Scribd
Upload
33 views

Class Test 2 Solution 2019

1) The document is a class test containing 3 questions about probability distributions and statistical concepts. 2) Question 1 asks about modeling the number of clients entering a bank using a Poisson distribution and calculating the probability of at least 3 clients entering between 12:00-12:05. 3) Question 2 relates to properties of geometric random variables and calculating the probability that the first deposit at an ATM was made on the fifth customer. 4) Question 3 involves confidence intervals, comparing productivity of insurance claim assessors before and after a training program, and suggesting an alternative experimental design.

Uploaded by

Ne Pa
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
33 views

Class Test 2 Solution 2019

1) The document is a class test containing 3 questions about probability distributions and statistical concepts. 2) Question 1 asks about modeling the number of clients entering a bank using a Poisson distribution and calculating the probability of at least 3 clients entering between 12:00-12:05. 3) Question 2 relates to properties of geometric random variables and calculating the probability that the first deposit at an ATM was made on the fifth customer. 4) Question 3 involves confidence intervals, comparing productivity of insurance claim assessors before and after a training program, and suggesting an alternative experimental design.

Uploaded by

Ne Pa
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 3

Class Test 2–STAT 1011Y (9 April 2018)

Instructions:
Answer ALL questions
Time allocated: 35 mins
Silent non-programmable calculators are allowed

Question 1

Clients enter a bank at a rate of 1 every 2 minutes.


(a) Which probability distribution would be appropriate to model the number of clients
entering the bank between 12:00 and 12:05? Justify your answer with any assumptions
you may make. [3]
Poisson distribution. It is assumed that clients come randomly between 12:00 and 12:05.
It is also assumed that the average number of clients entering the bank is constant over
the period of interest.
(b) What is the probability that at least 3 clients enter the bank between 12:00 and 12:05?
[3]
Let X be the r.v representing the number of clients entering the counter in 5 minutes.
X~Po(2.5)
2.52
{ (
P ( X ≥3 )=1−P ( X <3 )=1− e−2.5 1+2.5+
2 )}
=0.456

Question 2

Let X be a geometric random variable such that its probability distribution function is of the form
f X ( x )=( 1− p ) x−1 p for x=1,2 , …

(a) Show that for all non-negative integers s and t, P ( X ≥ s+t |X ≥ t ) =P( X ≥ s)

[3]

P { ( X ≥ s +t ) ∩ ( X ≥ t ) } P ( X ≥ s +t ) q s+ t s
P ( X ≥ s+t |X ≥ t ) = ¿ = t =q =P( X ≥ s)
P ( X ≥t ) P ( X ≥ t ) q

(b) From past experience it is noted that 3% of customers at an ATM machine make deposits
at the start of a new business day. What is the probability that the first deposit was made
when five customers used the ATM? [3]

Let X be the r.v representing the number of customers who used the ATM until the first
deposit was made.
X~Geo(0.03)
P ( X ≤5 )=1−0.97 5=0.141

Question 3
Class Test 2–STAT 1011Y (9 April 2018)

(a) The claim amounts for a certain policy are assumed to be independent of one another.
The mean (μ) of the claim amounts is Rs 100000. The approximate probability that the
sum of 50 such claims amounts being more than Rs 5100000 is 0.089. What is the
standard deviation (σ ) of the claim amounts? [4]
Let X be the random variable representing the claim amount
Since the sample size is large, by the central limit theorem,
σ2
(
X́ ˙ N 100000 ,
50 )
∑ X ˙ N ( 50 ×100000,50 × σ 2 )
5100000−5000000
P ( ∑ X >5100000 )=P Z > ( σ × 50 √ )
100000 100000 100000
¿ P Z>( σ √ 50 )
=0.089
σ √ 50
=1.347σ =
1.347 × √50
=10499

(b) A claim assessor looks at a claim situation, determine whether it falls under the coverage
of the policyholder and assess the costs involved. A training program has been devised
for the claim assessors of a very big insurance company in view of improving their
productivity which is measured by the number of claims closed. Data on the productivity
of two random samples of claim assessors before and after the training is given in the
following table.
Before Training After Training
Sample Size (n) 7 9
Mean 5.286 6.444
Variance 3.571 2.528

(i) Compute a 95% confidence interval for the difference in the average productivity
of the claim assessors before and after the training and interpret your result.

[7]
Let μb and μa be the true average number of claims closed before and after
training respectively.
( 7−1 ) × 3.571+ ( 9−1 ) ×2.528
S2p= =2.975
7+9−2
Assuming that the number of claims closed come from normal populations, are
independent and that their population variances are equal, a 95% CI for μa −μ b is
given by
1 1
√ ( )
( 6.444−5.286 ) ±2.1448 2.975 + =1.158 ± 1.864=(−0.706 , 3.022)
7 9
Since the confidence interval includes zero, this implies that there is no
significance difference in the average productivity of the claim assessors before
Class Test 2–STAT 1011Y (9 April 2018)

and after the training and conclude that there is insufficient evidence to say that
the training has been effective.

(ii) Suggest an alternative to the way of carrying out the experiment to determine
whether the training program has been effective. [2]
By considering a paired-experiment where the performance of the same individual
is recorded before and after training.

You might also like