Professional Documents
Culture Documents
Chapter 4: Pairs of Random Variables: Nguyễn Thị Thu Thủy
Chapter 4: Pairs of Random Variables: Nguyễn Thị Thu Thủy
(1)
NGUYỄN THỊ THU THỦY
HANOI – 2019
(1)
Email: thuy.nguyenthithu2@hust.edu.vn
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 1 / 74
Introduction
This chapter analyzes experiments that produce two random variables, X and Y .
1 FX,Y (x, y), the joint cumulative distribution function of two random variables.
2 PX,Y (x, y), the joint probability mass function for two discrete random variables.
3 fX,Y (x, y), the joint probability density function of two continuous random
variables.
4 Functions of two random variables.
5 Conditional probability and independence.
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 2 / 74
Introduction
This chapter analyzes experiments that produce two random variables, X and Y .
1 FX,Y (x, y), the joint cumulative distribution function of two random variables.
2 PX,Y (x, y), the joint probability mass function for two discrete random variables.
3 fX,Y (x, y), the joint probability density function of two continuous random
variables.
4 Functions of two random variables.
5 Conditional probability and independence.
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 2 / 74
Introduction
This chapter analyzes experiments that produce two random variables, X and Y .
1 FX,Y (x, y), the joint cumulative distribution function of two random variables.
2 PX,Y (x, y), the joint probability mass function for two discrete random variables.
3 fX,Y (x, y), the joint probability density function of two continuous random
variables.
4 Functions of two random variables.
5 Conditional probability and independence.
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 2 / 74
Introduction
This chapter analyzes experiments that produce two random variables, X and Y .
1 FX,Y (x, y), the joint cumulative distribution function of two random variables.
2 PX,Y (x, y), the joint probability mass function for two discrete random variables.
3 fX,Y (x, y), the joint probability density function of two continuous random
variables.
4 Functions of two random variables.
5 Conditional probability and independence.
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 2 / 74
Introduction
This chapter analyzes experiments that produce two random variables, X and Y .
1 FX,Y (x, y), the joint cumulative distribution function of two random variables.
2 PX,Y (x, y), the joint probability mass function for two discrete random variables.
3 fX,Y (x, y), the joint probability density function of two continuous random
variables.
4 Functions of two random variables.
5 Conditional probability and independence.
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 2 / 74
Introduction
This chapter analyzes experiments that produce two random variables, X and Y .
1 FX,Y (x, y), the joint cumulative distribution function of two random variables.
2 PX,Y (x, y), the joint probability mass function for two discrete random variables.
3 fX,Y (x, y), the joint probability density function of two continuous random
variables.
4 Functions of two random variables.
5 Conditional probability and independence.
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 2 / 74
4.1 Joint Cumulative Distribution Function 4.1.1 Definitions
4.1.1 Definitions
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 3 / 74
4.1 Joint Cumulative Distribution Function 4.1.1 Definitions
4.1.1 Definitions
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 3 / 74
4.1 Joint Cumulative Distribution Function 4.1.1 Definitions
4.1.1 Definitions
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 3 / 74
4.1 Joint Cumulative Distribution Function 4.1.2 Properties
4.1.2 Properties
Remark 4.1
The joint CDF has properties that are direct consequences of the definition. For example,
we note that the event {X < x} suggests that Y can have any value so long as the
condition on X is met. This corresponds to the joint event {X < x, Y < ∞}. Therefore,
FX (x) = P [X < x] = P [X < x, Y < ∞] = lim FX,Y (x, y) = FX,Y (x, ∞). (4.2)
y→∞
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 4 / 74
4.1 Joint Cumulative Distribution Function 4.1.2 Properties
4.1.2 Properties
Remark 4.1
The joint CDF has properties that are direct consequences of the definition. For example,
we note that the event {X < x} suggests that Y can have any value so long as the
condition on X is met. This corresponds to the joint event {X < x, Y < ∞}. Therefore,
FX (x) = P [X < x] = P [X < x, Y < ∞] = lim FX,Y (x, y) = FX,Y (x, ∞). (4.2)
y→∞
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 4 / 74
4.1 Joint Cumulative Distribution Function 4.1.2 Properties
4.1.2 Properties
Remark 4.1
The joint CDF has properties that are direct consequences of the definition. For example,
we note that the event {X < x} suggests that Y can have any value so long as the
condition on X is met. This corresponds to the joint event {X < x, Y < ∞}. Therefore,
FX (x) = P [X < x] = P [X < x, Y < ∞] = lim FX,Y (x, y) = FX,Y (x, ∞). (4.2)
y→∞
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 4 / 74
4.1 Joint Cumulative Distribution Function 4.1.2 Properties
4.1.2 Properties
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 5 / 74
4.1 Joint Cumulative Distribution Function 4.1.2 Properties
4.1.2 Properties
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 5 / 74
4.1 Joint Cumulative Distribution Function 4.1.2 Properties
4.1.2 Properties
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 5 / 74
4.1 Joint Cumulative Distribution Function 4.1.2 Properties
4.1.2 Properties
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 5 / 74
4.1 Joint Cumulative Distribution Function 4.1.2 Properties
4.1.2 Properties
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 5 / 74
4.1 Joint Cumulative Distribution Function 4.1.2 Properties
4.1.2 Properties
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 5 / 74
4.1 Joint Cumulative Distribution Function 4.1.2 Properties
4.1.2 Properties
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 5 / 74
4.1 Joint Cumulative Distribution Function 4.1.2 Properties
4.1.2 Properties
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 5 / 74
4.2 Joint Probability Mass Function 4.2.1 Definitions
4.2.1 Definitions
Note
Corresponding to SX , the range of a single discrete random variable, we use the
notation SX,Y to denote the set of possible values of the pair (X, Y ). That is,
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 6 / 74
4.2 Joint Probability Mass Function 4.2.1 Definitions
4.2.1 Definitions
Note
Corresponding to SX , the range of a single discrete random variable, we use the
notation SX,Y to denote the set of possible values of the pair (X, Y ). That is,
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 6 / 74
4.2 Joint Probability Mass Function 4.2.1 Definitions
4.2.1 Definitions
Note
Corresponding to SX , the range of a single discrete random variable, we use the
notation SX,Y to denote the set of possible values of the pair (X, Y ). That is,
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 6 / 74
4.2 Joint Probability Mass Function 4.2.1 Definitions
4.2.1 Definitions
Note
Corresponding to SX , the range of a single discrete random variable, we use the
notation SX,Y to denote the set of possible values of the pair (X, Y ). That is,
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 6 / 74
4.2 Joint Probability Mass Function 4.2.1 Definitions
4.2.1 Definitions
where
pij = P [X = xi , Y = yj ], i = 1, . . . , m, j = 1, . . . , n,
n
X m
X
P [X = xi ] = pij , i = 1, . . . , m, P [Y = yj ] = pij , j = 1, . . . , n.
j=1 i=1
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 7 / 74
4.2 Joint Probability Mass Function 4.2.1 Definitions
4.2.1 Definitions
where
pij = P [X = xi , Y = yj ], i = 1, . . . , m, j = 1, . . . , n,
n
X m
X
P [X = xi ] = pij , i = 1, . . . , m, P [Y = yj ] = pij , j = 1, . . . , n.
j=1 i=1
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 7 / 74
4.2 Joint Probability Mass Function 4.2.1 Definitions
4.2.1 Definitions
Theorem 4.2
(a) 0 ≤ pij ≤ 1 for all i = 1, . . . , m, j = 1, . . . , n.
Pm Pn
(b) i=1 j=1 pij = 1.
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 8 / 74
4.2 Joint Probability Mass Function 4.2.1 Definitions
4.2.1 Definitions
Remark 4.3
From (4.1) and Definition 4.3, the joint cumulative distribution function of discrete
random variables X and Y is
X X
FXY (x, y) = pij (4.5)
xi <x yj <y
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 9 / 74
4.2 Joint Probability Mass Function 4.2.1 Definitions
4.2.1 Definitions
Example 4.1
Test two integrated circuits one after the other. On each test, the possible outcomes are
a (accept) and r (reject). Assume that all circuits are acceptable with probability 0.9
and that the outcomes of successive tests are independent. Count the number of
acceptable circuits X and count the number of successful tests Y before you observe the
first reject. (If both tests are successful, let Y = 2.)
(a) Find the joint PMF of X and Y .
(b) Find the joint PDT of X and Y .
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 10 / 74
4.2 Joint Probability Mass Function 4.2.1 Definitions
4.2.1 Definitions
We compute
Each outcome specifies a pair of values X and Y . Let g(s) be the function that
transforms each outcome s in the sample space S into the pair of random variables
(X, Y ). Then
g(aa) = (2, 2), g(ar) = (1, 1), g(ra) = (1, 0), g(rr) = (0, 0).
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 11 / 74
4.2 Joint Probability Mass Function 4.2.1 Definitions
4.2.1 Definitions
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 12 / 74
4.2 Joint Probability Mass Function 4.2.1 Definitions
4.2.1 Definitions
Note
Note that all of the probabilities add up to 1. This reflects the second axiom of
probability that states P [S] = 1. Using the notation of random variables, we write this as
X X
PX,Y (x, y) = 1. (4.6)
x∈SX y∈SY
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 13 / 74
4.2 Joint Probability Mass Function 4.2.1 Definitions
4.2.1 Definitions
Note
Note that all of the probabilities add up to 1. This reflects the second axiom of
probability that states P [S] = 1. Using the notation of random variables, we write this as
X X
PX,Y (x, y) = 1. (4.6)
x∈SX y∈SY
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 13 / 74
4.2 Joint Probability Mass Function 4.2.2 Properties
4.2.2 Properties
Note
We represent an event B as a region in the X, Y plane. Figure 4.2 shows two examples
of events.
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 14 / 74
4.2 Joint Probability Mass Function 4.2.2 Properties
4.2.2 Properties
Note
We represent an event B as a region in the X, Y plane. Figure 4.2 shows two examples
of events.
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 14 / 74
4.2 Joint Probability Mass Function 4.2.2 Properties
4.2.2 Properties
Theorem 4.3
For discrete random variables X and Y and any set B in the X, Y plane, the probability
of the event {(X, Y ) ∈ B} is
X
P [B] = PX,Y (x, y). (4.7)
(x,y)∈B
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 15 / 74
4.2 Joint Probability Mass Function 4.2.2 Properties
4.2.2 Properties
Example 4.2
Continuing Example 4.1, find the probability of the event B that X, the number of
acceptable circuits, equals Y , the number of tests before observing the first failure.
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 16 / 74
4.2 Joint Probability Mass Function 4.2.2 Properties
4.2.2 Properties
Therefore,
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 17 / 74
4.2 Joint Probability Mass Function 4.2.3 Marginal PMF
Theorem 4.4
For discrete random variables X and Y with joint PMF PX,Y (x, y),
X X
PX (x) = PX,Y (x, y), PY (y) = PX,Y (x, y). (4.8)
y∈SY x∈SX
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 18 / 74
4.2 Joint Probability Mass Function 4.2.3 Marginal PMF
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 19 / 74
4.2 Joint Probability Mass Function 4.2.3 Marginal PMF
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 19 / 74
4.2 Joint Probability Mass Function 4.2.3 Marginal PMF
Example 4.3
In Example 4.1, we found the joint PMF of X and Y to be
(a) Find the marginal PMFs for the random variables X and Y .
(b) Find the marginal PDTs for the random variables X and Y .
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 20 / 74
4.2 Joint Probability Mass Function 4.2.3 Marginal PMF
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 21 / 74
4.2 Joint Probability Mass Function 4.2.3 Marginal PMF
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 22 / 74
4.2 Joint Probability Mass Function 4.2.3 Marginal PMF
0.01, x = 0,
0.1, y = 0,
0.18,
x = 1, 0.09, y = 1,
PX (x) = PY (y) =
0.81, x = 2,
0.81, y = 2,
0, otherwise. 0, otherwise.
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 23 / 74
4.3 Joint Probability Density Function 4.3.1 Definitions
4.3.1 Definitions
Theorem 4.5
∂ 2 FX,Y (x, y)
fX,Y (x, y) = . (4.9)
∂x∂y
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 24 / 74
4.3 Joint Probability Density Function 4.3.1 Definitions
4.3.1 Definitions
Theorem 4.5
∂ 2 FX,Y (x, y)
fX,Y (x, y) = . (4.9)
∂x∂y
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 24 / 74
4.3 Joint Probability Density Function 4.3.2 Properties
4.3.2 Properties
Theorem 4.7
A joint PDF fX,Y (x, y) has the following properties corresponding to first and second
axioms of probability:
(a) fX,Y (x, y) ≥ 0 for all (x, y) ∈ R2 ,
Z +∞ Z +∞
(b) fX,Y (x, y)dxdy = 1.
−∞ −∞
Theorem 4.8
The probability that the continuous random variables (X, Y ) are in A is
ZZ
P [A] = fX,Y (x, y)dxdy. (4.10)
A
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 25 / 74
4.3 Joint Probability Density Function 4.3.2 Properties
4.3.2 Properties
Theorem 4.7
A joint PDF fX,Y (x, y) has the following properties corresponding to first and second
axioms of probability:
(a) fX,Y (x, y) ≥ 0 for all (x, y) ∈ R2 ,
Z +∞ Z +∞
(b) fX,Y (x, y)dxdy = 1.
−∞ −∞
Theorem 4.8
The probability that the continuous random variables (X, Y ) are in A is
ZZ
P [A] = fX,Y (x, y)dxdy. (4.10)
A
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 25 / 74
4.3 Joint Probability Density Function 4.3.2 Properties
4.3.2 Properties
Example 4.4
Random variables X and Y have joint PDF
(
c, 0 ≤ x ≤ 5, 0 ≤ y ≤ 3
fX,Y (x, y) =
0, otherwise.
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 26 / 74
4.3 Joint Probability Density Function 4.3.2 Properties
4.3.2 Properties
Therefore, c = 1/15.
The small dark rectangle in the diagram is the event
A = {2 ≤ X < 3, 1 ≤ Y < 3}. P [A] is the integral of the PDF over this
rectangle, which is
Z3 Z3
1
P [A] = dvdu = 2/15.
15
2 1
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 27 / 74
4.3 Joint Probability Density Function 4.3.2 Properties
4.3.2 Properties
Therefore, c = 1/15.
The small dark rectangle in the diagram is the event
A = {2 ≤ X < 3, 1 ≤ Y < 3}. P [A] is the integral of the PDF over this
rectangle, which is
Z3 Z3
1
P [A] = dvdu = 2/15.
15
2 1
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 27 / 74
4.3 Joint Probability Density Function 4.3.3 Marginal PDF
Theorem 4.9
If X and Y are random variables with joint PDF fX,Y (x, y),
+∞
Z +∞
Z
fX (x) = fX,Y (x, y)dy, fY (y) = fX,Y (x, y)dx. (4.11)
−∞ −∞
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 28 / 74
4.3 Joint Probability Density Function 4.3.3 Marginal PDF
−1 O 1 x
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 29 / 74
4.3 Joint Probability Density Function 4.3.3 Marginal PDF
5(1 − x4 )
, −1 ≤ x ≤ 1,
fX (x) = 8
0, otherwise.
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 30 / 74
4.3 Joint Probability Density Function 4.3.3 Marginal PDF
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 31 / 74
4.3 Joint Probability Density Function 4.3.3 Marginal PDF
O
1 x
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 32 / 74
4.3 Joint Probability Density Function 4.3.3 Marginal PDF
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 33 / 74
4.3 Joint Probability Density Function 4.3.3 Marginal PDF
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 34 / 74
4.3 Joint Probability Density Function 4.3.3 Marginal PDF
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 34 / 74
4.4 Expected Values 4.4.1 Expected Values
Theorem 4.10
For random variables X and Y , the expected value of W = g(X, Y ) is
X X
Discrete: E[W ] = g(x, y)PX,Y (x, y),
x∈SX y∈SY
XX
or E[W ] = g(xi , yj )P [X = xi , Y = yj ],
i j
Z∞ Z∞
Continuous: E[W ] = g(x, y)fX,Y (x, y)dxdy.
−∞ −∞
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 35 / 74
4.4 Expected Values 4.4.1 Expected Values
Theorem 4.10
For random variables X and Y , the expected value of W = g(X, Y ) is
X X
Discrete: E[W ] = g(x, y)PX,Y (x, y),
x∈SX y∈SY
XX
or E[W ] = g(xi , yj )P [X = xi , Y = yj ],
i j
Z∞ Z∞
Continuous: E[W ] = g(x, y)fX,Y (x, y)dxdy.
−∞ −∞
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 35 / 74
4.4 Expected Values 4.4.1 Expected Values
Theorem 4.10
For random variables X and Y , the expected value of W = g(X, Y ) is
X X
Discrete: E[W ] = g(x, y)PX,Y (x, y),
x∈SX y∈SY
XX
or E[W ] = g(xi , yj )P [X = xi , Y = yj ],
i j
Z∞ Z∞
Continuous: E[W ] = g(x, y)fX,Y (x, y)dxdy.
−∞ −∞
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 35 / 74
4.4 Expected Values 4.4.1 Expected Values
Theorem 4.11
Theorem 4.12
For any two random variables X and Y ,
Theorem 4.13
The variance of the sum of two random variables is
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 36 / 74
4.4 Expected Values 4.4.1 Expected Values
Theorem 4.11
Theorem 4.12
For any two random variables X and Y ,
Theorem 4.13
The variance of the sum of two random variables is
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 36 / 74
4.4 Expected Values 4.4.1 Expected Values
Theorem 4.11
Theorem 4.12
For any two random variables X and Y ,
Theorem 4.13
The variance of the sum of two random variables is
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 36 / 74
4.4 Expected Values 4.4.2 Covariance
(a) Covariance
Remark 4.6
From the properites of the expected value,
where E[XY ] is
P P
xi yj pij , (Discrete Random Variables)
i j
+∞ +∞
E[XY ] = Z Z
xyf (x, y)dxdy, (Continuous Random Variables).
−∞ −∞
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 37 / 74
4.4 Expected Values 4.4.2 Covariance
(a) Covariance
Remark 4.6
From the properites of the expected value,
where E[XY ] is
P P
xi yj pij , (Discrete Random Variables)
i j
+∞ +∞
E[XY ] = Z Z
xyf (x, y)dxdy, (Continuous Random Variables).
−∞ −∞
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 37 / 74
4.4 Expected Values 4.4.2 Covariance
Properties
Theorem 4.14
(a) Cov(X, Y ) = E[XY ] − E[X].E[Y ] = rX,Y − µX µY .
(b) V ar[X + Y ] = V ar[X] + V ar[Y ] + 2Cov[X, Y ].
(c) V ar[X] = Cov[X, X], V ar[Y ] = Cov[Y, Y ].
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 38 / 74
4.4 Expected Values 4.4.2 Covariance
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 39 / 74
4.4 Expected Values 4.4.2 Covariance
(c) Correlation
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 40 / 74
4.4 Expected Values 4.4.2 Covariance
Examples
Example 4.7
For the integrated circuits tests in Example 4.1, we found in Example 4.3 that the
probability model for X and Y is given by the following matrix.
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 41 / 74
4.4 Expected Values 4.4.2 Covariance
Examples
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 42 / 74
4.4 Expected Values 4.4.2 Covariance
Examples
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 42 / 74
4.4 Expected Values 4.4.2 Covariance
Examples
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 42 / 74
4.4 Expected Values 4.4.2 Covariance
Examples
Example 4.8
The joint PDT of X and Y is
X Y −1 0 1
−1 4/15 1/15 4/15
1 0 2/15 0
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 43 / 74
4.4 Expected Values 4.4.2 Covariance
Examples
X -1 0 1 Y -1 0 1
P 9/15 4/15 5/15 P 5/15 5/15 5/15
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 44 / 74
4.4 Expected Values 4.4.2 Covariance
Examples
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 45 / 74
4.4 Expected Values 4.4.2 Covariance
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 46 / 74
4.4 Expected Values 4.4.2 Covariance
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 46 / 74
4.4 Expected Values 4.4.3 Correlation Coefficient
Theorem 4.17
−1 ≤ ρX,Y ≤ 1.
Theorem 4.18
If X and Y are random variables such that Y = aX + b
−1,
a < 0,
ρX,Y = 0, a = 0,
1, a > 0.
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 47 / 74
4.4 Expected Values 4.4.3 Correlation Coefficient
Theorem 4.17
−1 ≤ ρX,Y ≤ 1.
Theorem 4.18
If X and Y are random variables such that Y = aX + b
−1,
a < 0,
ρX,Y = 0, a = 0,
1, a > 0.
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 47 / 74
4.4 Expected Values 4.4.3 Correlation Coefficient
Theorem 4.17
−1 ≤ ρX,Y ≤ 1.
Theorem 4.18
If X and Y are random variables such that Y = aX + b
−1,
a < 0,
ρX,Y = 0, a = 0,
1, a > 0.
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 47 / 74
4.5 Conditioning by an Event 4.5.1 Conditional Joint PMF
Theorem 4.19
For any event B, a region of the X, Y plane with P [B] > 0,
PX,Y (x, y) , (x, y) ∈ B,
PX,Y |B (x, y) = P [B] (4.16)
0, otherwise.
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 48 / 74
4.5 Conditioning by an Event 4.5.1 Conditional Joint PMF
Theorem 4.19
For any event B, a region of the X, Y plane with P [B] > 0,
PX,Y (x, y) , (x, y) ∈ B,
PX,Y |B (x, y) = P [B] (4.16)
0, otherwise.
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 48 / 74
4.5 Conditioning by an Event 4.5.2 Conditional Joint PDF
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 49 / 74
4.5 Conditioning by an Event 4.5.2 Conditional Joint PDF
Example 4.9
X and Y are random variables with joint PDF
1, 0 ≤ x ≤ 5, 0 ≤ y ≤ 3,
fX,Y (x, y) = 15
0, otherwise.
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 50 / 74
4.5 Conditioning by an Event 4.5.2 Conditional Joint PDF
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 51 / 74
4.5 Conditioning by an Event 4.5.3 Conditional Expected Value
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 52 / 74
4.5 Conditioning by an Event 4.5.3 Conditional Expected Value
Example 4.10
Continuing Example 4.9, find the conditional expected value of W = XY given the
event B = {X + Y ≥ 4}.
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 53 / 74
4.5 Conditioning by an Event 4.5.3 Conditional Expected Value
Example 4.10
Continuing Example 4.9, find the conditional expected value of W = XY given the
event B = {X + Y ≥ 4}.
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 53 / 74
4.5 Conditioning by an Event 4.5.4 Conditional Variance
Theorem 4.21
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 54 / 74
4.5 Conditioning by an Event 4.5.4 Conditional Variance
Theorem 4.21
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 54 / 74
4.6 Conditioning by a Random Variable 4.6.1 Conditional PMF
Theorem 4.22
For random variables X and Y with joint PMF PX,Y (x, y), and x and y such that
PX (x) > 0 and PY (y) > 0,
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 55 / 74
4.6 Conditioning by a Random Variable 4.6.1 Conditional PMF
Theorem 4.22
For random variables X and Y with joint PMF PX,Y (x, y), and x and y such that
PX (x) > 0 and PY (y) > 0,
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 55 / 74
4.6 Conditioning by a Random Variable 4.6.2 Conditional Expected Value of a Function
Note
The conditional expected value of X given Y = y is a special case of Theorem 4.23:
X
E[X|Y = y] = xPX|Y (x|y).
x∈SX
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 56 / 74
4.6 Conditioning by a Random Variable 4.6.2 Conditional Expected Value of a Function
Note
The conditional expected value of X given Y = y is a special case of Theorem 4.23:
X
E[X|Y = y] = xPX|Y (x|y).
x∈SX
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 56 / 74
4.6 Conditioning by a Random Variable 4.6.3 Conditional PDF
fX,Y (x, y)
fX|Y (x|y) = . (4.19)
fY (y)
Note
Definition 4.13 implies
fX,Y (x, y)
fY |X (y|x) = . (4.20)
fX (x)
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 57 / 74
4.6 Conditioning by a Random Variable 4.6.3 Conditional PDF
fX,Y (x, y)
fX|Y (x|y) = . (4.19)
fY (y)
Note
Definition 4.13 implies
fX,Y (x, y)
fY |X (y|x) = . (4.20)
fX (x)
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 57 / 74
4.6 Conditioning by a Random Variable 4.6.3 Conditional PDF
Example 4.11
Random variables X and Y have joint PDF
(
2, 0 < y < x < 1,
fX,Y (x, y) =
0, otherwise.
For 0 < x < 1, find the conditional PDF fY |X (y|x). For 0 < y < 1, find the conditional
PDF fX|Y (x|y).
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 58 / 74
4.6 Conditioning by a Random Variable 4.6.3 Conditional PDF
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 59 / 74
4.6 Conditioning by a Random Variable 4.6.3 Conditional PDF
Furthermore,
(
fX,Y (x, y) 1/(1 − y), y < x < 1,
fX|Y (x|y) = =
fY (y) 0, otherwise.
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 60 / 74
4.6 Conditioning by a Random Variable 4.6.3 Conditional PDF
Theorem 4.24
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 61 / 74
4.6 Conditioning by a Random Variable 4.6.4 Conditional Expected Value of a Function
Note
The conditional expected value of X given Y = y is a special case of Definition 4.14:
+∞
Z
E[X|Y = y] = xfX|Y (x|y)dx.
−∞
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 62 / 74
4.6 Conditioning by a Random Variable 4.6.5 Conditional Expected Value
Example 4.12
For random variables X and Y in Example 4.19, we found in that the conditional PDF
of X given Y is
(
fX,Y (x, y) 1/(1 − y), y < x < 1,
fX|Y (x|y) = =
fY (y) 0, otherwise.
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 63 / 74
4.6 Conditioning by a Random Variable 4.6.5 Conditional Expected Value
Example 4.12
For random variables X and Y in Example 4.19, we found in that the conditional PDF
of X given Y is
(
fX,Y (x, y) 1/(1 − y), y < x < 1,
fX|Y (x|y) = =
fY (y) 0, otherwise.
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 63 / 74
4.6 Conditioning by a Random Variable 4.6.5 Conditional Expected Value
Z1
1 x2 x=1 1+y
= xdx = = .
1−y 2(1 − y) x=y 2
y
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 64 / 74
4.7 Independent Random Variables 4.7.1 Definitions
4.9.1 Definitions
Note
Theorem 4.22 implies that if X and Y are independent discrete random variables, then
Theorem 4.24 implies that if X and Y are independent continuous random variables,
then
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 65 / 74
4.7 Independent Random Variables 4.7.1 Definitions
4.9.1 Definitions
Note
Theorem 4.22 implies that if X and Y are independent discrete random variables, then
Theorem 4.24 implies that if X and Y are independent continuous random variables,
then
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 65 / 74
4.7 Independent Random Variables 4.7.1 Definitions
4.7.1 Definitions
Example 4.13
(
4xy, 0 ≤ x ≤ 1, 0 ≤ y ≤ 1,
fX,Y (x, y) =
0, otherwise.
Are X and Y independent?
It is easily verified that fX,Y (x, y) = fX (x)fY (y) for all pairs (x, y) and so we conclude
that X and Y are independent.
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 66 / 74
4.7 Independent Random Variables 4.7.1 Definitions
4.7.1 Definitions
Example 4.13
(
4xy, 0 ≤ x ≤ 1, 0 ≤ y ≤ 1,
fX,Y (x, y) =
0, otherwise.
Are X and Y independent?
It is easily verified that fX,Y (x, y) = fX (x)fY (y) for all pairs (x, y) and so we conclude
that X and Y are independent.
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 66 / 74
4.7 Independent Random Variables 4.7.2 Properties
4.9.2 Properties
Theorem 4.27
For independent random variables X and Y ,
(a) E[g(X)h(Y )] = E[g(X)]E[h(Y )],
(b) rX,Y = E[XY ] = E[X]E[Y ],
(c) Cov[X, Y ] = ρX,Y = 0,
(d) V ar[X + Y ] = V ar[X] + V ar[Y ],
(e) E[X|Y = y] = E[X] for all y ∈ SY ,
(f) E[Y |X = x] = E[Y ] for all x ∈ SX .
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 67 / 74
4.7 Independent Random Variables 4.7.2 Properties
4.7.2 Properties
Example 4.14
Random variables X and Y have a joint PMF given by the following matrix
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 68 / 74
4.7 Independent Random Variables 4.7.2 Properties
4.9.2 Properties
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 69 / 74
4.7 Independent Random Variables 4.7.2 Properties
Practice Test
Question 4.1
A code word contains 5 digits, each either 0 or 1: to be valid the word must contain
exactly three 1’s and two 0’s. One word is selected at random from the valid code words.
Deflne X to be the flrst (left most digit) and let Y be the second digit in the word
selected.
(a) Define the joint PMF and PDT for (X, Y ).
(b) Find the marginal probability of X and Y .
(c) Are X and Y independent?
(d) Find E[X], E[Y ], V ar[X], V ar[Y ].
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 70 / 74
4.7 Independent Random Variables 4.7.2 Properties
Practice Test
Question 4.2
A certain drugstore has three public telephone booths. The probability that the booth is
occupied at a given time is identical for each booth, and is denoted by p, which is equal
to 0.2. Let X and Y denote the number of booths that will be occupied at two
independent time.
(a) Define the joint PMF and PDT for (X, Y ).
(b) Find P [X = Y ].
(c) Find P [X > Y ].
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 71 / 74
4.7 Independent Random Variables 4.7.2 Properties
Practice Test
Question 4.3
Suppose that in a certain drug, the concentration of a particular chemical is a random
variable with a continuous distribution for which the PDF g is as follows
3 x2 , 0 ≤ x ≤ 2,
g(x) = 8
0, otherwise.
Suppose the concentrations X and Y of the chemical in two seperate batches of the
drug are independent random variables for each of the PDF is g. Determine
(a) The joint PDF of X and Y .
(b) Find P [X > Y ].
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 72 / 74
4.7 Independent Random Variables 4.7.2 Properties
Practice Test
Question 4.4
Suppose that 2 persons make an appointment to meet between 5pm and 6 pm at a
certain location, and they agree that neither person will wait more than 10 minutes for
the other person. If they arrive indepently at random times between 5pm and 6 pm,
what is the probability that they meet?
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 73 / 74
4.7 Independent Random Variables 4.7.2 Properties
Practice Test
Question 4.5
Suppose that a person’s score X on a mathematics aptitude test is a number between 0
and 1, and that his score Y on a music aptitude test is a number between 0 and 1.
Suppose further that in the population of a college students in the United States, the
scores X and Y are distributed according to the following joint PDF
(
k(2x + 3y), 0 < x < 1, 0 < y < 1,
fX,Y (x, y) =
0, otherwise.
(a) Find k?
(b) What proportion of a college students obtain a score greater than 0.8 on the
mathematics test?
(c) If a student’s score on the music test is 0.3, what is the probability that his score
on the mathametics test will be greater than 0.8?
(d) If a student’s score on the mathematics test is 0.3, what is the probability that his
score on the music test will be greater than 0.8?
Nguyễn Thị Thu Thủy (SAMI-HUST) Pairs of Random Variables HANOI – 2019 74 / 74