You are on page 1of 4

Past Exam 1

MTH2222

Throughout this paper, CDF, PMF, PDF and MGF stand for cumulative distribution
function, probability mass function, probability density function and moment generating
function, respectively. All answers must be justied.

1 A laboratory blood test is eective in detecting a certain disease when it is in fact


present, with probability 1 . However, the test also yields a false positive (i.e.
the test result of a healthy person indicates he has the disease) with probability .
If in a given population, a randomly selected person actually has the disease with
probability p, what is the probability a person has the disease given that his test
result is positive?
[4 marks]

2 Let X be a discrete random variable with PMF


pX (x) = c a2x ,

x = 1, 2, . . .

where 0 < a < 1.


(a) Write down an expression for

a2n , for |a| < 1.

n=0

(b) Obtain c, identify the distribution of X and deduce E[X] and var(X).
[7 marks]

3 In a game show, contestants select at random (with equal probability) one of three
topics, Anatomy, Biology and Chemistry. The host then asks n questions from the
chosen topic. Maries knowledge allows her to correctly answer a randomly selected
question from these topics with probability qA , qB and qC respectively. Assuming
that, for a given topic, the outcomes of the n questions (correct or incorrect) are
independent, nd the PMF of the number of Maries correct answers, and its mean.
[6 marks]

4 Let, for an integer k 3, X have the following PDF:


fX (x) =

c
xk+1

, x > 1.

(a) Find c, E[X] and var(X).


(b) Find the PDF of ln X and identify its distribution.
[9 marks]

5 Let X be a random variable with MGF given by


MX (t) =

exp(t2 )
1t

(t < 1).

Find the mean and variance of X.


[5 marks]
Page 2 of 5

Past Exam 1

MTH2222

6 The joint PDF of X and Y is given by


fX,Y (x, y) = 2 ey e(1r)x , 0 < x < y/r,
where r > 0.
(a) Find the marginal PDF of X, and identify its distribution.
(b) Find the conditional PDF of Y given X = x.
(c) Deduce the conditional mean of Y given X = x.
(d) Find the mean and variance of Y .
(e) Find the covariance of X and Y by conditioning on X.
(f) Are X and Y independent? Explain.
[17 marks]

7 Let X be a random variable with MGF given by


(

MX (t) =

e2t 1
2t

)n

where n is a strictly positive integer.


(a) Identify the distribution of X when n = 1.
(b) Deduce the mean and variance of X for an arbitrary n.
[6 marks]

8 Let X1 , X2 , . . . be a sequence of independent Bernoulli p random variables, let N be


a binomial (n, a) random variable (i.e. with n trials and probability a of success)
independent of the Xi s, and let
S=

Xk , if N 1 and S = 0, if N = 0.

k=1

Obtain and identify the distribution of S.


[6 marks]

9 Let Xn be the number of successes in n Bernoulli trials where the probability of


success is p. Let Yn = Xn /n be the average number of successes per trial. Derive
the limit of Yn as n by applying the Chebyshev inequality to the event
{|Yn p| > a}. In what sense does Yn converge to this limit?
[4 marks]
End of examination questions

Page 3 of 5

Past Exam 1

MTH2222

Formula Sheet
Common Random Variables
The Bernoulli Random Variable with probability p of success:
pX (x) = px (1 p)1x , x = 0, 1
E[X] = p, var(X) = p(1 p) and MX (t) = (1 p) + pet .
The Binomial Random Variable with n trials and probability p of success:
n!
pX (x) =
px q nx , x = 0, 1, . . . , n
x!(n x)!
(
)n
E[X] = np, var(X) = np(1 p) and MX (t) = (1 p) + pet .
The Discrete Uniform Random Variable over [m, n]:
1
pX (x) =
, x = m, . . . , n
nm+1
m+n
(n m)(n m + 2)
e(n+1)t emt
E[X] =
, var(X) =
and MX (t) =
.
2
12
(n m + 1)(et 1)
The Geometric Random Variable with probability p of success:
pX (x) = p(1 p)x1 , x = 1, 2, . . .
1
1p
pet
E[X] = , var(X) =
and
M
(t)
=
, t < ln(1 p).
X
p
p2
1 (1 p)et
The Poisson Random Variable with parameter :
x
pX (x) = e , x = 0, 1, . . .
x!
t
E[X] = , var(X) = and MX (t) = e(e 1) .
The Continuous Uniform Random Variable over [a, b]:
1
fX (x) =
,axb
ba
a+b
(b a)2
ebt eat
E[X] =
, var(X) =
and MX (t) =
.
2
12
(b a)t
The Exponential Random Variable with parameter :
fX (x) = ex , x > 0
1
1

E[X] = , var(X) = 2 and MX (t) =


, t < .

t
The Gamma Random Variable with parameters and :
1 x
x e ,x>0
fX (x) =
()
(
)

E[X] = , var(X) = 2 and MX (t) =


, t < .

t
The Normal Random Variable with parameters and 2 :
1
2
2
fX (x) =
e(x) /(2 )
2
(
)
E[X] = , var(X) = 2 and MX (t) = exp t + 2 t2 /2 .
Page 4 of 5

Past Exam 1

MTH2222

The Bivariate Normal Distribution with parameters (, ), ( 2 , 2 ) and :


fX,Y (x, y)

1
1
(x )2 (y )2
(x )(y )

=
exp

2
2(1 2 )
2
2

2 1 2

]}

X is normal with mean and variance 2 . Y is normal with mean and variance

2 . Conditionally on Y = y, X is normal with mean + (y ) and variance

2 (1 2 ).

Common Sums and Formulae


The Arithmetic and Associated Sums:
n

k=

k=1

n
n
n(n + 1)
n(n + 1)(2n + 1)
n2 (n + 1)2
,
k2 =
,
k3 =
2
6
4
k=1
k=1

The Binomial and Associated Formulae:


n

( )

k=0

( )

n k nk
n k nk
a b
= (a + b)n ,
k
a b
= na(a + b)n1 ,
k
k
k=1
n

k=1

( )

n k nk
a b
= na(na + b)(a + b)n2
k

The Geometric and Associated Sums: For all z = 1,


n

zk =

k=0

1 z n+1
1z

and for |z| < 1,

1
2
1
k1
,
kz
=
,
k(k 1)z k2 =
z =
2
1 z k=1
(1 z) k=2
(1 z)3
k=0

The Exponential Power Series: For all z,

zk
k=0

k!

= ez

End of examination paper


Page 5 of 5

You might also like