INDIVIDUAL ASSIGNMENT 2

MAS202
Business Statistics
Your full name : Trần Nguyễn Phúc Nguyện
Nguyện
RollNumber:CS171285
Class:BA1703

SCENARIO 1: A company producing orange juice buys all its oranges from a large orange
orchard. The amount of juice that can be squeezed from each of these oranges is
approximately normally distributed with a mean of 4.7 ounces and some unknown standard
deviation. The company’s production manager knows that the probability is 30.85% that a
randomly selected orange will contain less than 4.5 ounces of juice.

1. Using the function NORM.S.INV in Mircosoft Excel to estimate 𝜎

where 𝑛 is the
sample
size used by company’s production manager.
P(X<4.5)= 30.85% or P(X<4.5)= 0.3085
=> Z value at 0.3085 = -0.5001 
Calculate the population standard deviation:

<=>-0.5001=(4.5-4.7)/ standard deviation

=> standard deviation=0.4

2. What is the probability that a randomly selected orange will contain between 4.5 and 5.2
ounces of juices?

1
P(4.5<X<5.2)=((4.5-4.7)/0.4)<Z<((5.2-4.7)/0.4)=P(-0.5<Z<1.25)
P(4.5<Z<5.2)=P(Z<1.25)-P(Z<0.5)=0.8944-0.3085=0.5859
3. What is the probability that a randomly selected orange will contain between 4.2 and 4.9
ounces of juices?
P(4.2<X<4.9)=((4.2-4.7)/0.4)<Z<((4.9-4.7)/0.4)=P(-1.25<Z<0.5)

P(4.2<X<4.9)=P(Z<0.5)-P(Z<-1.25)=0.6915-0.1056=0.5859

4. What is the probability that a randomly selected orange will contain at least 4.9 ounces of
juices?

P(X≥4.9)=P(X≥(4.9-4.7)/0.4)(=)P(Z≥0.5)=1- P(X≤4.9)
P(Z≥0.5)= 1-P(Z≤0.5)=1-0.6915=0.3085

5.What is the probability that a randomly selected orange will contain more than 4.2 ounces
of juices?

P(X>4.2)(=)P(Z>4.2-4.7)/0.4)(=)P(Z>-1.25)
P(X>4.2)=1-P(X≤4.2)
(=)P(Z>-1.25)=1- P(X≤-1.25)=1-0.1056=0.8944

SCENARIO 2: The time spent studying by students in the week before final exams follows
a normal distribution with a standard deviation of 8 hours. A random sample of 4 students
was taken to estimate the mean study time for the population of all students.
1. What is the probability that the sample mean exceeds the population mean by more than 2
hours?
The formula for the probability distribution of the sample mean is:

2
We can use a standard normal distribution to find the probabilities of different z-scores,
which are standardized values of the sample mean. The formula for z-score is:

Find the probability that the sample mean exceeds the population mean by more than 2
hours, we need to find the z-score that corresponds to 2 hours above the population mean:

The probability that z is less than this value, which is the area under the curve to the left of
this point. We can subtract this probability from 1 to get the probability that z is greater than
this value, which is the area under the curve to the right of this point. That is:

We have standard deviation of 8 hours,n=4

 There is about a 30.85% chance that the sample mean exceeds the population mean by more
than 2 hours.
2. What is the probability that the sample mean is more than 3 hours below the population
mean?
We need to find the z-score that corresponds to 3 hours below the population mean:

We can find the probability that z is less than this value, which is the area under the curve to
the left of this point. That is:

We have standard deviation of 8 hours,n=4

So there is about a 22.66% chance that the sample mean is more than 3 hours below the
population mean

3
3. What is the probability that the sample mean differs from the population mean by less
than 2 hours?

 we need to find the z-scores that correspond to 2 hours above and below the population
mean. That is:

So

if n=4 and σ=8, then

So there is about a 38.30% chance that the sample mean differs from the population mean by
less than 2 hours.

SCENARIO 3: The lifetimes of a certain brand of light bulbs are known to be

normally distributed with a mean of 1,600 hours and a standard deviation of 400 hours. A
random sample of 64 of these light bulbs is taken.
1. What is the probability that the sample mean lifetime is more than 1,550
hours?
Answer:

Z= (Sample mean -Population mean ) / (Standard deviation / Sqrt(n)) = (1,550

- 1,600)/(400/Sqrt(64)=-1
  P(sample mean ≤1,550) = P(Z ≤ -1) = 0.1587
=> P(Sample mean>1,550) = 1 - P(Sample mean≤ 1,550) = 1 - 0.1587 = 0.8413

There is an 84.13% chance that the sample mean lifetime is more than 1,550 hours.
2. The probability is 0.15 that the sample mean lifetime is more than how many
hours?
Because The probability is 0.15 that the sample mean lifetime is more than so -1.04
will be 1.04

4
   Z=1.04=(Sample mean – population mean ) / (Standard devitaion /Sqrt(n)
  Sample mean = Z(standard deviation / Sqrt(n) +population mean = 1.04(400 /
sqrt(64 )) + 1600 = 1,652
Therefore, the probability is 0.15 that the sample mean lifetime is more than 1652
hours.

3. The probability is 0.20 that the sample mean lifetime differs from the
population mean lifetime by at least how many hours?

According to the Central Limit Theorem, for samples of size 30 or more, the sample mean is

approximately normally distributed, with mean       and standard

deviation                   

Therefore, the sample mean is approximately normally distributed with mean: 1600

and standard deviation:                        

We want to find the value of d such that                                    

This means that the probability of the sample mean being more than d hours away
from the population mean is 0.20. 

Using the formula:                          

P(IzI ≥d/50) = 0.20

Using table E.2 find that z ≈ 1.28. Therefore, we have                  

=> d = 64

So, the sample mean lifetime differs from the population mean lifetime by at least 64
hours with a probability of 0.20.

5
SCENARIO 4:
1. A quality control engineer is interested in the mean length of sheet
insulation being cut automatically by machine. The desired mean length of the
insulation is 12 feet. It is known that the standard deviation in the cutting length is
0.15 feet. A sample of 70 cut sheets yields a mean length of 12.14 feet. This sample
will be used to obtain a 99% confidence interval for the mean length cut by machine.
Determine this confidence interval?

x is the sample mean, zα/2 is the critical value for the standard normal distribution

Therefore, the 99% confidence interval for the mean length cut by machine is
(12.094, 12.186) feet.

2. To become an actuary, it is necessary to pass a series of 10 exams,

including the most important one, an exam in probability and statistics. An insurance
company wants to estimate the mean score on this exam for actuarial students who
have enrolled in a special study program. They take a sample of 8 actuarial students
in this program and determine that their scores are: 2, 5, 8, 8, 7, 6, 5, and 7. This
sample will be used to calculate a 90% confidence interval for the mean score for
actuarial students in the special study program. Determine this confidence interval?

Given scores: 2, 5, 8, 8, 7, 6, 5, and 7 => n = 8 (sample size)

Sample mean x̄ = (2 + 5 + 8 + 8 + 7 + 6 + 5 + 7) / 8 = 48 / 8 = 6

To calculate a 90% confidence interval for the mean score for actuarial students in the
special study program, and we don’t know standard deviation,so:

6
 where x̄ is the sample mean, tα/2,n−1 is the critical value for the t-distribution with
n−1 degrees of freedom corresponding to a significance level of α

We need to calculate the standard deviation from the given data. 

For a 90% confidence interval, the t-score (since the sample size is less than 30) for 7
degrees of freedom is approximately 1.895.

Therefore, the 90% confidence interval for the mean score for actuarial students in the
special study program is (4.661 , 7.339)

SCENARIO 5:
1. A university dean is interested in determining the proportion of students
who receive some sort of financial aid. Rather than examine the records for all
students, the dean randomly selects 200 students and finds that 118 of them are
receiving financial aid. Use a 90% confidence interval to estimate the true proportion
of students who receive financial aid.

1 - α = 0.9
=>α = 1 - 0.9 = 0.1

7
 =>α /2 = 1/2 = 0.05
Using the formula:
p ± Zα/2*SQrt(p(1-p)/n)
           = 118/200± 1.65*Sqrt(118/200(1-118/200)200)
          = 0.59± 1.65*Sqrt(0.59(1-0.59)/200)
           =0.59±0.057
          0.533 ≤pi≤ 0.647
2. The head of a computer science department is interested in estimating
the proportion of students entering the department who will choose the new computer
engineering option.
Suppose there is no information about the proportion of students who might choose the
option. What size sample should the department head take if she wants to be 95% confident
that the estimate is within 0.10 of the true proportion?
p is the expected proportion. If we have no information about the proportion,
we can use p = 0.5 as a conservative estimate.
error e = 0.10
Significance level α = 0.05
The critical value:
Z/2 = 1.96 for a 95% confidence level

Sample size = n = p*(1- p)*(Zα/2/e)^2

n = 0.5(1 - 0.5)(1.96/0.10)^2
n = 96

So, the department head should take a sample of 96 students if she wants to be 95%
confident that the estimate is within 0.10 of the true proportion.

SCENARIO 6:

A poll was conducted by the marketing department of a video game company to

determine the popularity of a new game that was targeted to be launched in three months.
Telephone interviews with 1,500 young adults were conducted which revealed that 49% said
they would purchase the new game. The margin of error was ±3 percentage points.

1. What is the sampling error?

8
 The difference between the sample result and the true population value it
represents.  The sample result is 49% who said they would purchase the new
game. Since the margin of error is ±3 percentage points, the sampling error
would be ±3 percentage points

2. What is the needed sample size to obtain a 95% confidence interval

estimate of the percentage of the targeted young adults who will purchase the new
game by allowing the same level of margin of error?

Calculate the needed sample size to obtain a 95% confidence interval estimate with
the same level of margin of error, we can use the formula:

n is the sample size

Z is the Z-score (1.96 for a 95% confidence interval)

p is the estimated proportion (0.49 in this case)

e is the margin of error (0.03 in this case)

Since you cannot have a fraction of a person, you would round up to the nearest whole
number. So, the required sample size is approximately 1067 young adults.

3. What is the needed sample size to obtain a 95% confidence interval in

estimating the percentage of the targeted young adults who will purchase the new
game to within±5% if you do not have the information on the 49% in the interviews
who said that they would purchase the new game?

9
Without information on the 49%, So,use a worst-case scenario for p. The worst-case
scenario would be p = 0.5 (50%), which provides the maximum sample size required.

The needed sample size to obtain a 95% confidence interval estimate within ±5% without
information on the proportion of young adults who will purchase the new game is 384.

SCENARIO 7:
The Three Brothers Energy Drink Company bottles and distributes a popular drink for
athletes and exercise enthusiasts. Because of its marketing successes the company has
installed an additional filling machine and the managers are eager to use it in daily
operations. The machine is set to fill bottles at 16 oz. However, we know there is inherent
machine variability and quality control has determined through testing a mean of 16.2 oz.
and a standard deviation of 0.3 oz. using a 100 bottle sample.
1. In calculating a 90% confidence interval for the population what would
be the sampling error?

 Zα/2 = 1.645 for a 90% confidence level

Using formula:

Sampling error=e=Zα/2*(α/n)
(=)e=1.645*(0.3/sqrt(100)
e=0.04935
  So, the sampling error for a 90% confidence interval is 0.04935 oz.        
sampling error
2. Find a 90% confidence interval for the mean volume of the filled bottle
contents

10
Confidence interval = sample mean± Zα/2*(α/sqrt(n))

= 16.2  1.6450.3100

= 16.2 ± 0.04935

= (16.15065 and16.24935)

So, a 90% confidence interval for the mean volume is (16.15065 oz and16.24935 oz).

3. Suppose you want to estimate the population mean fill with 95%
confidence and 0.04 oz. sampling error rate. What should be your sample size?
n = (Zα/2)^2*α^2/e^2 = 1.96^2*0.3^2/0.04^2 = 216
The required sample size is 216.

SCENARIO 8:
An appliance manufacturer claims to have developed a compact microwave oven that
consumes a mean of no more than 250 W. From previous studies, it is believed that power
consumption for microwave ovens is normally distributed with a population standard
deviation of 15 W. A consumer group has decided to try to discover if the claim appears true.
They take a sample of 20 microwave ovens and find that they consume a mean of 257.3 W
1. What is the parameter of interest?
Answer:
An appliance manufacturer claims to have developed a compact microwave oven that
consumes a mean of no more than 250 W. From previous studies, it is believed that power
consumption for microwave ovens is normally distributed with a population standard
deviation of 15 W. A consumer group has decided to try to discover if the claim appears
true. They take a sample of 20 microwave ovens and find that they consume a mean of
257.3 W
1. What is the parameter of interest?
Answer:
The parameter of interest in this scenario is the mean power consumption of the compact
microwave ovens produced by the manufacturer.

11
2. Can the consumer group conclude that there is enough evidence that the manufacturer’s
claim is not true when allowing for a 5% probability of committing a Type I error?
To determine if the consumer group can conclude that there is enough evidence to reject the
manufacturer's claim, we can conduct a hypothesis test.

The null hypothesis (H0) is that the mean power consumption of the compact microwave
ovens ≤ 250 W
The alternative hypothesis (H1) is that the mean power consumption of the compact
microwave ovens is greater than >250 W.

Since the sample size (n = 20) is reasonably large and the population standard deviation (σ =
15 W) is known, we can use a z-test.

First, we calculate the test statistic (z-score) using the formula:

z = (sample mean - population mean) / (population standard deviation / sqrt(sample size))
z = (257.3 - 250) / (15 / sqrt(20))
z = 7.3 / (15 / 4.472)
z ≈ 7.3 / 3.355
z ≈ 2.17

Next, we compare the calculated z-score with the critical value from the standard normal
distribution. For a 5% significance level (α = 0.05) and a one-tailed test, the critical z-value
is approximately 1.645 (obtained from a z-table or calculator).

12
Since the calculated z-score (2.17) is greater than the critical z-value (1.645), we reject the
null hypothesis.

Therefore, the consumer group can conclude that there is enough evidence to suggest that
the manufacturer's claim is not true

SCENARIO 9:
One of the biggest issues facing e-retailers is the ability to turn browsers into buyers.
This is measured by the conversion rate, the percentage of browsers who buy something in
their visit to a site. The conversion rate for a company’s website was 10.1%. The website at
the company was redesigned in an attempt to increase its conversion rates. A sample of 200
browsers at the redesigned site was selected. Suppose that 24 browsers made a purchase. The
company officials would like to know if there is evidence of an increase in conversion rate at
the 5% level of significance.
1. What critical value should the company officials use to determine the rejection
region?

Null hypothesis (H0): The conversion rate after the website redesign is the same as
before or lower.
Alternative hypothesis (H1): The conversion rate after the website redesign is
higher than before.
So will use a one-tailed test.n=200

Upper tail of the t distribution contains an area of 0.05, the critical value of the t
distribution with d.f = 200 - 1 = 199 degrees of freedom is approximately 1.645.

The critical value should the company officials use to determine the rejection
region: 1.645
2. Is it true if the company officials can conclude that there is sufficient evidence
that the conversion rate at the company’s website has increased using a level of
significance of 0.05? Sample mean=0.12;population mean=0.101

13
 Since 0.89 < 1.645 we fail to reject H0 and conclude that the increase is not
significant.
3. What will be the p-value if these data were used to perform a two-tail test?

H0: = 0.101 
H1: # 0.101
n = 200. Decided to use α/2 = 2.5% or 0.025

Z ≈ 0.8917

To find the p-value for a two-tailed test, we need to calculate the probability of observing a
test statistic as extreme as 0.8917 or more extreme in either tail of the standard normal
distribution.

Using a standard normal distribution table or statistical software, we find that the probability
of getting a Z-statistic greater than 0.8917 is approximately 0.1871. Since this is a two-tailed
test, we need to double this probability.

Therefore, the p-value for this two-tailed test is approximately 2 * 0.1871 = 0.3742.

Since the p-value (0.3742) is greater than the significance level (α = 0.05), we do not reject
the null hypothesis. There is not enough evidence to conclude that the conversion rate has
increased after the website redesign

SCENARIO 10:
The president of a university claimed that the entering class this year appeared to be
larger than the entering class from previous years but their mean SAT score is lower than
previous years. He took a sample of 20 of this year’s entering students and found that their
mean SAT score is 1,501 with a standard deviation of 53. The university’s record indicates

14
that the mean SAT score for entering students from previous years is 1,520. He wants to find
out if his claim is supported by the evidence at a 5% level of significance. Please help him.
Because we have a standard deviation =53 is know so we use the Z-score test:

Sample mean (x̄) = 1,501

Sample standard deviation (S) = 53
Population mean (μ) = 1,520
Sample size (n) = 20
Significance level (α) = 0.05

The null hypothesis (H0) is that the mean SAT score for this year's entering class is
equal to or “≥” the mean SAT score for previous years.
The alternative hypothesis (H1) is that the mean SAT score for this year's entering class
is “<” the mean SAT score for previous years.
So we use 1 tailed
We can calculate the test statistic (t-score) using the formula:
t = (sample mean - population mean) / (sample standard deviation / sqrt(sample size))
t = (1,501 - 1,520) / (53 / sqrt(20))
t = -19 / (53 / 4.472)
t ≈ -19 / 11.819
t ≈ -1.61

Next, we determine the critical t-value for a one-tailed test at a 5% significance level
and 19 degrees of freedom (n - 1 = 20 - 1 = 19). Using a t-table or calculator, the critical t-
value is approximately -1.729.
Since the calculated t-score (-1.61) is > the critical t-value (-1.729), we fail to reject the null
hypothesis.

15
 Therefore, based on the evidence at a 5% level of significance, we do not have enough
evidence to support the claim that the mean SAT score for this year's entering class is lower
than the mean SAT score for previous years

16