AMA2104 Probability and Engineering Statistics

Assignment 1

Due at 17:00, October 11, 2019, Friday. Please submit your homework into the assignment box at floor
7 or 8 (depends on how general office would arrange the box), core T. The assignment box will be available
days after the assignment is posted, and with the lecturer’s name “Dr. Guo Xin” printed on the front.
The markers of the assignments are research students from department AMA. Please show your courtesy
to them by boxing your final solutions if that is not difficult, like:

...therefore the desired probability is P (A) = 0.334 .

In all the computations, if you need to round a number, please keep four decimal places, like

1000 0.02
= 142.8571, = 0.0029.
7 7
Full marks: 100.

Required part. Each and every student should try the problems in this part. Please show all of your
steps.
1. (10 marks) Let X be a random variable with density function
{
xe−x /2 , when x > 0,
2

f (x) =
0, when x ≤ 0.

(a). Find the CDF of X.

(b). Find E[X 2 ].
2. (10 marks) Let X be a random variable with CDF
{
0, when x < 0,
F (x) = −x −x
1 − e − xe , when x ≥ 0.

(a). Find the PDF of X.

(b). Find E[X] and Var(X).
(c). Find E[etX ], where t < 1 is a constant.
3. (10 marks) Let X be a discrete random variable with PMF
{
2−x , for x = 1, 2, 3, . . . ,
f (x) =
0, otherwise.

(a). Find P (X ≤ 10).

(b). Find E[X] and Var(X).
(c). Find E[etX ], where t < ln 2 is a constant.
4. (10 marks) Suppose that the CDF of a random variable X is given by
{
1 −(x−3)2 /2
2e , when x ≤ 3,
F (x) =
1 − 21 e3−x , when x > 3.

Find P (2 < x < 6).

5. (10 marks) Let X1 , . . . , X100 be a sample independently drawn from Uniform(0, 1). Let X be the
sample mean. Recall that the density function f of Uniform(0, 1) is
{
1, when 0 < x < 1,
f (x) =
0, otherwise.

1
 (a). Find E[X1 ] and Var(X1 ).
(b). Find E[X] and Var(X).
(c). Find P (0.45 < X < 0.55).

6. (10 marks) Let s2 be the sample variance from a sample drawn independently from N (122.55, 18) of
size 30.

(a). Find E[s2 ] and Var(s2 ).

(b). Find x1 and x2 such that P (s2 < x1 ) = P (s2 > x2 ) = 0.05.

7. (10 marks) Suppose we have the following sample drawn independently from a normal distribution.

11.8, 9.6, 9.6, 9.2, 10.2.

a. If the population variance is not known, find a 95% confidence interval for the population mean.
The sample variance s2 = 1.052 is computed for your convenience.
b. If we know that the population variance is 1.052, find a 95% confidence interval for the population
mean.

8. (20 marks) Suppose we have two independent samples:

• Sample 1: X1 , . . . , Xm , drawn independently from N (µ1 , σ12 ).

• Sample 2: Y1 , . . . , Yn , drawn independently from N (µ2 , σ22 ).

Some statistics are listed below.

sample size sample mean sample variance

Sample 1 12 102 3.5
Sample 2 15 95 2.8

(a). Build a 95% confidence interval for µ1 − µ2 .

(b). If we know that σ1 = σ2 , build a 95% confidence interval for µ1 − µ2 .
(c). If we know that σ1 = 3.7 and σ2 = 2.5, build a 95% confidence interval for µ1 − µ2 .

9. (10 marks) 1 In a study conducted in the Forestry and Wildlife Department at Virginia Tech, J. A.
Wesson examined the influence of the drug succinylcholine on the circulation levels of androgens in
the blood. Blood samples were taken from wild, free-ranging deer immediatley after they had received
an intramuscular injection of succinylcholine administered using darts and a capture gun. A second
blood sample was obtained from each deer 30 minutes after the first sample, after which the deer was
released. The levels of androgens at time of capture and 30 minutes later, measured in nanograms per
milliliter (ng/mL), for 15 deer are given in the table below.
Assume that the populations of androgen levels at time of injection has a normal distribution N (µ1 , σ12 )
with unit ng/mL, and the androgen levels 30 minutes later has another normal distribution N (µ2 , σ22 )
with unit ng/mL. Draw a 95% confidence interval for µ2 − µ1 .
1 This problem is partly cited from a textbook for educational purpose, permitted by Hong Kong Ordinances CAP 528

COPYRIGHT ORDINANCE Section 41A Fair dealing for purposes of giving or receiving instruction. The detailed information
of the textbook will be provided in the solutions of this assignment.

2
 Androgen (ng/mL)
Deer di
At Time of Injection 30 Minutes after Injection
1 2.76 7.02 4.26
2 5.18 3.10 -2.08
3 2.68 5.44 2.76
4 3.05 3.99 0.94
5 4.10 5.21 1.11
6 7.05 10.26 3.21
7 6.60 13.91 7.31
8 4.79 18.53 13.74
9 7.39 7.91 0.52
10 7.30 4.85 -2.45
11 11.78 11.10 -0.68
12 3.90 3.74 -0.16
13 26.00 94.03 68.03
14 67.48 94.03 26.55
15 17.04 41.70 24.66

The following statistics are computed for your convenience: d¯ = 9.848, sd = 18.474. Find the 95%
confidence interval for µ2 − µ1 .

Optional part. Students may also try the following problems which are more involved. The problems
below are not required, and they do not carry marks.

10.* Suppose that an infinite sequence of independent trials are carried out, where each trial outputs only
two possible outcomes: “success” with probability p (0 < p < 1), and “failure” with probability 1 − p.
Let r ≥ 1 be an integer. Let X denote the number of failures that occur before the r’th successes.
Then X is a discrete random variable with the probability mass function
{ (r+x−1)
x pr (1 − p)x , for x = 0, 1, 2, . . . ,
f (x) =
0, otherwise.
(n)
Recall that for any two integers m and n, if 0 ≤ m ≤ n, then m n!
:= m!(n−m)! . We call the distribution
of X the negative binomial distribution and denote it by NB(r, p). Find E[X] and Var(X).

11.* Recall the binomial distributions. Suppose X ∼ Binomial(n, p) (where n ≥ 1 is an integer and 0 < p <
1), which means that the PMF of X is
{ ( n)
px (1 − p)n−x , for x = 0, 1, . . . , n,
x
f (x) =
0, otherwise.

Find E[X] and Var(X).

12.* Prove the following Markov Inequality. Suppose that X is a continuous random variable having density
function f , and that f (x) = 0 for any x < 0. Prove that for any number t > 0,

E[X]
P (X ≥ t) ≤ .
t

13.* Suppose X has a Cauchy Distribution, of which the density function is

α
f (x) = , for − ∞ < x < ∞.
1 + x2

(a). Find α.
(b). Prove2 that E[|X|] = ∞.

2 Note that if a random variable X satisfies E[|X|] = ∞, we say that the random variable X has no mean.