Probability Distribution

Download as pdf or txt
Download as pdf or txt
You are on page 1of 7

Problem 14.2. A fair die is tossed and its outcome is denoted by X, i.e.

,
X
_
1 2 3 4 5 6
1/6 1/6 1/6 1/6 1/6 1/6
_
.
www. statisticsassignmentexperts.com
email us at info@ statisticsassignmentexperts.com or call us at +1 520 8371215
After that, X independent fair coins are tossed and the number of heads obtained is denoted by
Y .
Compute:
1. P[Y = 4].
2. P[X = 5|Y = 4].
3. E[Y ].
4. E[XY ].
Solution:
1. For k = 1, . . . , 6, conditionally on X = k, Y has the binomial distribution with parameters
k and
1
2
. Therefore,
P[Y = i|X = k] =
_
_
k
i
_
2
k
, 0 i k
0, i > k,
and so, by the law of total probability.
P[Y = 4] =
6

k=1
P[Y = 4|X = k]P[X = k]
=
1
6
(2
4
+
_
5
4
_
2
5
+
_
6
4
_
2
6
)

=
29
384

.
(14.1)
2. By the (idea behind the) Bayes formula
P[X = 5|Y = 4] =
P[X = 5, Y = 4]
P[Y = 4]
=
P[Y = 4|X = 5]P[X = 5]
P[Y = 4]
=
_
5
4
_
2
5

1
6
1
6
_
2
4
+
_
5
4
_
2
5
+
_
6
4
_
2
6
_

=
10
29

.
3. Since E[Y |X = k] =
k
2
(the expectation of a binomial with n = k and p =
1
2
), the law of total
probability implies that
E[Y ] =
6

k=1
E[Y |X = k]P[X = k] =
1
6
6

k=1
k
2

=
7
4

.
4. By the same reasoning,
E[XY ] =
6

k=1
E[XY |X = k]P[X = k] =
6

k=1
E[kY |X = k]P[X = k]
=
6

k=1
kE[Y |X = k]P[X = k] =
1
6
6

k=1
1
2
k
2

=
91
12

.
www. statisticsassignmentexperts.com
email us at info@ statisticsassignmentexperts.com or call us at +1 520 8371215
.
Problem 14.4.
1. Consider an experiment which consists of 2 independent coin-tosses. Let the random vari-
able X denote the number of heads appearing. Write down the probability mass function
of X.
2. There are 10 balls in an urn numbered 1 through 10. You randomly select 3 of those balls.
Let the random variable Y denote the maximum of the three numbers on the extracted
balls. Find the probability mass function of Y . You should simplify your answer to a fraction
that does not involve binomial coecients. Then calculate: P[Y 7].
3. A fair die is tossed 7 times. We say that a toss is a success if a 5 or 6 appears; otherwise
its a failure. What is the distribution of the random variable X representing the number
of successes out of the 7 tosses? What is the probability that there are exactly 3 successes?
What is the probability that there are no successes?
4. The number of misprints per page of text is commonly modeled by a Poisson distribution.
It is given that the parameter of this distribution is = 0.6 for a particular book. Find the
probability that there are exactly 2 misprints on a given page in the book. How about the
probability that there are 2 or more misprints?
www. statisticsassignmentexperts.com
email us at info@ statisticsassignmentexperts.com or call us at +1 520 8371215
Solution:
1.
p
0
= P[{(T, T)}] =
1
4
,
p
1
= P[{(T, H), (H, T)}] =
1
2
,
p
2
= P[{(H, H)}] =
1
4
,
p
k
= 0, for all other k.
2. The random variable Y can take the values in the set {3, 4, . . . 10}. For any i, the triplet
resulting in Y attaining the value i must consist of the ball numbered i and a pair of balls
with lower numbers. So,
p
i
= P[Y = i] =
_
i1
2
_
_
10
3
_ =
(i1)(i2)
2
1098
321
=
(i 1)(i 2)
240
.
Since the balls are numbered 1 through 10, we have
P[Y 7] = P[Y = 7] +P[Y = 8] +P[Y = 9] +P[Y = 10].
So,
P[Y 7] =
6 5
240
+
7 6
240
+
8 7
240
+
9 8
240
=
1
240
(30 + 42 + 56 + 72)
=
200
240
=
5
6
.
3. X has a binominal distribution with parameters n = 7 and p = 1/3, i.e., X b(7, 1/3).
P[X = 3] =
_
7
3
__
1
3
_
3
_
2
3
_
4
=
560
2187
,
P[X = 0] =
_
2
3
_
7
=
128
2187
.
4. Let X denote the random variable which stands for the number of misprints on a given
page. Then
P[X = 2] =
0.6
2
2!
e
0.6
0.0988,
P[X 2] = 1 P[X < 2]
= 1 (P[X = 0] +P[X = 1])
= 1
_
0.6
0
0!
e
0.6
+
0.6
1
1!
e
0.6
_
= 1
_
e
0.6
+ 0.6e
0.6
_
= 1 1.6e
0.6
0.122.
www. statisticsassignmentexperts.com
email us at info@ statisticsassignmentexperts.com or call us at +1 520 8371215
Problem 14.5. Let X and Y be two Bernoulli random variables with the same parameter p =
1
2
.
Can the support of their sum be equal to {0, 1}? How about the case where p is not necesarily
equal to
1
2
? Note that no particular dependence structure between X and Y is assumed.
Solution: Let p
ij
, i = 0, 1, j = 0, 1 be dened by
p
ij
= P[X = i, Y = j].
These four numbers eectively specify the full dependence structure of X and Y (in other words,
they completely determine the distribution of the random vector (X, Y )). Since we are requiring
that both X and Y be Bernoulli with parameter p, we must have
p = P[X = 1] = P[X = 1, Y = 0] +P[X = 1, Y = 1] = p
10
+ p
11
. (14.2)
Similarly, we must have
1 p = p
00
+ p
01
, (14.3)
p = p
01
+ p
11
, (14.4)
1 p = p
00
+ p
10
(14.5)
Suppose now that the support of X + Y equals to {0, 1}. Then p
00
> 0 and p
01
+ p
10
> 0, but
p
11
= 0 (why?). Then, the relation (14.2) implies that p
10
= p. Similarly, p
01
= p by relation (14.4).
Relations (14.3) and (14.5) tell us that p
00
= 1 2p. When p =
1
2
, this implies that p
00
= 0 - a
contradiction with the fact that 0
X+Y
.
When p <
1
2
, there is still hope. We construct X and Y as follows: let X be a Bernoulli
random variable with parameter p. Then, we dene Y depending on the value of X. If X = 1,
we set Y = 0. If X = 0, we set Y = 0 with probabilty
12p
1p
and 1 with probability
p
1p
. How do
we know that Y is Bernoulli with probability p? We use the law of total probability:
P[Y = 0] = P[Y = 0|X = 0]P[X = 0] +P[Y = 0|X = 1]P[X = 1] =
12p
1p
(1 p) + p = 1 p.
Similarly,
P[Y = 1] = P[Y = 1|X = 0]P[X = 0] +P[Y = 1|X = 1]P[X = 1] = (1
12p
1p
)(1 p) = p.
www. statisticsassignmentexperts.com
email us at info@ statisticsassignmentexperts.com or call us at +1 520 8371215
3. Compute the variance of A
n
, for n N.
(Note: You may need to use the following identities:
n

k=1
k =
n(n + 1)
2
and
n

k=1
k
2
=
n(n + 1)(2n + 1)
6
, for n N.)
Solution:
1. No it is not. The distribution of A
2
is
_
_

3
2

1
2
1
2
3
2
1
4
1
4
1
4
1
4
_
_
In particular, its support is {
3
2
,
1
2
,
1
2
,
3
2
}. For n = 1, A
1
= X
1
, which has the support
{1, 1}. Therefore, the support of the dierence A
2
A
1
cannot be {1, 1} (indeed, the
dierence must be able to take fractional values). This is in contradiction with the deni-
tion of the random walk which states that all increments must have distributions supported
by {1, 1}.
2. We write X
k
=

k
i=1

i
, and X
l
=

l
j=1

j
, where {
n
}
nN
are the (iid) increments of
{X
n
}
nN
0
. Since E[X
k
] = E[X
l
] = 0, we have
Cov(X
k
, X
l
) = E[X
k
X
l
] = E
_
_
_
k

i=1

i
_
_
_
l

j=1

j
_
_
_
_
When the sum above is expanded, the terms of the form E[
i

j
], for i = j will disappear
because
i
and
j
are independent for i = j. The only terms left are those of the form
E[
i

i
]. Their value is 1, and there are k of them (remember k l). Therefore,
Cov(X
k
, X
l
) = k.
3. Let B
n
=

n
k=1
X
k
= nA
n
. We know that E[A
n
] = 0, and that Var[A
n
] =
1
n
2
Var[B
n
], so it
suces to compute
Var[B
n
] = E[B
2
n
] = E
__
n

k=1
X
k
__
n

l=1
X
l
__
We expand the sum on the right and group together equal (k = l) and dierent indices
(k = l) to get
Var[B
n
] =
n

k=1
Var[X
k
] + 2

1k<ln
Cov(X
k
, X
l
) =
n

k=1
k + 2

1k<ln
k.
www. statisticsassignmentexperts.com
email us at info@ statisticsassignmentexperts.com or call us at +1 520 8371215
2. p
1
= P

X
(0), and
P

X
(s) =
1

1 s
2
(1 +

1 s
2
)
,
so p
1
=
1
2
.
3. If E[X] existed, it would be equal to P

X
(1). However,
lim
s1
P

X
(s) = +,
so E[X] (and, equivalently, P

X
(1)) does not exist.
Problem 14.15. Let N be a random time, independent of {
n
}
nN
, where {
n
}
nN
is a sequence
of mutually independent Bernoulli ({0, 1}-valued) random variables with parameter p
B
(0, 1).
Suppose that N has a geometric distribution g(p
g
) with parameter p
g
(0, 1). Compute the
distribution of the random sum
Y =
N

k=1

k
.
(Note: You can think of Y as a binomial random variable with random n.)
Solution: Independence between N and {
n
}
nN
allows us to use the fact that the generating
function P
Y
(s) of Y is given by
P
Y
(s) = P
N
(P
B
(s)),
where P
N
(s) =
pg
1qgs
is the generating function of N (geometric distribution) and P
B
(s) =
q
B
+ p
B
s is the generating function of each
k
(Bernoulli distribution). Therefore,
P
Y
(s) =
p
g
1 q
g
(q
b
+ p
B
s)
=
pg
1qgq
B
1
qgp
B
1qgq
B
s
=
p
Y
1 q
Y
s
, where p
Y
=
p
g
1 q
g
q
B
and q
Y
= 1 p
Y
.
P
Y
can be recognized as the generating function of a geometric random variable with parameter
p
Y
.
Problem 14.16. Six fair gold coins are tossed, and the total number of tails is recorded; lets
call this number N. Then, a set of three fair silver coins is tossed N times. Let X be the total
number of times at least two heads are observed (among the N tosses of the set of silver coins).
(Note: A typical outcome of such a procedure would be the following: out of the six gold coins
4 were tails and 2 were heads. Therefore N = 4 and the 4 tosses of the set of three silver coins
may look something like {HHT, THT, TTT, HTH}, so that X = 2 in this state of the world. )
Find the generating function and the pmf of X. You dont have to evaluate binomial coe-
cients.
Solution: Let H
k
, k N, be the number of heads on the k
th
toss of the set of three silver
coins. The distribution of H
k
is binomial so P[H
k
2] = P[H
k
= 2] +P[H
k
= 3] = 3/8+1/8 = 1/2.
Let
k
be the indicator

k
= 1
{H
k
2}
=
_
1, H
k
2,
0, H
k
< 2.
www. statisticsassignmentexperts.com
email us at info@ statisticsassignmentexperts.com or call us at +1 520 8371215

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy