 0
2000
2000
−6
6 × 10
= 𝑒 −4 න 𝑒 −0.001𝑥 𝑑𝑥
0.002
0
6 × 10−6 −4 1 − 𝑒 −2
= 𝑒 = 0.0475
0.002 0.001
The second integral is
∞ ∞ ∞
−0.002𝑦 −6
𝑒 6 × 10
6 × 10−6 න อ 𝑒 −0.001𝑥 𝑑𝑥 = න 𝑒 −0.003𝑥 𝑑𝑥
−0.002 0.002
2000 𝑥 2000
6 × 10−6 𝑒 −6
= = 0.0025
0.002 0.003
Therefore,
P(Y > 2000) = 0.0475 + 0.0025 = 0.05
 Marginal Probability Density Function
A probability for only one random variable, say, for fY(y) = 6 × 10−3e−0.002y(1 − e−0.001y) for y > 0
example, P(a < X < b), can be found from the marginal
probability distribution of X or from the integral of the
joint probability distribution of X and Y as We have obtained the marginal probability density
𝑏 𝑏 ∞
function of Y. Now,
𝑃 𝑎 < 𝑋 < 𝑏 = න 𝑓𝑋 𝑥 𝑑𝑥 = න න 𝑓 𝑥, 𝑦 𝑑𝑦 𝑑𝑥 ∞
𝑎 𝑎 −∞
𝑏 ∞
𝑃 𝑌 > 2000 = 6 × 10−3 න 𝑒 −0.002𝑦 1 − 𝑒 −0.001𝑦 𝑑𝑦
= ‫׬ 𝑎׬‬−∞ 𝑓 𝑥, 𝑦 𝑑𝑦 𝑑𝑥 2000
∞ ∞
Alternatively, the probability can be calculated from the 𝑒 −0.002𝑦 𝑒 −0.003𝑦
marginal probability distribution of Y as follows. = 6 × 10−3 อ − อ
−0.002 −0.003
2000 2000
For y > 0, 𝑦 𝑒 −4
𝑒 −6
= 6 × 10−3 − = 0.05
𝑓𝑌 𝑦 = න 6 × 10−6 𝑒 −0.001𝑥−0.002𝑦 𝑑𝑥 0.002 0.003
0 𝑦

= 6 × 10−6 𝑒 −0.002𝑦 න 𝑒 −0.001𝑥 𝑑𝑥

0
𝑦
𝑒 −0.001𝑥
= 6 × 10−6 𝑒 −0.002𝑦 อ
−0.001
0
1 − 𝑒 −0.001𝑦
= 6 × 10−6 𝑒 −0.002𝑦
0.001
 Marginal Probability Density Function
3.40/105 A fast-food restaurant operates both a drive-
through facility and a walk-in facility. On a randomly
selected day, let X and Y, respectively, be the proportions
of the time that the drive-through and walk-in facilities
are in use, and suppose that the joint density function of
these random variables is

2
𝑓 𝑥, 𝑦 = ቐ3 𝑥 + 2𝑦 , 0 ≤ 𝑥 ≤ 1, 0 ≤ 𝑦 ≤ 1,
0, elsewhere.

(a) Find the marginal density of X.

(b) Find the marginal density of Y.
(c) Find the probability that the drive-through facility is
busy less than one-half of the time.
 Conditional Distribution
CONDITIONAL PROBABILITY MASS / DENSITY Because the conditional probability mass/density
FUNCTION function fY|x(y) is a probability density function for
Let X and Y be two random variables, discrete or all y in Rx, the following properties are satisfied:
continuous. The conditional distribution of the (1) 𝑓𝑌|𝑥(𝑦) ≥ 0
random variable Y, given that X = x, is
𝑓𝑋𝑌 𝑥, 𝑦 2 σ 𝑓𝑌|𝑥 (𝑦) 𝑑𝑦 = 1 𝑜𝑟 ‫ = 𝑦𝑑 )𝑦(𝑥|𝑌𝑓 ׬‬1
𝑓𝑌 |𝑥 𝑦 = , 𝑓𝑋 (𝑥) > 0.
𝑓𝑋 𝑥
3 𝑃 𝑌 ∈ 𝐵|𝑋 = 𝑥 =

Similarly, the conditional distribution of the random ෍ 𝑓𝑌|𝑥 𝑦 = න 𝑓𝑌|𝑥 𝑦 𝑑𝑦

variable X, given that Y = y, is 𝑎𝑙𝑙 𝑦 𝑖𝑛 𝐵 𝐵
𝑓𝑋𝑌 𝑥, 𝑦
𝑓𝑋|𝑦 𝑥 = , 𝑓𝑌 (𝑦) > 0. for any set B in the range of Y
𝑓𝑌 𝑦
(5-5)
 Conditional Probability Mass Function
Examples: x=1 x=2 x=3 fy
5-5/162 Conditional Probabilities for Mobile
4 0.15 0.1 0.05 0.3
Response Time For Example 5-1, X and Y denote
the number of bars of signal strength and times you 3 0.02 0.1 0.05 0.17
need to state your departure city received,
2 0.02 0.03 0.2 0.25
respectively. Then,
𝑃 𝑋 = 3, 𝑌 = 1 1 0.01 0.02 0.25 0.28
𝑃 𝑌 = 1𝑋 = 3 =
𝑃 𝑋 = 3 fx 0.2 0.25 0.55
𝑓𝑋𝑌 3, 1 0.25
= = = 0.454
𝑓𝑋(3) 0.55 Additional Conclusion: Further work shows that
P(Y = 3|X = 3) = 0.091
The probability that Y = 2 given that X = 3 is P(Y = 4|X = 3) = 0.091.
𝑃 𝑋 = 3, 𝑌 = 2
𝑃 𝑌 = 2𝑋 = 3 = Note that
𝑃(𝑋 = 3)
𝑓𝑋𝑌 3,2 0.2 P(Y = 1|X = 3)+P(Y = 2|X = 3) + P(Y = 3|X = 3) +
= = = 0.364 P(Y = 4|X = 3) = 1.
𝑓𝑋( 3) 0.55
This set of probabilities defines the conditional
probability distribution of Y given that X = 3.
 Conditional Probability Mass Function
3.18/99 Referring to Joint Probability
Distribution below, find the conditional
distribution of X, given that Y = 1, and
use it to determine P(X = 0|Y = 1).
x Row
f(x, y) 0 1 2 Totals

0 3/28 9/28 3/28 15/28

y 1 3/14 3/14 0 3/7
2 1/28 0 0 1/28
Column Totals 5/14 15/28 3/28 1
 Conditional Probability Mass Function
3.49/106 Let X denote the number of times a
certain numerical control machine will
malfunction: 1, 2, or 3 times on any given day.
Let Y denote the number of times a technician
is called on an emergency call. Their joint
probability distribution is given as
f(x, y) x
1 2 3
y 1 0.05 0.05 0.10
3 0.05 0.10 0.35
5 0.00 0.20 0.10
(a) Evaluate the marginal distribution of X.
(b) Evaluate the marginal distribution of Y.
(c) Find P(Y = 3|X = 2).
 Conditional Probability Density Function
Examples:
3.19/100 The joint density function for the
random variables (X, Y), where X is the unit
temperature change and Y is the proportion of
spectrum shift that a certain atomic particle
produces is
10𝑥𝑦 2 , 0 < 𝑥 < 𝑦 < 1
𝑓𝑋𝑌 𝑥, 𝑦 = ቊ
0, elsewhere.
a) Find the marginal densities fX(x), fY(y), and
the conditional probability fY|x(y).
b) Find the probability that the spectrum
shifts more than half of the total
observations, given the temperature is
increased to 0.25 units.
 Conditional Probability Density Function
• 3.20/100 Given the joint density
function
𝑥 1 + 3𝑦 2
𝑓𝑋𝑌 𝑥, 𝑦 = ቐ , 0 < 𝑥 < 2, 0 < 𝑦 < 1
4
0, elsewhere,
find
fX(x), fY(y), fX|y(x)

and evaluate
P(¼ < X < ½|Y = ⅓).
 Conditional Probability Density Function
3.53/106 Given the joint density function

6−𝑥−𝑦
𝑓𝑋𝑌 𝑥, 𝑦 = ቐ , 0 < 𝑥 < 2, 2 < 𝑦 < 4,
8
0, elsewhere,

find P(1 < Y < 3|X = 1).

 Independence
For random variables X and Y, if any one of
the following properties is true, the others are
also true, and X and Y are independent.
(1) fXY(x, y) = fX(x)fY(y) for all x and y
(2) fY|x(y) = fY(y) for all x and y with fX(x) > 0
(3) fX|y(x) = fX(x) for all x and y with fY(y) > 0
(4) P(X ∈ A, Y ∈ B) = P(X ∈ A) P(Y ∈ B) for
any sets A and B in the range of X and Y,
respectively.
(5-7)
 Independence
Examples: • Therefore, fXY(x, y) = fX(x)fY(y) for all x and y,
5-11/166 Independent Random Variables and X and Y are independent.
Suppose that Example 5-2 is modified so that the
joint probability density function of X and Y is
fXY(x, y) = 2 × 10−6e−0.001x − 0.002y for x ≥ 0 and y ≥ 0.
Show that X and Y are independent and determine To determine the probability requested, property
P(X > 1000, Y < 1000). (4) of Equation 5-7 and the fact that each
The marginal probability density function of X is random variable has an exponential distribution
∞
can be applied.
𝑓𝑋 𝑥 = න 2 × 10−6 𝑒 −0.001𝑥−0.002𝑦 𝑑𝑦
P(X > 1000, Y < 1000) = P(X > 1000)P(Y < 1000)
0
= 0.001e−0.001x for x > 0 = e−1(1 − e−2) = 0.0318
The marginal probability
∞
density function of Y is

𝑓𝑌 𝑦 = න 2 × 10−6 𝑒 −0.001𝑥−0.002𝑦 𝑑𝑥
0
= 0.002e−0.002y for y > 0
 Independence
• 3.21/102 Show that the random variables of
Example 3.14 are not statistically
independent.
• Table 3.1: Joint Probability Distribution for
Example 3.14

x Row Totals
f(x, y) 0 1 2
0 3/28 9/28 3/28 15/28
y 1 3/14 3/14 0 3/7
2 1/28 0 0 1/28
Column Totals 5/14 15/28 3/28 1
 Examples
• 5-1/170 Show that the following function satisfies the
properties of a joint probability mass function.
x y fXY(x, y)
Determine the following:
1 1 1/4
(a) P(X < 2.5, Y < 3)
1.5 2 1/8
(b) P(X < 2.5)
1.5 3 1/4
(c) P(Y < 3)
2.5 4 1/4
(d) P(X > 1.8, Y > 4.7)
3 5 1/8
(e) E(X) E(Y) V(X) V(Y)
(f) Marginal probability distribution of the random variable X
(g) Conditional probability distribution of Y given that X = 2.5
(h) Conditional probability distribution of X given that Y = 2.
(i) E(Y|X = 1.5)
(j) Are X and Y independent?
 Examples
• 5-2/170 Determine the value of c that makes the • 5-6/171 A small-business Web site contains 100
function f(x, y) = c(x + y) a joint probability mass pages and 60%, 30%, and 10% of the pages
function over the nine points with x = 1, 2, 3 and y contain low, moderate, high graphic content,
= 1, 2, 3. Determine the following: respectively. A sample of four pages is selected
• (a) P(X = 1, Y < 4) (b) P(X = 1) without replacement, and X and Y denote the
• (c) P(Y = 2) (d) P(X < 2, Y < 2) number of pages with moderate and high graphics
output in the sample. Determine:
• (e) E(X), E(Y), V(X), and V(Y)
• (a) fXY(x, y)
• (f) Marginal probability distribution of the random
variable X • (b) fX(x)
• (g) Conditional probability distribution of Y given • (c) E(X)
that X = 1
• (d) fY|3(y)
• (h) Conditional probability distribution of X given
that Y = 2 • (e) E(Y|X = 3)
• (i) E(Y|X = 1) • (f) V(Y|X = 3)
• (j) Are X and Y independent? • (g) Are X and Y independent?
 Expected Value of a Function of Two Random Variables
• 𝐸 ℎ 𝑋, 𝑌 =
σ σ ℎ 𝑥, 𝑦 𝑓𝑋𝑌 𝑥, 𝑦 𝑋, 𝑌 discrete
൝
‫ ׬ ׬‬ℎ 𝑥, 𝑦 𝑓𝑋𝑌 𝑥, 𝑦 𝑑𝑥 𝑑𝑦 𝑋, 𝑌 continuous

(5-13)
5-19/174 Expected Value of a Function of
Two Random Variables For the joint
probability distribution of the two random
variables in Example 5-1, calculate E[(X −
μX)(Y − μY)].
 Covariance
A measure of linear relationship between the
random variables
If the relationship between the random
variables is nonlinear, the covariance might
not be sensitive to the relationship, as
illustrated in Fig. 5-12(d). The only points with
nonzero probability are the points on the circle.

cov(X, Y) = σXY = E[(X − μX)(Y − μY)]

(5-14)
 Covariance
• 5-20/176 In Example 5-1, the random
variables X and Y are the number of signal
bars and the response time (to the nearest
second), respectively. Interpret the
covariance between X and Y as positive or
negative. As the signal bars increase, the
response time tends to decrease. Therefore,
X and Y have a negative covariance. The
covariance was calculated to be −0.5815 in
Example 5-19.
 Covariance
4.47/127 For the random variables X
and Y whose joint density function is
given in Exercise 3.40 on page 105,
find the covariance.

2
𝑓 𝑥, 𝑦 = ቐ3 𝑥 + 2𝑦 , 0 ≤ 𝑥 ≤ 1, 0 ≤ 𝑦 ≤ 1,
0, elsewhere
 Covariance
• 5-21/176 Covariance For the discrete random
variables X and Y with the joint distribution
shown in Fig. 5-13, determine σXY and ρXY.
 Correlation
• The correlation between random variables X and Y,
denoted as ρXY, is
cov 𝑋, 𝑌 σ𝑋𝑌
𝜌𝑋𝑌 = =
𝑉 𝑋 𝑉 𝑌 𝜎𝑋 𝜎𝑌
(5-15)
For any two random variables X and Y
−1 ≤ ρXY ≤ +1
(5-16)

If X and Y are independent random variables,

σXY = ρXY = 0
(5-17)
 Correlation
• 5-22/177 Correlation Suppose that the random
variable X has the following distribution:
P(X = 1) = 0.2, P(X = 2) = 0.6, P(X = 3) = 0.2.
Let Y = 2X + 5. That is,
P(Y = 7) = 0.2, P(Y = 11) = 0.2.
Determine the correlation between X and Y. Refer
to Fig. 5-14. Because X and Y are linearly related, ρ
= 1. This can be verified by direct calculations.
 Examples
• 5-33/178 Determine the covariance and
correlation for the following joint probability
distribution

x 1 1 2 4
y 3 4 5 6
fXY(x, y) 1/8 1/4 1/2 1/8
 Examples
• 5-35/178 Determine the value for c and the
covariance and correlation for the joint
probability mass function fXY(x, y) = c(x + y)
for x = 1, 2, 3 and y = 1, 2, 3.

• 5-41/179 Determine the covariance and

correlation for the joint probability density
function fXY(x, y) = e−x − y over the range 0 < x
and 0 < y.
 Examples
• 5-43/179 The joint probability distribution is
x −1 0 0 1
y 0 −1 1 0
fXY(x, y) ¼ 1/4 1/4 1/4
• Show that the correlation between X and Y
is zero, but X and Y are not independent.
 Summary
• A joint probability mass function is a • A conditional probability mass function is the
function used to calculate probabilities for probability mass function of the conditional
two or more discrete random variables. probability distribution of a discrete random
• A joint probability density function is a variable.
function used to calculate probabilities for • A conditional probability density function is
two or more continuous random variables. the probability density function of the
• A marginal probability mass function is the conditional probability distribution of a
probability mass function of a discrete continuous random variable.
random variable obtained from the joint • The covariance is a measure of association
probability distribution of two or more between two random variables obtained as
random variables. the expected value of the product of the two
• A marginal probability density function is random variables around their means; that is
the probability density function of a cov(X, Y) = σXY = E[(X − μX)(Y − μY)].
continuous random variable obtained from • In the most general usage, the correlation is
the joint probability distribution of two or a measure of the interdependence among
more random variables. data. The concept may include more than two
variables.
 References
• Montgomery and Runger. Applied Statistics and Probability for Engineers, 6th Ed. © 2014
• Walpole, et al. Probability and Statistics for Engineers and Scientists 9th Ed. © 2012, 2007, 2002