Joint probability mass function
If the random variables are discrete, then the joint probability mass
function consists of probability values P(X = i , Y = j ) = Pi j satisfying
1 ) 0 ≤ Pi j≤1
2) ∑∑ Pi j = 1
Marginal Probability Distributions: Even though two random variables
X and Y may be jointly distributed, if interest is focused on only one of
the random variables, then it is appropriate to consider the probability
distribution of that random variable alone. This is known as the marginal
distribution of the random variable and can be obtained quite simply by
summing the joint probability distribution over the values of the other
random variable.
For example, for two discrete random variables X and Y, the probability
values of the marginal distribution of X are
P(X = i ) = ∑𝑗 𝑃𝑖𝑗
i =1,2,3,4 and j =1,2,3
P(X=i) = ∑3𝑗=1 𝑃𝑖𝑗 = Pi1 + Pi2 + Pi3
P(X=1) = ∑3𝑗=1 𝑃1𝑗 = P11 + P12 + P13
Conditional Probability Distributions : If two random variables X and
Y are jointly distributed, then it is sometimes useful to consider the
distribution of one random variable conditional on the other random
variable having taken a particular value.
The conditional probability distribution of random variable X
conditional on the event Y = j consists of the probability values
𝑃(𝑋,𝑌=𝑗)
P(X|Y=j) =
𝑃(𝑌=𝑗)
Covariance: Cov(X, Y ) = E(XY) − E(X)E(Y )
𝐶𝑜𝑣(𝑋,𝑌)
Correlation: Corr(X,Y) =
√𝑉(𝑋)𝑉(𝑌)
-1 to 1
Question: A company that services air conditioner units in residences.
If the random variable X, taking the values 1, 2, 3, and 4, is the service
time in hours taken at a particular location, and the random variable Y ,
taking the values 1, 2, and 3, is the number of air conditioner units at the
location, then these two random variables can be thought of as jointly
related.
Suppose that their joint probability mass function Pij is given in the
following Figure. The figure indicates, for example, that there is a
probability of 0.12 that X = 1 and Y = 1, so that there is a probability of
0.12 that a particular location chosen at random has one air conditioner
unit that takes a technician one hour to service. Similarly, there is a
probability of 0.07 that a location has three air conditioner units that take
four hours to service.
1) Show that this is a valid joint probability mass function
Solution: ∑𝟒𝒊=𝟏 ∑𝟑𝒋=𝟏 𝑷𝒊𝒋 = 0.12 + 0.08 + ・・・ + 0.07 = 1.00
2) Calculate the probability that a location has no more than two air
conditioner units that take no more than two hours to service.
i = 1,2 j = 1,2
Solution: P11 + P12 + P21 + P22 = 0.12 + 0.08 + 0.08 + 0.15 = 0.43
3) Find marginal probability mass function.
Solution: P(X = 1) = 0.12 + 0.08 + 0.01 = 0.21
P(X = 2) = 0.08 + 0.15 + 0.01 = 0.24
P(X = 3) = 0.07 + 0.21 + 0.02 = 0.3
P(X= 4) = 0.05 + 0.13+ 0.07 = 0.25
Similarly, you also need to calculate P(Y=1), P(Y=2) and P(Y=3)
4) Calculate the expected service time and the variance in the service
times
Solution: E(x) = ∑xp(x), E(x2) = ∑x2p(x),
The expected service time is E(X) = ∑4𝑖=1 𝑖𝑃(𝑋 = 𝑖)
=1P(X=1) + 2P(X=2) + 3P(X=3) + 4P(X=4)
= (1 . 0.21) + (2 . 0.24) + (3 . 0.30) + (4 . 0.25) = 2.59
We know, V(X) = E(X2) – (E(X))2
Since E(X2) = ∑4𝑖=1 𝑖 2 𝑃(𝑋 = 𝑖)
=1P(X=1) + 4P(X=2) + 9P(X=3) + 16P(X=4)
= (1 . 0.21) + (4 . 0.24) + (9 . 0.30) + (16 . 0.25) = 7.87
The variance in the service times is
Var(X) = E(X2) − (E(X))2 = 7.87 – (2.59)2 = 1.162
5) Calculate the expected number of units serviced and the variance
in the number of units serviced.
Solution: The expected number of units serviced E(Y) = ∑3𝑗=1 𝑗𝑃(𝑌 = 𝑗)
= 1P(Y=1) + 2P(Y=2) + 3P(Y=3)
= 1×0.32 + 2×0.57 + 3×0.11 = 1.79
We know, V(Y) = E(Y2) – (E(Y))2
Here, E(Y2) = ∑3𝑗=1 𝑗 2 𝑃(𝑌 = 𝑗)
= 1×0.32 + 4×0.57 + 9×0.11 = 3.59
The variance in the number of units serviced V(Y) = 3.59 – (1.79)2
= 0.3859
5) Suppose that a technician is visiting a location that is known to have
three air conditioner units, what is the conditional distribution of the
service time X.
Solution:
𝑃(𝑋,𝑌=𝑗)
We know, P(X|Y=j) =
𝑃(𝑌=𝑗)
𝑃(𝑋,𝑌=3)
⇒P(X|Y=3) =
𝑃(𝑌=3)
Here, P(Y = 3) = 0.01 + 0.01 + 0.02 + 0.07 = 0.11
P(X=1,Y=3) 0.01
P(X=1|Y=3) = = = 0.091
𝑃(𝑌=3) 0.11
P(X=2,Y=3) 0.01
P(X=2|Y=3) = = = 0.091
𝑃(𝑌=3) 0.11
P(X=3,Y=3) 0.02
P(X=3|Y=3) = = = 0.182
𝑃(𝑌=3) 0.11
P(X=4,Y=3) 0.07
P(X=4|Y=3) = = = 0.636
𝑃(𝑌=3) 0.11
6) Calculate the conditional expectation of the service time.
Solution:
E(X|Y = 3) = ∑4i=1 iP(X|Y = 3)
= (1 × 0.091) + (2 × 0.091) + (3 × 0.182) + (4 × 0.636) = 3.36
E(Y|X = 3) = ∑3j=1 jP(Y|X = 3)
7) Calculate the covariance and correlation.
Solution:
Cov(X,Y) = E(X,Y) – E(X)E(Y)
The expected service time is E(X) = 2.59 hours, and the expected number
of units serviced is E(Y ) = 1.79.
E(X,Y) = ∑4𝑖=1 ∑3𝑗=1 𝑖𝑗𝑃𝑖𝑗 = (1 × 1 × 0.12) + (1 × 2 × 0.08) + ··· + (4 × 3
× 0.07) = 4.86
Cov(X,Y) = 4.86 – 2.56 × 1.79 = 0.224
We know,
𝐶𝑜𝑣(𝑋,𝑌) 0.224
Corr(X,Y) = = = 0.34
√𝑉(𝑋)𝑉(𝑌) √1.162 × 0.384
