12.52 Enlighten management.
A manager who knows no statistics asks you, “What does it mean to say that a process is in control? Is being in control a guarantee that the quality of the product is good?” Answer these questions in plain language that the manager can understand.
12.53 Pareto charts.
You manage the customer service operation for a maker of electronic equipment sold to business customers. Traditionally, the most common complaint is that equipment does not operate properly when installed, but attention to manufacturing and installation quality will reduce these complaints. You hire an outside firm to conduct a sample survey of your customers. Here are the percent of customers with each of several kinds of complaints:
Category | Percent |
Accuracy of invoices | 25 |
Clarity of operating manual | 8 |
Complete invoice | 24 |
Complete shipment | 16 |
Correct equipment shipped | 15 |
Ease of obtaining invoice adjustments/credits | 33 |
Equipment operates when installed | 6 |
Meeting promised delivery date | 11 |
Sales rep returns calls | 4 |
Technical competence of sales rep | 12 |
12.53
(a) The customers could make 0 or many complaints, not just 1. (b) The three biggest complaints are problems with invoices, so that should be the focus.
640
12.54 Purchased material.
At the present time, about five out of every 1000 lots of material arriving at a plant site from outside vendors are rejected because they are incorrect. The plant receives about 300 lots per week. As part of an effort to reduce errors in the system of placing and filling orders, you will monitor the proportion of rejected lots each week. What type of control chart will you use? What are the initial center line and control limits?
You have just installed a new system that uses an interferometer to measure the thickness of polystyrene film. To control the thickness, you plan to measure three film specimens every 10 minutes and keep and s charts. To establish control you measure 22 samples of three films each at 10-minute intervals. Table 12.11 gives and s for these samples. The units are millimeters . Exercises 12.55 through 12.57 are based on this process improvement setting.
12.55 chart.
Calculate control limits for s, make an chart, and comment on control of short-term process variation.
12.55
, using and . The first sample is out of control.
film
12.56 chart.
Interviews with the operators reveal that in Samples 1 and 10, mistakes in operating the interferometer resulted in one high-outlier thickness reading that was clearly incorrect. Recalculate after removing Samples 1 and 10. Recalculate UCL for the chart and add the new UCL to your chart from the previous exercise. Control for the remaining samples is excellent. Now find the appropriate center line and control limits for an chart, make the chart, and comment on control.
Sample | Sample | ||||
1 | 848 | 20.1 | 12 | 823 | 12.6 |
2 | 832 | 1.1 | 13 | 835 | 4.4 |
3 | 826 | 11.0 | 14 | 843 | 3.6 |
4 | 833 | 7.5 | 15 | 841 | 5.9 |
5 | 837 | 12.5 | 16 | 840 | 3.6 |
6 | 834 | 1.8 | 17 | 833 | 4.9 |
7 | 834 | 1.3 | 18 | 840 | 8.0 |
8 | 838 | 7.4 | 19 | 826 | 6.1 |
9 | 835 | 2.1 | 20 | 839 | 10.2 |
10 | 852 | 18.9 | 21 | 836 | 14.8 |
11 | 836 | 3.8 | 22 | 829 | 6.7 |
film
12.57 Categorizing the output.
Previously, control of the process was based on categorizing the thickness of each film inspected as satisfactory or not. Steady improvement in process quality has occurred, so that just 15 of the last 5000 films inspected were unsatisfactory.
12.57
(a) A chart would be appropriate. , so use 0. (b) The chance of an unsatisfactory film is so small that we only expect 0.3 in each sample of 100. But if a sample has 2 defects, is already over than the UCL and would signal an out-of-control process, which isn’t true.
12.58 Hospital losses revisited.
Refer to Exercise 12.14 (page 614), in which you were asked to construct and charts for the hospital losses data shown in Table 12.4.
hloss
12.59 Bone density revisited.
Refer to Exercise 12.26 (page 627), in which you were asked to construct and charts for the calibration data from a Lunar bone densitometer shown in Table 12.6.
bone
12.59
(a) , using and .
(b) For . The process is in control.
12.60 Even more signals.
There are other out-of-control signals that are sometimes used with charts. One is “15 points in a row within the level.” That is, 15 consecutive points fall between and . This signal suggests either that the value of used for the chart is too large or that careless measurement is producing results that are suspiciously close to the target. Find the probability that the next 15 points will give this signal when the process remains in control with the given and .
12.61 It's all in the wrist.
Consider the saga of a professional basketball player plagued with poor free-throw shooting performance. Here are the number of free throws he made out of 50 attempts on 20 consecutive practice days (read left to right):
fthrow
25 | 27 | 31 | 28 | 22 | 21 | 27 | 20 | 25 | 27 |
23 | 22 | 29 | 34 | 30 | 27 | 26 | 25 | 28 | 25 |
641
34 | 38 | 35 | 43 | 31 | 35 | 32 | 36 | 28 | 39 |
Plot the new sample proportions along with the control limits determined in part (a). What are your conclusions? What should be the values of the control limits for future samples?
12.61
(a) . The process is in control. (b) The process appears out of control because the process mean has shifted. The new control limits are .
12.62 Monitoring rare events.
In certain SPC applications, we are concerned with monitoring the occurrence of events that can occur at any point within a continuous interval of time, such as the number of computer operator errors per day or plant injuries per month. However, for highly capable processes, the occurrence of events is rare. As a result, the data will plot as many strings of zeros with an occasional nonzero observation. Under such circumstances, a control chart will be fairly useless. In light of this issue, SPC practitioners monitor the time between successive events—for example, the time between accidental contaminated needle sticks in a health care setting. For this exercise, consider data on the time between fatal commercial airline accidents worldwide between January 1995 and August 2013.11
afatal
12.63 Monitoring budgets.
Control charts are used for a wide variety of applications in business. In the accounting area, control charts can be used to monitor budget variances. A budget variance is the difference between planned spending and actual spending for a given time period. Often, budget variances are measured in percents. For improved budget planning, it is important to identify unusual variances on both the low and high sides. The data file for this exercise includes variance percents for 40 consecutive weeks for a manufacturing work center.
budget
12.63
(a) . Subgroup 5 is out of control, below the LCL. (b) Subgroups 20 to 28 are all above the CL, violating the nine-in-a-row rule. (c) The process is now in control, and there are no out of control signals. . (d) The MR chart shows the process is in control.
12.64 Is it really Poisson?
Certain manufacturing environments, such as semiconductor manufacturing and biotechnology, require a low level of environmental pollutants (for example, dust, airborne microbes, and aerosol particles). For such industries, manufacturing occurs in ultraclean environments known as cleanrooms. There are federal and international classifications of cleanrooms that specify the maximum number of pollutants of a particular size allowed per volume of air. Consider a manufacturer of integrated circuits. One cubic meter of air is sampled at constant intervals of time, and the number of pollutants of size 0.3 microns or larger is recorded. Here are the count data for 25 consecutive samples (read left to right):
clean
642
7 | 3 | 13 | 1 | 17 | 3 | 6 | 9 | 12 | 5 | 5 | 0 | 6 |
2 | 9 | 1 | 12 | 2 | 3 | 3 | 7 | 5 | 0 | 3 | 13 |