Hello, dear friend, you can consult us at any time if you have any questions, add WeChat: THEend8_
MATH2801: Theory of Statistics Assignment
Please follow the instructions below for the assignment (worth 15% of the final mark):
Due date: Before 4 PM Tuesday 1st August (Week 10).
Submission details:
1. This assignment may be completed in a group (max. 4 people), or individually.
2. Two Turnitin submission links will be provide in Moodle. Each person in the group
must submit an electronic copy of the assignment via the INDIVIDUAL Turnitin link.
One person must also submit the assignment via the GRADED Turnitin link.
3. The assignment may be typed or handwritten then scanned. It must be submitted
as a pdf file. Please make sure all the names and zIDs of each group member are
written on all pages.
4. Make sure you show all workings. You do not need to include RStudio commands/code.
Try to aim for clarity and conciseness!
Length: At most 8 pages are allowed for your assignment solutions. This cover sheet must be
submitted with your assignment, but it is not counted in the 8-page limit. A single pdf and Word
version of the coversheet is available in Moodle. Please do not exceed the 8-page limit!
Declaration: You must sign and date your submitted assignment, and include the PRINTED
names/zIDs of any other group members below:
I (We) declare that this assessment item is my (our) own work, except where acknowledged, and
has not been submitted for academic credit elsewhere, and acknowledge that the assessor of this
item may, for the purpose of assessing this item:
• Reproduce this assessment item and provide a copy to another member of the University;
and/or,
• Communicate a copy of this assessment item to a plagiarism checking service (which may
then retain a copy of the assessment item on its database for the purpose of future plagiarism
checking).
I (We) certify that I (We) have read and understood the University Rules in respect of Student
Academic Misconduct.
Date:
Name/zID/signature:
Name/zID/signature:
Name/zID/signature:
Name/zID/signature:
P
ro
pe
rt
y
of
U
N
SW
Some of these questions require the use of RStudio. You do not need to include ALL the
RStudio commands/code, only include commands/code of what is asked in the question.
Make sure to include all plots in your assignment.
1. (a) Let X1, . . . , Xn be a random sample of size n from a Poisson distribution with
parameter λ. Find:
i. The moment generating function of W = X1 + · · ·+Xn.
ii. Using the moment generating function of W , calculate E(W ).
Make sure you show all workings for both parts.
(b) Use RStudio to simulate a random sample of size n = 200 from X ∼ Poisson(1.2),
and then create a frequency histogram using these simulated data.
Comment on the shape of the histogram (in no more than 2 lines).
(c) Use RStudio to simulate 10,000 samples of size n = 200 from X ∼ Poisson(1.2).
Then, compute the sample sum Y =
∑n
i=1Xi for each of the 10,000 simulated
samples. Finally, produce a frequency histogram for the sample sums.
(d) Construct a normal quantile plot of these 10,000 sample sums (from part c).
(e) Explain (in no more than 3 lines) whether the Central Limit Theorem is verified
in this simulation study using the plots from parts c and d.
2. Let Y1, . . . , Yn be a random sample of observations from the model
fY (y;ψ) = (ψ + 1)y
ψ, 0 < y < 1, ψ > −1.
(a) Find the method-of-moments estimator ψ˜ of ψ.
(b) i. Find the maximum likelihood estimator ψ̂ of ψ.
ii. Compute the Fisher Information of ψ̂.
iii. Hence, compute the standard error of ψ̂.
(c) Obtain the probability density function of U = − ln(Y ).
3. (a) Why is randomization important in an experiment (explain in no more than 2
lines)?
(b) “Accuracy of the results of a statistical analysis are so important that we should
always take the largest possible sample size”. Comment on the above statement
(in no more than 3 lines).
(c) Suppose we have a population measurement which comes from Normal(µ, σ2)
where µ ∈ R is unknown but σ = 2.5 is known. Find the sample size that will
ensure that the length of a 99% confidence interval for µ is no longer than 1.