Histogram Exercise – Support Beam Thickness

A quality engineer at a steering manufacturing company wants to inspect the process capability of the
process that manufacturers the steering column. According to the engineer, there is a difference in the
process capability between the day and night shifts. To support his claim, he measures the diameter of
five steering column samples out of 10 cartons from each shift. The design requirements state that the
steering column's diameter should be between 15.79 mm and 16.44 mm.

Interpretations of the histogram:

 From the histogram plot, one can observe that all the measured steering columns' diameters are
between 10.29 mm and 10.40 mm. Thus, all the steering columns meet the design requirement.
 From the histogram, one can roughly estimate the mean diameter to be around 16.34 mm. The
design requirement is that the diameter should be between 15.79 mm and 16.44 mm, which means
the desired process average is 16.12 mm (mean of the limits). Thus, one can say that the process is
not centered between the design requirements.

Attribution: The following exercises and data sets have been taken from
Minitab’s “Data Set Library” at https://support.minitab.com/en-us/datasets/
Box Plot Exercise – Support Beam Thickness by Shift

Interpretations of the box plot:

 From the box plot, one can infer that the variability is higher in shift 2 as its inter-quartile range is
higher.
o Shift 1: Inter-quartile range = 0.03
o Shift 2: Inter-quartile range = 0.0325
 Steering column diameter from shift 1 and shift 2 have the following medians,
o Shift 1: Median = 16.35 mm
o Shift 2: Median = 16.34 mm
 Both the shifts produce steering columns that meet the design requirements (15.79 mm to 16.44
mm).
 No potential outliers are present in any shift.

Attribution: The following exercises and data sets have been taken from
Minitab’s “Data Set Library” at https://support.minitab.com/en-us/datasets/
Graphical Summary Exercise – Support Beam Thickness

Interpretations of Graphical summary report:

 The mean steering column diameter is 16.342 mm, with a standard deviation of 0.023 mm.
 The 95% confidence interval for means shows that a likely range for the steering column diameter is
16.337 mm to 16.346 mm.

According to the 95% confidence interval for the mean, most columns will stratify the design
requirements.

Normality Test Exercise – MPG

Attribution: The following exercises and data sets have been taken from
Minitab’s “Data Set Library” at https://support.minitab.com/en-us/datasets/
An engineering economist wants to determine if the average fuel economy of IC engine powered vehicles
has changed from the previous year. He randomly samples 25 vehicle manufacturers and records their
fleet fuel economy for the current year. Last year, the mean fuel economy was 20 MPG. The economist
should determine if the data is normal or not before doing any statistical comparison tests. Use the
Normality.MTW data file to determine if the data are normally distributed.

State your interpretation to include your null hypothesis, the alternate hypothesis, and your conclusion
about whether you reject or fail to reject, thereby concluding the data to be normal or not. Use the
Anderson-Darling test option.

Solution:

Null Hypothesis ( H o ): The MPG for the vehicles is normally distributed.

Alternative Hypothesis ( H a ): The MPG for the vehicles is not normally distributed.

Conclusions:

We fail to reject the null hypothesis since the p-value of the normality test is 0.640 (greater than 0.05) and
claim that the data is normally distributed.

Attribution: The following exercises and data sets have been taken from
Minitab’s “Data Set Library” at https://support.minitab.com/en-us/datasets/
The mean MPG of the IC engine powered vehicles has changed to 24.93 MPG; however, one should
confirm it with statistical comparison tests.

Scatterplot Exercise – Body Fat Percentage

A medical researcher studies obesity in engineering students at a local university. Because body fat
percentage is difficult and expensive to measure directly, the researcher wants to determine whether the
body mass index (BMI), a more straightforward measurement that is easy to take, will be a good
predictor of body fat percentage. The researcher collects BMI, body fat percentage, and other personal
variables of 92 engineering students at Clemson University. Use the Scatterplot.MTW data to run a
scatterplot on %Fat vs. BMI. Clearly state your conclusions.

Solution:

Conclusion:

Attribution: The following exercises and data sets have been taken from
Minitab’s “Data Set Library” at https://support.minitab.com/en-us/datasets/
From the scatter plot, one can observe a relation between the BMI and % Fat data. A student with a
lower BMI has lower %Fat and vice versa. Thus, the medical researcher can use BMI as an indicator of
%Fat, since BMI is a good measure of % body fat.

Run Chart Exercise – Stock Price

A business analyst is examining the revenues of two transmission manufacturing companies over the
past 24 months, intending to create a visual chart that shows the revenue performance of both
companies over the period. Use the Run_Chart.MTW data set to present a run chart for each company’s
revenue. Clearly state your conclusions.

Solution:

Attribution: The following exercises and data sets have been taken from
Minitab’s “Data Set Library” at https://support.minitab.com/en-us/datasets/
Conclusion:

From the Run Chart of Company A’s Revenue, one can observe that its revenue has risen over the past 24
months, even though it had some ups and downs. The revenue of Company B shows a similar trend.
However, the revenue of Company B has increased more than that of Company A.

Attribution: The following exercises and data sets have been taken from
Minitab’s “Data Set Library” at https://support.minitab.com/en-us/datasets/