0% found this document useful (0 votes)
32 views14 pages

QCAR LAb Exam Key

The document discusses various statistical analyses conducted by managers in different industries, including confidence intervals, variance comparisons, control charts, and capability analyses. It covers specific scenarios such as car rentals, gasket thickness, investment percentages, customer returns, and assembly times, providing methods, results, and conclusions for each case. The findings indicate whether processes are in control, the effectiveness of advertising campaigns, and the normality of data distributions.

Uploaded by

Ranjith Rao
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
32 views14 pages

QCAR LAb Exam Key

The document discusses various statistical analyses conducted by managers in different industries, including confidence intervals, variance comparisons, control charts, and capability analyses. It covers specific scenarios such as car rentals, gasket thickness, investment percentages, customer returns, and assembly times, providing methods, results, and conclusions for each case. The findings indicate whether processes are in control, the effectiveness of advertising campaigns, and the normality of data distributions.

Uploaded by

Ranjith Rao
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 14

1.

a) The manager of a car rental company wants to estimate the average number of times luxury
cars would be rented a month. She takes a random sample of 19 cars that produces the following
number of times those cars are rented in a month. Result: 3, 7, 12,
12, 5, 9, 13, 2, 8, 6, 14, 6, 1, 2, 3,
2, 5, 11, 13, 5 She wants to use these data to construct a 95 percent confidence interval to
estimate the average. Construct the confidence interval for the mean. (5M) b) Kolda Automotive
receives gaskets for its enginess from two suppliers. The QA manager wants to compare the
variance in thickness of the gaskets with α = 0.05. He takes a sample of 10 gaskets from supplier
A and 12 from supplier B and obtains a standard deviation of 0.087 from A and 0.092 from B.
Commentonthe
nthe variance of thickness of the gaskets supplied by the both the suppliers. (5M

a) Identifying the correct method: 1M


Correct Input – 1M

Correct Answer – 2M

If the method is wrong, mark completely ZERO

b) Identifying the correct method: 1M


Correct Input – 1M

Correct Hypothesis – 1M
1M; Correct Result – 2 M
Conclusion – 1 M
Since p – value (0.881) > alpha (0.05), the null hypothesis cannot be rejected. There is no statistically
significant evidence that there is difference between the variances of the thickness of the gaskets supplied
by the both the suppliers.

2. The data in the Table represents the temperature of two rooms in Fahrenheit: one was built
with metal door and window frames and the other one without any metal.

a) Construct the Box Plots (6M)

b) What is the five point summary for each box plot. (2M)

c) Compare the plots and comment on the distribution of the plots, outliers and the temperature
difference between the rooms. (2M)

Correct Box Plots: 6M

a) ) Five-point
point summary – 2M

(c ) Correct Answer – 2M
With metal: Left Skewed
Without metal:
Left Skewed,
One outlier was found in the box plot of data with metal. It can be due to the error
in the measurement.

The reduction in the room temperature when a metal door is not used is more
m as
compared to the room using a metal door.

Percentage investment in new-product


product development is monitored for a pharmaceutical company,
by quarter. The observations are listed row – wise:
a) Can we conclude that the sequence of investment percentages is random? Use α = 0.05.
b) Is there clustering? Is there a trend? Use α = 0.05.
c) Can you conclude that the distribution of investment percentages is normal? Use α =
0.01.
Correct Run chart: 7M

If the chart has been done column wise: 5 M

b) Can we conclude that the sequence of investment percentages is random? Use α = 0.05.
(1 M)
Since the number of runs about the median is not equal to expected number of runs, we can
conclude that data is not random. There might be patterns present in the data.
(b) Is there clustering? Is there a trend? Use α = 0.05. (1M)
Since P- value for clustering (0.032) is less than alpha, clustering is present in the data.
P- value for trends (0.117) is greater than alpha, trends is not present in the data.
(c ) Can you conclude that the distribution of investment percentages is normal? Use α
= 0.01. (1M)
Since the data is not random, we can conclude that the data is not normally distributed.
Below table shows the area inspected of a bond paper produced and the number of flaws for 30
samples
a) Construct an appropriate control chart. 5M b) Is the process under control? If not, what are the
special causes? If the process is not under control, what are the revised control limits?2M c)
What are the 1σ and 2 σ control limits for the process? 3M d) Is there any trend or clustering or
any other phenomenon that can be observed in the control chart? 2
a) Correct chart selection – 2M
Correct chart – 3M

b) Is the process under control? If not, what are the special causes? If the process is
not under control, what are the revised control limits? 2 M
c) What are the 1σ and 2 σ control limits for the process? 2M

d) Is there any trend or clustering or any other phenomenon that can be observed in
the control chart? 1 M
There are no trends or clusters found in the data.
It can be confirmed with run chart. (NOT MANDATORY)

The waiting time in minutes before being served in a local post office is observed for 50
randomly chosen customers:
(a) Test for normality using a = 0.05. What inferences can you draw? (3M)
(b) Verify whether the process is in control or not? (3M)
(c) If the goal of the post office is for the waiting time not to exceed 4 minutes with tolerance as
±1 minute , perform the process capability analysis and the capability of the process.(4M)
17th – 5 PM; 18th_ 2 PM Question
a) Correct Plot – 2 M

Conclusion – 1M
Since P – value (0.129) > alpha (0.05) , Null hypothesis cannot be rejected. The data is normally
distributed.

a) Control Chart - 2M

b) Capability Analysis – 2M
Correct answer and Conclusion -2M
Since all the capability indices are less than 1, the process is not capable of meeting the customer
specifications/ requirements.
1A ) The data given in the table below was gathered during a period of one month to analyze the
reasons behind a high volume of customer returns of cellular phones ordered.
Construct a Pareto Chart and comment on the out
outcome.(5M)
b) b)A random sample of 50 observations on the waiting time (in seconds) of customers before
speaking to a representative at a call center is as follows:
Construct a Histogram with fitting curve and comment on the distribution. (5M)

a)

As per the Pareto Chart, if the issue of Misinformed about the contract is addressed first, almost
60% of the customer returns of the phones can be avoided.

Give 4 M – if the Pareto Chart is correct.

1M – for conclusion statement

If total is considered in constructing the Pareto Chart – Deduct 1M for Pareto Chart.

b) Stacking of the Data - 1 M

Correct Histogram – 3M
If Histogram is drawn without curve – 2M

Conclusion – 1M

The data is not symmetrical. It is positively skewed, since the right tail is longer.

The mean time to assemble a product as found from a sample of size 40 is 10.4 minutes. The
standard deviation of the assembly times is known to be 1.2 minutes.
(a) Find a two-sided
sided 90% confidence interval for the mean assembly time, and interpret it.
(b) The manager in charge of the assembly line believes that the mean assembly time is less than
10.8 min. Can he make this conclusion at a significance level of 0.
0.05?
Since p < alpha, we cannot accept the null hypothesis. The claim of the
manager that the mean assembly time is less than 10.8 min can be
accepted.,
(a) Find the control limits for the 𝑋 − 𝑅 charts: Correct chart - 8 M

(b) Assuming special causes for out


out-of-control
control points, find the revised control limits. 2M
As all the points are well within control limits, there are no special causes present.

19th 5- 7PM
a) An advertising agency is judged by the increase in the proportion of people
who buy a particular product after the advertising campaign is conducted. In a
random sample of 200 people prior to the campaign, 40 said that they prefer
the product in question. After the advertising campaign, out of a random
sample of 300, 80 say they prefer the product.
• Find a 90% confidence interval for the difference in the proportion
of people who prefer the stipulated product before and after the
advertising campaign.
• Can
n you conclude that the advertising campaign has been
successful in increasing the proportion of people who prefer the
product? Use a level of significance of 0.10.
b)

20th 5 -7 AM
A component part for a jet aircraft engine is manufactured by an investment casting process. The
vane opening on this casting is an important functional parameter of the part. Table (Check the
excel sheet) presents 20 samples of five parts each. The specification for the vane spacing is 35
± 2 mm.
• Perform Capability Analysis and comment on the capability of the process.
a)

b)

Since all the observations are within the control limits, the process is under statistical control.

c)

Since all the indices are less than 1, we can conclude that the process is not capable of
meeting customer requirements.
ABC bicycle parts manufacturer produces precision ball bearings for bicycles. The
Quality manager was checking the output of the 5mm bearings used in wheel hubs. From each
batch, he has sampled 5 bearings with the following results.
a) Identify and construct an appropriate control chart for the above data to help the
manager to determine whether the process is in control or not. (6M)

Correct chart selection – 2M; Correct chart – 3M

b) Is the process under control? If not, what could be the special cause for the process to go
out of control? (1M)

No, The process is out of control at the point 10.

The finishing of the individual parts, concentricity of the rings etc.

d) If the process is not under control, what are the revised control limits after bringing it in
control? (1M)
d) What are the 1sigma and 2 sigma control limits for the revised chart? 1M

You might also like