0% found this document useful (0 votes)
26 views9 pages

W2GS

Uploaded by

Sara
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
26 views9 pages

W2GS

Uploaded by

Sara
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 9

Statistics for Data Science - 2

Week 2 Graded Assignment


Multiple random variables

1. Let X and Y be two independent discrete random variables with CDFs FX and FY ,
respectively. Define another random variable Z = min(X, Y ), then the CDF of Z is

a) min(FX , FY )
b) FX FY
c) FX + FY + FX FY
d) FX + FY − FX FY

Solution:

FZ (z) = P (Z ≤ z) = P (min(X, Y ) ≤ z)
= 1 − P (min(X, Y ) > z)
= 1 − P (X > z, Y > z)

Since X and Y are two independent discrete random variables,


P (X > z, Y > z) = P (X > z)P (Y > z)

FZ (z) = 1 − P (X > z)P (Y > z)


= 1 − [(1 − P (X ≤ z))(1 − P (Y ≤ z))]
= 1 − [(1 − FX (z))(1 − FY (z))]
= FX (z) + FY (z) − FX (z)FY (z)

2. Let X and Y be two independent random variables with PMFs


(
1
for k = 1, 2, 3, 4, 5, 6.
fX (k) = fY (k) = 6
0 otherwise

Define Z = X − Y . Find the value of fZ (3).


4
a)
12
3
b)
12
5
c)
12
1
d)
12
Solution:

fZ (3) = P (Z = 3) = P (X − Y = 3)
= P (X = 4, Y = 1) + P (X = 5, Y = 2) + P (X = 6, Y = 3)

Given that X and Y are two independent random variables.


⇒ P (X = x, Y = y) = P (X = x)P (Y = y) for all (x, y).

fZ (3) = P (X = 4, Y = 1) + P (X = 5, Y = 2) + P (X = 6, Y = 3)
= P (X = 4)P (Y = 1) + P (X = 5)P (Y = 2) + P (X = 6)P (Y = 3)
1 1 1 1 1 1
= × + × + ×
6 6 6 6 6 6
3
=
36
1
=
12

3. Let X ∼ Geometric(p) and Y ∼ Geometric(p) be independent and let Z = X + Y .


Determine the values of p for which P (Z = 26) > P (Z = 25).

a) p > 0.02
b) p < 0.04
c) p > 0.15
d) p < 0.30
e) p = 0.05

Solution:
If X ∼ Geometric(p) and Y ∼ Geometric(p) are two independent random variables and
Z = X + Y , then

P (Z = n) = (n − 1)p2 (1 − p)n−2
(Try derivation yourself)
We have to find the value of p for which P (Z = 26) > P (Z = 25).
P (Z = 26) = (26 − 1)p2 (1 − p)26−2
and P (Z = 25) = (25 − 1)p2 (1 − p)25−2

Comparing both, we will get


25p2 (1 − p)24 > 24p2 (1 − p)23

Page 2
⇒ 25(1 − p) > 24
⇒ 1 − p > 24
25
⇒ p < 0.04

4. The following options gives the joint PMF of the random variables X and Y . If the
random variables X and Y are independent, then which of the following option(s) can
be the joint PMF of X and Y ?

Y
0 1 2
X

0 0.01 0 0

1 0.09 0.09 0

2 0 0 0.81

a)

Y
0 1 2
X

0 0.06 0.18 0.12

1 0.04 0.12 0.48

b)

Y
0 1 2
X
1 1 1
0
12 24 24
1 1 1
1
6 12 8
1 1 1
2
4 8 12

c)

Page 3
Y
0 1 2
X
1 1 1
0
10 5 5
1 1 3
1
10 10 10

d)

Y
0 1
X

0 0.10 0.15

1 0.20 0.30

2 0.10 0.15

e)

Answer: e

Solution:
In option a)
P (X = 0, Y = 1) = 0 but P (X = 0) = 0.01+0+0 = 0.01 and P (Y = 1) = 0+0.09+0 =
0.09
⇒ P (X = 0, Y = 1) 6= P (X = 0)P (Y = 1)
Therefore, option (a) cannot be the joint PMF of X and Y.

In option b)
P (X = 0, Y = 0) = 0.06 but P (X = 0) = 0.06 + 0.18 + 0.12 = 0.36 and P (Y = 0) =
0.06 + 0.04 = 0.10
⇒ P (X = 0, Y = 0) = 0.06 6= 0.036 = P (X = 0)P (Y = 0)
Therefore, option (b) cannot be the joint PMF of X and Y.

In option c)
P (X = 1, Y = 0) = 1/6 but P (X = 1) = 1/6 + 1/12 + 1/8 = 3/8 and P (Y = 0) =
1/12 + 1/6 + 1/4 = 1/2
⇒ P (X = 1, Y = 0) = 1/6 6= 3/16 = P (X = 1)P (Y = 0)
Therefore, option (c) cannot be the joint PMF of X and Y.

Page 4
In option d)
P (X = 0, Y = 1) = 1/5 but P (X = 0) = 1/10 + 1/5 + 1/5 = 1/2 and P (Y = 1) =
1/5 + 1/10 = 3/10
⇒ P (X = 0, Y = 1) = 1/5 6= 3/20 = P (X = 0)P (Y = 1)
Therefore, option (d) cannot be the joint PMF of X and Y.

In option e)
For every (x, y), P (X = x, Y = y) = P (X = x)P (Y = y) (check yourself)
Hence option (e) is the joint PMF of X and Y.

5. Let X and Y be two independent random variables such that X ∼ Bernoulli(0.2) and
Y ∼ Bernoulli(0.4). Let another random variable Z be defined as Z = X + Y . Find
the value of fX|Z=1 (1). Enter the answer correct to two decimal places.
Answer: [0.25, 0.29]

Solution:
X ∼ Bernoulli(0.2)
Y ∼ Bernoulli(0.4)
Z =X +Y

P (X = 1, Z = 1)
fX|Z=1 (1) =
P (Z = 1)
P (X = 1, Y = 0)
=
P (X = 1, Y = 0) + P (X = 0, Y = 1)
P (X = 1)P (Y = 0)
=
P (X = 1)P (Y = 0) + P (X = 0)P (Y = 1)
0.2 × 0.6
=
(0.2 × 0.6) + (0.8 × 0.4)
=0.28

6. Let X1 , X2 and X3 be three independent and identically distributed Poisson random


variables with λi = 3 for all i. Find the probability that exactly one of the Xi equals 0
and exactly one of the Xi equals 1?

(a) 18e−6 (1 − 4e−3 )


(b) 9e−6 (1 − 4e−3 )
(c) 3e−6 (1 − 4e−3 )
(d) 12e−6 (1 − 4e−3 )

Page 5
Solution:
First we will find the probability such that X1 = 0, X2 = 1 and X3 do not take values 0
and 1.
Since all the four random variable are independent, we have
P (X1 = 0, X2 = 1, X3 6= {0, 1}) = P (X1 = 0)P (X2 = 1)P (X3 6= {0, 1})
Now, P (X1 = 0) = e−3 , P (X1 = 1) = 3e−3
P (X3 6= {0, 1}) = 1 − P (X3 = {0, 1})
= 1 − [P (X3 = 0) + P (X3 = 1)]
= 1 − 4e−3
Now, P (X1 = 0, X2 = 1, X3 6= {0, 1}) = e−3 3e−3 (1 − 4e−3 ) = 3e−6 (1 − 4e−3 )
We can choose such pairs of Xi in 3! ways.
Therefore, probability that exactlyXi equals 0 and exactly one Xi equals 1 is given by
6 × 3e−6 (1 − 4e−3 ) = 18e−6 (1 − 4e−3 ) ways.
7. Let X ∼ Bernoulli(0.3) and Y ∼ Bernoulli(0.5) be independent. Define Z = X+Y −XY ,
find the distribution of Z.
(a) Z ∼ Bernoulli(0.35)
(b) Z ∼ Bernoulli(0.65)
(c) Z ∼ Bernoulli(0.15)
(d) Z ∼ Bernoulli(0.85)
Solution:
Given X ∼ Bernoulli(0.3) and Y ∼ Bernoulli(0.5) are independent.
Z = X + Y − XY
Since X ∼ Bernoulli(0.3), it will take the values in {0, 1}.
Similarly Y will take values in {0, 1}.
Also X and Y are given to be independent, therefore fXY (x, y) = fX (x)fY (y) for all
(x, y).
Consider the following joint distribution table of X and Y .

X Y X + Y − XY fXY (x, y)
1 1 1 (0.3)(0.5) = 0.15
1 0 1 (0.3)(0.5) = 0.15
0 1 1 (0.7)(0.5) = 0.35
0 0 0 (0.7)(0.5) = 0.35

The range of Z is {0, 1}.


P (Z = 0) = 0.35, P (Z = 1) = 0.65
Therefore, Z ∼ Bernoulli(0.65).

Page 6
8. Let X and Y be independent and identically distributed Geometric random variables
with parameter 0.6.

(a) Find P (X = 2 | X + Y = 11). Enter the answer correct to one decimal place.
Answer: 0.1

Solution:
Given X, Y ∼ i.i.d. Geometric(0.6).

P (X = 2, X + Y = 11)
P (X = 2 | X + Y = 11) =
P (X + Y = 11)
P (X = 2)P (Y = 9)
= 10
P
P (X = i, Y = 11 − i)
i=1
(0.4)(0.6) × (0.4)8 (0.6)
= 10
P
P (X = i)P (Y = 11 − i)
i=1
(0.4)9 (0.6)2
= = 0.1
10(0.4)9 (0.6)2

(b) Find P (X = 7 | X + Y = 11). Enter the answer correct to one decimal place.
Answer: 0.1

Solution:
This can also be solved using the above steps.
1
Remark: For any i, P (X = i | X + Y = n) = , for i : 1 → n − 1.
n−1
9. The joint distribution of X and Y is given by
9
fXY (x, y) = ,
16 × 4x+y
where TX , TY ∈ {0, 1, 2, . . .}.

(i) Find the probability mass function of X + Y .


9
(a) k
16 · 4k
9
(b) (k + 1)
16 · 4k
9
(c) (k + 1)
16 · 4k+1
9
(d) k
16 · 4k+1

Page 7
Solution:
X, Y is in the range {0, 1, 2, . . .}.
The range of X + Y is {0, 1, 2, . . .}.

X +Y fX+Y (k)
9
0
16
9
1 2
16 × 4
9
2 3
16 × 42
.. ..
. .
9
k (k + 1)
16 · 4k

9
Therefore, P (X + Y = k) = (k + 1)
16 · 4k
(ii) Find the probability mass function of Z = max{X, Y }.
3(4k − 1)
(a) fZ (k) = for k = 1, 2, . . .
2 · 42k
3(4k − 1)
(b) fZ (k) = for k = 0, 1, . . .
2 · 42k
9 3(4k − 1)
(c) fZ (k) = + for k = 0, 1, . . .
16 · 42k 2 · 42k
9 3(4k − 1)
(d) fZ (k) = + for k = 1, 2, . . .
16 · 42k 2 · 42k
Solution:
The joint distribution of X and Y is given by
9
fXY (x, y) =
16 × 4x+y

Let Z = max{X, Y }.
Clearly, range of Z will be TZ = {0, 1, 2, . . .}.

Now, choose k ∈ TZ . Then

Page 8
Z fZ (k)
9
0
16
9 9
1 2 +
16 · 4 16 · 42
9 9 9
2 2 + 2 +
16 · 42 16 · 43 16 · 44
.. ..
.  . 
9 1 1 1 9
k 2 k
1 + + 2 + . . . + (k−1) +
16 · 4 4 4 4 16 · 42k

Now,
 
9 1 1 1 9
fZ (k) =2 1 + + 2 + . . . + (k−1) +
16 · 4k 4 4 4 16 · 42k
  k 
1
1−
9   4  9
=2 +

k
16 · 4 
 1  16 · 42k

1−
4
9 3(4k − 1)
= +
16 · 42k 2 · 42k
9 3(4k − 1)
Therefore, fZ (k) = + for k = 0, 1, . . .
16 · 42k 2 · 42k
10. Let the random variables X and Y , which represent the number of calls received by call
centers A and B, respectively, in a one-hour interval follow the Poisson distribution. The
average number of calls received in call centers A and B is 2 per hour and 3 per hour,
respectively. Assume that X and Y are independent. If Z denotes the total number of
calls received in call centers A and B, find the conditional probability fY |Z=5 (3). Enter
the answer correct to two decimal places.
Answer: [0.33, 0.36]

Solution:
Given, X and Y denote the number of calls received by call center A and B in a one-hour
interval.
Also, X ∼ Poisson(2) and Y ∼ Poisson(3) are independent.

Z = X + Y represents the total calls received in a one-hour interval.


 
3
Now, Y | Z = 5 ∼ Binomial 5,
2+3
 3  2
3 2
Therefore, fY |Z=5 (3) = 5C 3 = 0.35
5 5

Page 9

You might also like