Exercise 1

Actual lengths of stay at Hamad hospital’s emergency department are shown in the following
table (rounded to the nearest hour). Length of stay is the total of wait and service times. Some
longer stays are also approximated as 15 hours in this table.
Hours Count Percent
1 19 3.80
2 51 10.20
3 86 17.20
4 102 20.40
5 87 17.40
6 62 12.40
7 40 8.00
8 18 3.60
9 14 2.80
10 11 2.20
15 10 2.00
(a) Calculate the probability that the length of stay is less than or equal to 4 hours.
Assume 5 patients arrive independently for the service.
(b) What is the probability that the length of stay of exactly one person is less than or equal to 4
hours?
(c) What is the probability that exactly two people wait more than 4 hours?
(d) What is the probability that at least one person waits more than 4 hours?
(e) What is the expected value of people who wait more than 4 hours?
(f) What is the probability that the eighth person waits more than 4 hours?
Exercise 2
Consider the patient data in table below. Let X denote the hospital number of the selected
patient (either 1, 2, 3, or 4).

Hospital

1 2 3 4 Total

Total 5892 6991 5640 5047 22852

Leave Without Being Seen (LWBS) 195 270 246 242 953

Admitted 1277 1558 666 984 4485

Not admitted 4420 5163 4728 3821 17414

Suppose that four patients are randomly selected with replacement from the total for hospital
1.

(a) Determine the probability of exactly one is LWBS

Suppose that patients are randomly selected with replacement from the total for hospital 4.
(b) What is the smallest sample size needed so that the probability is at least 90% that at least
one patient is LWBS?
(c) What is the probability that the fifth visit is the first one to LWBS?
The arrivals of patients to the hospitals between 1:00 and 2:00 PM follows a Poisson process
with the mean of 10.5
(d) What is the probability that no patients arrive between 1:00 and 1:10 pm?

Exercise 3

Data was taken on the levels of contamination and existence of defects from the entire
population of semiconductor wafers:

Low Moderate High

Non-defective 170 70 30
Defective 85 190 155
Let X be a random variable that encodes the level of contamination, taking the values of a
randomly chosen wafer as 0, 1, 2 for low, moderate, and high contamination, respectively.
Likewise, let Y be a random variable that encodes the existence of defects, taking values 0 and 1
for non-defective and defective, respectively.
(a) Determine the joint probability mass function (PMF) of X and Y and the marginal PMF’s of X
and Y.
(b) Are X and Y independent?
(c) Find the covariance of X and Y
(d) Find the correlation of X and Y

Exercise 4
Let X be a random variable that takes values -2, -1, 0, 1, 2 with uniform distribution. Let Y = X2.
(a) Determine the joint probability mass function (PMF) of X and Y and the marginal PMF’s of X
and of Y. (Hint: note that Y can take only values of 0, 1 & 4)
(b) Find E(X) and E(Y)
(c) Find Correlation of X and Y
(d) Are X and Y are independent (justify)

Exercise 5

Hits to a high-volume Web site are assumed to follow a Poisson distribution with a mean of
10,000 per day. Approximate each of the following:
(a) Probability of more than 20,000 hits in a day.

(b) Probability of less than 9900 hits in a day.

(c) Value such that the probability that the number of hits in a day exceeds the value is 0.01.
(d) Expected number of days in a year (365 days) that exceed 10,200 hits.

(e) Probability that over a year (365 days), each of the more than 15 days has more than 10,200
hits.

Exercise 6
Kahramaa is provided to approximately 2.7 million people who are served through more than
362,000 accounts. All accounts are metered and billed monthly. The probability that an account
has an error in a month is 0.001, and accounts can be assumed to be independent.
(a) What are the mean and standard deviation of the number of account errors each month?
(b) Approximate the probability of fewer than 350 errors in a month.
(c) Approximate a value so that the probability that the number of errors exceeds this value is
0.05.
(d) Approximate the probability of more than 400 errors per month in the next two months.
Assume that results between months are independent.
Exercise 7

An electron emitter produces an electron beam with changing kinetic energy that is uniformly
distributed in the range [2,11]. Let X denote the kinetic energy produced by this electron
emitter.

(a) Determine the mean and variance of X.

(b) A random sample of n = 20 is selected from this distribution. Find the probability that the
sample mean is greater than 6.8

A fault to the electron emitter has developed and the researchers wishes to test 𝐻𝐻0 : 𝜇𝜇 =
6.5 Joules versus 𝐻𝐻0 : 𝜇𝜇 ≠ 6.5 Joules, using the results of the previous sample.

(c) The acceptance region is 6.30 ≤ 𝑋𝑋� ≤ 6.65. Find the value of α

(d) Find the power of the test for detecting a true mean changing kinetic energy of 6.8 Joules.

Exercise 8

Service time for a customer coming through a checkout counter in a retail store is a random
variable with the mean of 1.5 minutes and standard deviation of 4.0 minutes. Suppose that the
distribution of service time is fairly close to a normal distribution. Suppose there are two
counters in a store, n1 = 41 customers in the first line and n2 = 51 customers in the second line.

(a) Find the probability that the difference between the mean service time for the shorter line
X 1 and the mean service time for the longer one X 2 is more than 0.4 minutes. Assume that
the service times for each customer can be regarded as independent random variables.

The retail store have introduced a self-checkout in the first line and the manager wishes to test
H0: μ=1.5 minutes versus H1: μ> 1.5 minutes, using the results of the previous sample.

(b) The acceptance region is 𝑋𝑋� ≤ 1.51. Find the value of α.

(c) Find the power of the test for detecting a true mean of serving customers is 1.48 minutes.
Exercise 9
Let X be random variable with the following probability distribution
1
𝑓𝑓𝑇𝑇 (𝑡𝑡) = (1 + 𝛼𝛼 cos 𝑡𝑡), −𝜋𝜋 ≤ 𝑡𝑡 ≤ 𝜋𝜋
2𝜋𝜋
(a) Find the moment estimator of α (Hint: In this case the mean is 0 for all values of α, so you
will have to compute the second moment to obtain an estimator)
(b) Check whether it is a biased or unbiased estimator
Assume a random sample T of size 8 from the above distribution is given below
- - -
2.733186 2.136283 3.078761 2.70177 1.85354 2.79602 2.70177 2.70177

(c) Estimate the point statistic of parameter α.

(d) Determine the mean square error of α

Exercise 10

Consider the following distribution

𝛽𝛽𝜃𝜃𝛽𝛽
𝑓𝑓(𝑥𝑥) = {𝑥𝑥 𝛽𝛽+1 , 𝑥𝑥 ≥ 𝜃𝜃,
0, 𝑥𝑥 < 𝜃𝜃.

(a) Assume that β ˃ 1, Find the moment estimator for θ ˃ 0.

(b) Check whether the estimator of θ is biased or not?

(c) Assume a random sample X of size 10 from the above distribution is given below
26 11 18 28 21 23 10 20 19 18
(c) Estimate the point statistic of parameter θ.

(d) Determine the mean square error of θ.

Exercise 11
In an attempt to measure the velocity of light in vacuum, a scientist used a new method. The
observations (in kilometres per second) are as follows (Note that each value has 299,000
subtracted from it)

850 1000 740 980 900 850 1000 740 980 900

930 1070 650 930 760 930 1070 650 930 760

850 810 950 1000 980 850 810 950 1000 980

1000 980 960 880 960 1000 980 960 880 960

(a) Construct a stem-and-leaf diagram and comment on its shape

(b) Compute the sample mean, mode, median, variance, standard deviation, quartiles,
interquartile range. Are there any outliers?

(c) Find an approximate 95% confidence interval on the mean

(d) What is the minimum sample size, n, required to achieve a maximum error E = |𝑋𝑋� - µ| = 100
for the 95% confidence level?

Exercise 12

In an attempt to measure the effects of acid rain, researchers measured the pH of water
collected from rain in Doha.

5.47 5.37 5.38 4.63 5.37 3.74 3.71 4.96 4.64 5.11

5.65 5.39 4.16 5.62 4.57 4.64 5.48 4.57 4.57 4.51

4.86 4.56 4.61 4.32 3.98 5.70 4.15 3.98 5.65 3.10

5.04 4.62 4.51 4.34 4.16 4.64 5.12 3.71 4.64 5.59

(a) Construct a stem-and-leaf diagram and comment on its shape

(b) Compute the sample mean, mode, median, variance, standard deviation, quartiles,
interquartile range. Are there any outliers?
(c) Find an approximate 95% confidence interval on the mean

(d) What is the minimum sample size, n, required to achieve a maximum error E = |𝑋𝑋� - µ| = 0.1
for the 95% confidence level?

Exercise 13

Aging bridges are inspected regularly to evaluate the risk of catastrophic failure. Here is the
condition reported on a scale from 1 to 7 from a sample of 30 bridges (Hint: the data is ordered):
3.42 3.48 3.61 3.97 4 4.19 4.41 4.54 4.66 4.83
4.93 4.95 5.07 5.08 5.26 5.27 5.43 5.44 5.48 5.57
5.61 5.72 5.76 5.91 6.04 6.26 6.43 6.66 7 7
A. Find the sample mean and the sample standard deviation of these condition numbers (4 marks)

B. Construct a stem-and-leaf diagram (Hint: use a leaf unit of 0.10 i.e. ignore the rightmost digit –
make sure that the values are in ascending order) (5 marks)

C. Comment on the shape of the distribution (i.e. skewness and number of modes) (1 mark)

D. Find the minimum, the quartiles, and the interquartile range of this data set. (4 marks)

E. Do any bridges appear to have unusually good or poor ratings? (Hint: check for any outliers) (2
marks)

F. Construct a two-sided 95% confidence interval on the mean of the condition (hint: assume the
sample variance matches the population variance for a large sample size) (5 marks)

G. What is the minimum sample size, n, required to achieve a maximum error E = |𝑋𝑋� - μ| = 0.75 for
the 95% confidence level? (Hint: always round up) (4 marks)
Exercise 14

Electronics company is comparing the brightness of two picture tube types for use in its television sets.
Tube type A has a mean brightness of 100 and a standard deviation of 16, and tube type B has an unknown
mean brightness, but the standard deviation is assumed to be identical to that for type A. A random sample
of n = 25 tubes of each type is selected and X B − X A is computed. If µ B equals or exceeds µ A , the
manufacturer would like to adopt type B for use. The observed difference is 𝑥𝑥̄ 𝐵𝐵 − 𝑥𝑥̄𝐴𝐴 = 3.0.
A. What is the probability that X B exceeds X A by 3.0 or more if µ B and µ A are equal? (5 marks)
B. The company wishes to test H0: μB = 103 versus H1: μB < 103, using the results of n = 25 samples.
Is there evidence to support the claim that the mean brightness of tube type B exceeds 103 if the
observed 𝑥𝑥̄ 𝐵𝐵 = 100? Use α=5% (Hint: it is sufficient to check whether test statistic Z0 is either
greater or smaller than Z0.05) (10 mark)
C. Find the type I error probability if the critical region is actually 𝑥𝑥̅ < 97 (5 mark)
D. What is the power of the test if the true mean is 94? (5 mark)

Exercise 15

A random sample X 1 ,..., X n is selected from the shifted exponential distribution

eβ − x , x≥β
f ( x) = {
0, x < β

A. What is the expected value of X? (Hint: you may use integration by parts) (5 marks)

B. What is the moment estimator for β ? (5 marks)

C. Check whether it is biased or unbiased (5 marks)

NOW, assume a random sample size of 10 is given as follows:

{44; 37; 38; 42; 41; 39; 38; 44; 39; 42}

D. Estimate the point statistic of the parameter β . (5 marks)

E. Determine the mean square error of β . (5 marks)

Exercise 16
Consider the endothermic reactions in the table below:
Final Temperature Conditions Number of Reactions
226 K 48
271 K 60
274 K 92
A total of 20 independent reactions are to be conducted. Answer the following:
A. Determine the probability that a reaction results in a final temperature less than 272 K (5 marks)
B. What is the probability that exactly 12 reactions result in a final temperature less than 272 K? (5
marks)
C. What is the probability that at least 18 reactions result in a final temperature less than 272 K? (5
marks)
D. What is the expected number of reactions that result in a final temperature of less than 272 K? (5
marks)
E. What is the probability that the first reaction that results in a final temperature less than 272 K
occurs on the tenth trial? (5 marks)

Exercise 17

Disaster data can be used to inform policy decisions to help reduce disaster risks and build resilience.
Geological investigations and historical records of earthquakes in a specific region show that the average
number of earthquakes with magnitude 4 to 4.9 is 456 per year. Assume a POISSON distribution.
A. Determine the mean number of earthquakes per month (5 marks)
B. Determine the standard deviation of earthquakes per month (5 marks)
C. Use the appropriate approximation to find the probability that at least 42 earthquakes occur in a
month (5 marks).
D. Use the appropriate approximation to find the probability that at most 34 earthquakes occur in a
month (5 marks).
E. Use the appropriate approximation to find the least number of earthquakes per month with
probability 0.90 (5 marks)

Exercise 18

Let X be a random variable that takes values −𝜋𝜋�6 , −𝜋𝜋�3 , 0, 𝜋𝜋�3 , 𝜋𝜋�6 with UNIFORM distribution. Let
Y = Cos (X).

A. Determine the joint probability mass function (PMF) of X and Y (5 marks) and the
marginal PMF’s of X and of Y (5 marks) (Hint: note that Y can take only values of 1,
√3
0.5 & )
2

B. Find E(X) and E(Y) (5 marks)

C. Find Covariance of X and Y (5 marks)
D. Are X and Y are independent (justify) (5 marks) (Hint: you can either use conditional
probability rule or product rule)
Exercise 19 (20 marks)

A data packet consists of 10 000 bits, where each bit is a 0 or a 1 with equal probability.

Calculate the expected value of the number of ones (4 marks)

Let X be the number of ones which follows a binomial random variable with n = 10000 and p =
0.5. Its expected value is E[X] = np = 10000 x 0.5 = 5000

Calculate the standard deviation of the number of ones (4 marks)

The standard deviation is given by Var[X] = sqrt(np(1-p)) = sqrt(10000 x 0.5 x 0.5) = 50

Estimate the probability of having at least 5020 ones. (4 marks)

The probability can be calculated exactly using the equation below

10000
10000 𝑥𝑥
𝑃𝑃(𝑋𝑋 ≥ 5020) = � � � 𝑝𝑝 (1 − 𝑝𝑝)10000−𝑥𝑥 = 0.348269
𝑥𝑥
𝑥𝑥=5020
However, this sum is tedious to calculate without access to fast calculators. Instead, normal
approximation to binomial distribution is used

5019.5−5000
𝑃𝑃(𝑋𝑋 ≥ 5020) = 𝑃𝑃(𝑋𝑋 > 5019.5) = 𝑃𝑃 �𝑍𝑍 > 50
� = 𝑃𝑃(𝑍𝑍 > 0.39) = 0.348268
The approximation is very close to the exact value to 5 significant figures!!!

Estimate the probability of having at most 4980 zeros. (4 marks)

Again, the probability can be calculated exactly using the equation below
4980
10000 𝑥𝑥
𝑃𝑃(𝑋𝑋 ≤ 4980) = � � � 𝑝𝑝 (1 − 𝑝𝑝)10000−𝑥𝑥 = 0.348269
𝑥𝑥
𝑥𝑥=0
Like the previous question, this sum is tedious to calculate without access to fast calculators.
Instead, normal approximation to binomial distribution is used

4980.5−5000
𝑃𝑃(𝑋𝑋 ≤ 4980) = 𝑃𝑃(𝑋𝑋 < 4980.5) = 𝑃𝑃 �𝑍𝑍 < 50
� = 𝑃𝑃(𝑍𝑍 < −0.39) = 0.348268
Once more, the approximation is very close to the exact value to 5 significant figures!!!
Estimate the average number of ones with a probability exceeding 0.9 (4 marks)

Again, this equation is challenging to solve analytically using the exact binomial distribution.
Instead we apply the normal approximation to the binomial distribution

𝑋𝑋� − 0.5 − 5000

𝑃𝑃 �𝑍𝑍 ≤ � > 0.9
50

𝑍𝑍 > 1.281552

𝑋𝑋� − 0.5 − 5000

≥ 1.281552
50

𝑋𝑋� ≥ 5065
Exercise 20 (20 marks)

A factory produces links for heavy metal chains. The research lab of the factory models the length (in
cm) of a link by the random variable X, with expected value E[X] = 5 and variance Var(X)=0.04.

The length of a link is defined in such a way that the length of a chain is equal to the sum of the lengths
of its links.

The factory sells chains of 50 meters; to be on the safe side 1002 links are used for such chains. The
factory guarantees that the chain is not shorter than 50 meters. If by chance a chain is too short, the
customer is reimbursed, and a new chain is given for free

Determine the mean and variance of the chain length with 1002 links (denoted by the random variable
Y) (6 marks)

1002

𝑌𝑌 = � 0.01 × 𝑋𝑋𝑖𝑖
1

𝐸𝐸[𝑌𝑌] = 1002 × 𝐸𝐸[𝑋𝑋] = 50.1 𝑚𝑚

𝑉𝑉𝑉𝑉𝑉𝑉[𝑌𝑌] = 1002 × 0.0001 × 𝑉𝑉𝑉𝑉𝑉𝑉[𝑋𝑋] = 0.004008 𝑚𝑚2

Give an estimate of the probability that for a chain of at least 50 meters more than 1002 links are
needed (4 marks)

50 − 50.1
𝑃𝑃(𝑌𝑌 > 50) = 𝑃𝑃 �𝑍𝑍 > � = 0.943777642
0.063
For what percentage of the chains does the factory have to reimburse clients and provide free chains? (2
marks)

Around 5.62% of chains are reimbursed

The sales department of the factory notices that it has to hand out a lot of free chains and asks the
research lab what is wrong. After further investigations the research lab reports to the sales department
that the expectation value 5 is incorrect, and that the correct value is 4.99 (cm).

Do you think that it was necessary to report such a minor change of this value? (8 marks)

Hint: repeat your answers for the previous parts using the new expectation value and compare your
results to draw a judgement

1002

𝑌𝑌 = � 0.01 × 𝑋𝑋𝑖𝑖
1

𝐸𝐸[𝑌𝑌] = 1002 × 𝐸𝐸[𝑋𝑋] = 49.9998 𝑚𝑚

 50 − 49.9998
𝑃𝑃(𝑌𝑌 > 50) = 𝑃𝑃 �𝑍𝑍 > � = 0.498735355
0.063

Yes, it was necessary to report such a minor change since it changes the percentage of reimbursed
chains considerably.
Exercise 21 (20 marks)

The joint probability distribution of two discrete random variables X and Y is partly given in the following
table.

1/6 1/6 1/6

0 0

Complete the table (5 marks)

Are X and Y independent? Justify your answer (5 marks)

X and Y are not independent since P(X=1, Y=1) = ½ whereas P(X=1) x P(Y=1) = 2/3 x ½ = 1/3

Are X and Y correlated? Justify your answer (5 marks)

E[X] = 1

E[Y] = 0

E[XY] = 0

Cov [X,Y] = E[XY] – E[X]E[Y] = 0

Cor [X,Y] = Cov [X,Y]/sqrt(Var[X] x Var[Y]) = 0

X and Y are uncorrelated

Determine Var (X+Y) (5 marks)

Var [X] = E[X2] – E[X]2 = 4/3 – 1 = 1/3

Var [Y] = E[Y2] – E[Y]2 = 1 – 0 = 1

Var[X+Y] = Var[X] + Var[Y] = 4/3 (note the Cov [X,Y] = 0)

Exercise 22 (20 marks)

The mean price of cars produced by a car manufacturer is 36000 QAR and the standard deviation is 2000
QAR. It is claimed that the prices of new cars have increased. To test this claim, a sample of 50 new cars
is tested, and it is found that the mean price is 37000 QAR.

Is there sufficient evidence to support the claim at a 0.01 level of significance? (4 marks)

1. The parameter of interest is the true mean of car prices

2. Null Hypothesis: H0: μ = 36000 QAR

3. Alternative Hypothesis: H1: μ > 36000 QAR

� −μ
X
4. Test statistic is Z0 = σ
√n

5. Reject if the observed significance level is less than α = 0.01. The boundaries of the critical
region would be Z0.01 = 2.33
� −μ
X 37000−36000
6. Calculation Z0 = σ = 2000 = 3.53
√n √50

7. Conclusion: since Z0 = 3.53 (which is greater than 2.33) and the observed significance level
is [1 − Φ(3.53)] = 0.00020778, we reject the H0: μ = 36000 QAR at the 0.01 significance
level. There is a (strong) evidence to support the claim that the average car prices exceeds
36000 QAR
Determine the probability of a Type I error if the critical price should not exceed 36300 QAR, i.e. α. (4
marks)

α = P(𝑋𝑋� > 36300 when μ = 36000)

𝑋𝑋� − 36000 36300 − 36000
= 𝑃𝑃 � > �
2000⁄√50 2000⁄√50
= P(Z > 1.06) = 0.14572
Construct an upper one-sided 99% confidence interval on the mean price of cars (4 marks)

𝜎𝜎
𝜇𝜇 ≤ 𝑋𝑋� + 𝑍𝑍𝛼𝛼
√𝑛𝑛
2000
𝜇𝜇 ≤ 37000 + 𝑍𝑍0.01
√50
2000
𝜇𝜇 ≤ 37000 + 2.33
√50
μ ≤ 37659 QAR

Find the probability of a Type II error if the true mean price has increased to 36600, i.e. β. (4 marks)

β = P(𝑋𝑋� < 36300 when μ = 36600)

𝑋𝑋� − 36600 36300 − 36600
= 𝑃𝑃 � < � = P(Z < −1.06) = 0.14572
2000⁄√50 2000⁄√50
In response to significant increase in road travel, the car manufacturer has decided to increase the
prices of its cars in two ways: (i) increase the prices of each car by 3600 QAR, and (ii) increase the price
of each car by 10%.

Determine the mean and standard deviation of the new prices for each of these two schemes and
explain the impact of each scheme. (4 marks)

Let Y1 be the new random variable for the new price using scheme (i) and Y2 be the new random
variable for the new price using scheme (ii).

Y1 = X + 3600

Y2 = 1.1X

E[Y1] = E[X] + 3600 = 39600 QAR

E[Y2] = 1.1 x E[X] = 39600 QAR

Var [Y1] = Var[X] = 4 million QAR2

Var [Y2] = 1.12 x Var[X] = 4.84 million QAR2

Std [Y1] = 2000

Std [Y2] = 2200

There will be more variability in the second scheme

Exercise 23 (20 marks)

The cumulative distribution function of a non-negative random variable, 𝑋𝑋, is given by:

𝑥𝑥 2
− 2
𝐹𝐹(𝑥𝑥) = 1 − e 2𝜎𝜎 , 𝑥𝑥 ≥ 0

where σ is the scale parameter of the distribution

Determine the probability density function 𝑓𝑓(𝑥𝑥) (4 marks)

𝑑𝑑𝑑𝑑(𝑥𝑥) 𝑥𝑥 − 𝑥𝑥 22
𝑓𝑓(𝑥𝑥) = = 2 e 2𝜎𝜎
𝑑𝑑𝑑𝑑 𝜎𝜎

Determine the expected value of 𝑋𝑋. (4 marks)

2
∞ − 𝑥𝑥 2 𝜋𝜋
Hint: use integration by parts and note that ∫0 e 2𝜎𝜎 𝑑𝑑𝑑𝑑 = 𝜎𝜎�
2

∞ ∞ 2
𝑥𝑥2 − 𝑥𝑥
𝐸𝐸[𝑋𝑋] = � 𝑥𝑥𝑥𝑥(𝑥𝑥) 𝑑𝑑𝑑𝑑 = � 2 e 2𝜎𝜎2 𝑑𝑑𝑑𝑑
0 0
𝜎𝜎

Using integration by parts and the hint provided

𝜋𝜋
𝐸𝐸[𝑋𝑋] = 𝜎𝜎�
2
Determine an estimator for 𝜎𝜎 using the method of moment (4 marks)

Since only a single parameter is required namely, σ, thus only the first moment need to be determined.

Equating the population mean to the sample mean

𝑛𝑛
𝜋𝜋 1
𝜇𝜇 = 𝜎𝜎� = 𝑋𝑋� = � 𝑋𝑋𝑖𝑖
2 𝑛𝑛
𝑖𝑖=1

2
Therefore, 𝜎𝜎� = � 𝑋𝑋�
𝜋𝜋

Check whether the estimator is biased (4 marks)

2 2 2 1
𝑛𝑛 �2 𝑛𝑛 �2 𝑛𝑛 �2
𝜋𝜋 𝜋𝜋 𝜋𝜋
𝐸𝐸[𝜎𝜎�] = 𝐸𝐸 �� 𝑋𝑋�� = � 𝐸𝐸[𝑋𝑋�] = � 𝐸𝐸 � � 𝑋𝑋𝑖𝑖 � = 𝐸𝐸 �� 𝑋𝑋𝑖𝑖 � = � 𝐸𝐸[𝑋𝑋𝑖𝑖 ] = 𝑛𝑛𝑛𝑛[𝑋𝑋𝑖𝑖 ]
𝜋𝜋 𝜋𝜋 𝜋𝜋 𝑛𝑛 𝑛𝑛 𝑛𝑛 𝑛𝑛
𝑖𝑖=1 𝑖𝑖=1 𝑖𝑖=1

2 𝜋𝜋
= � 𝜎𝜎� = 𝜎𝜎
𝜋𝜋 2

The estimator is unbiased

Assume a random sample from the above distribution is given below

4.42

3.33

2.73

3.28

2.28

3.83

2.23

3.49

2.08

0.97

Determine the point estimate of parameter 𝜎𝜎. (4 marks)

𝑋𝑋� = 2.86

√2
𝜎𝜎� = 𝑋𝑋� = 2.29
√𝜋𝜋