In the Measure phase of DMAIC, what are the items needed?

A)

A solution to the problem.

B)

Data for doing a Design of Experiments.

C)

Data to help break down the problem.

D)

A problem, a process, a financial benefit, a metric and a goal, and a customer metric.

E)

A valid measurement system.

2

In the Measure phase, we are going to establish a defect rate, but black belts typically see the defect rate go down.

A)

True

B)

False

3

What is one of the first important milestones that indicates that a black belt is on track?

A)

Lack of buy-in from the team members.

B)

No data is available.

C)

The champion does not know the project benefit.

D)

The process map is complete.

E)

When the team adopts a desire to constantly learn

4

How many data points do you need to have a short-term capability?

A)

Two data points.

B)

Over 100 data points.

C)

Fewer than five data points.

D)

Between 30 and 50 data points.

5

Process mapping is a:

A)

A one-time event.

B)

A tool used for statistical validation.

C)

A tool used at the end of the DMAIC process.

D)

An ongoing living document used throughout the DMAIC process.

6

A failure modes and effects analysis FMEA describes the following.

A)

Potential defects

B)

The risk of the problem

C)

Capability of the process

D)

Root cause

E)

What you want to know about a type of defect

7

An FMEA is complete during the Measure phase.

A)

True

B)

False

8

In an FMEA, what is the RPN if POCC is 5, PDET is 4, and the PSEV is 9?

A)

0

B)

20

C)

9

D)

180

E)

None of the above

9

Measurement system analysis MSA is used:

A)

To assess capability

B)

To validate the data used for analysis

C)

As an optional tool during the DMAIC process

D)

A nonstatistical assessment of the process

10

MSA is a tool that can be omitted in the DMAIC model.

A)

True

B)

False

11

Cp is a capability index with the units measured in:

A)

Meters

B)

Gallons

C)

Yards

D)

Productivity

E)

Defect rate or yield

F)

No units

12

If the Cp is 1.0, what is the sigma value?

A)

1

B)

2

C)

3

D)

6

E)

None of above

13

Can Cp be greater than Cpk?

A)

Yes

B)

No

C)

Sometimes

14

What is the Cp and Cpk index number when you have a six-sigma capability?

A)

Cp = 1.0 and Cpk = 0.5

B)

Cp = 1.5 and Cpk = 2.0

C)

Cp = 3.0 and Cpk = 6.0

D)

Cp = 2.0, and Cpk = 1.5

E)

None of the above

15

What is the purpose for gauge R&R?

A)

Statistical analysis to evaluate measure error

B)

To understand repeatability and reproducibility of your MSA

C)

To help validate what is a defect and what is not
d. Look for variation within operator and between operators

D)

To gauge the rest and relaxation needed for a black belt

E)

a through d

F)

None of the above

16

If your data are nonnormal, you are stuck in the Measure phase.

A)

True

B)

False

17

What is the layperson’s description of a hypothesis test?

A)

Helps to solve problems

B)

Breaking the problem up

C)

Dissecting the data

D)

There is no way to make it simple

E)

A tool to compare stuff

18

What are the reasons for nonnormality?

A)

a. All data have that pattern

B)

Due to abnormal conditions

C)

Bimodal conditions exist

D)

Different normal distributions are within the data set

E)

a and d

F)

None of the above

G)

c and d

19

If you have a nonnormal data set, does transforming the data fix the nonnormal causes of the problem?

A)

Yes

B)

No

C)

None of the above

20

What would best describe a bimodal distribution?

A)

A manufacturing process

B)

Material variance

C)

Transactional defects

D)

Mutlivari chart

E)

Within-part variation

F)

An X-factor that has two different Y-output distributions

21

How does comparing factors help solve the problem?

A)

It breaks down the problem into the vital X’s.

B)

It contrasts the trivial many versus the vital few.

C)

It helps answer the hypothesis question.

D)

It deals with data facts that can be proven.

E)

It focuses the team on data, not opinion.

F)

All of the above

22

Tool wear can cause nonnormal distributions.

A)

True

B)

False

23

What plot describes the many distributions in one graph in quartiles?

A)

Interval plot

B)

Capability plot

C)

Probability plot

D)

Median plot

E)

Box plot

24

Is it okay to remove outliers in a data set that cause an increase in standard deviation?

A)

Yes

B)

No

C)

Yes, only if you know the cause of stopping it

D)

b and c

25

What is the best way to show multimode distributions?

A)

a. Bimodal graph

B)

b. Interval plot

C)

Dot plot

D)

One-way ANOVA

E)

Box plot

F)

a and b

G)

b through d

26

Lowess analysis fits a robust line through the data to display a relationship between X and Y.

A)

True

B)

False

27

In a multivari analysis, the X levels are randomly selected levels during the study.

A)

True

B)

False

28

Different operators producing the same Y cannot cause nonsymmetrical distributions:

A)

True

B)

False

29

Two-way interaction cannot cause asymmetrical distributions.

A)

True

B)

False

C)

Sometimes

D)

None of the above

30

In simple terms, what is meant by a p-value of less than 0.05?

A)

That there are no significant difference

B)

The variance terms are equal

C)

The mean has a shift of 1.5 sigma

D)

You’re 95 percent confident that there is a statistical difference

E)

All the above

31

The 95 percent confidence interval increases as the standard deviation decreases.

A)

True

B)

False

32

A multvari analysis is an active form of comparing within- and between-part variation over time.

A)

True

B)

False

33

You do not need a capable measurement system for multivari analysis.

A)

True

B)

False

34

Shift-to-shift variation can be measured on one shift.

A)

True

B)

False

35

A hypothesis test can show the interaction of the factors.

A)

True

B)

False

36

Sample size has no effect on the width of a distribution.

A)

True

B)

False

37

If an X has been identified as statistically significant, do you disregard it owing to an expert telling you to ignore it?

A)

No

B)

Yes

C)

Ask what data does the expert have to show to ignore it

D)

None of the above

E)

a and c

38

If you were told to purchase new technology for over $2 million to make the business more productive, but the hypothesis of the new technology shows no statistical difference in productivity, do you purchase it?

A)

No

B)

Yes

39

What does hypothesis testing fundamentally change?

A)

It’s a departure from the “I think” and “I feel” culture

B)

Destroys the emotions of the problem

C)

Turns the problem into a fact-based process

D)

Data are now used to drive decisions

E)

All of the above

40

If you changed an X that was proven to be statistically significant and the Y was given to you with 3 months prior to the change and 1 month after, could you show a before and after hypothesis to validate the change?

A)

No

B)

Yes

41

Using an Anderson-Darling normality test, normal data have a p-value of less than 0.5.

A)

True

B)

False

42

How many runs does a 2^{3} full factorial experiment consist of ?

A)

6

B)

5

C)

8

D)

12

43

In an experiment, inputs are allowed to vary randomly throughout the specification range.

A)

True

B)

False

44

One-factor-at-a-time experiments generate more powerful data than a full factorial experiment.

A)

True

B)

False

45

What is an experimental factor?

A)

The input variables for the experiment

B)

The metrics of the process

C)

A covariant

D)

The largest standard deviation

46

What does orthogonal mean?

A)

One or more effects that cannot unambiguously be attributed to a single factor or factor interaction

B)

Involves running the experimental runs in random order

C)

A property that ensures that all experimental factors are independent of each other; no correlation exists between X’s.

47

What is a “Balanced Design?”

A)

A design in which each of the variables has a different number of runs at the high and low levels

B)

A design in which each of the variables or factors has the same number of runs at the high and low levels

C)

A design in which two of the variables has a different number of runs at the high and low levels

D)

All of the above

48

Standard order is the same as run order.

A)

True

B)

False

49

Why use factorial plots?

A)

Allow you to see the plots of the main effects

B)

Allow you to see the interaction plots

C)

Allow you to see the cube plots

D)

Show how to set each factor to either maximize or minimize the response

E)

All of the above

50

What tools can be used to determine if factors have interaction?

A)

Balanced ANOVA

B)

Standardized effects

C)

Interaction plots

D)

Fractional factorial fits

E)

All of the above

51

What does it mean when no p-values are presented in the ANOVA output?

A)

Means the factors are statistically significant

B)

Means the factors are not different

C)

Only one repetition was run at each treatment combination

D)

Had no center points

E)

All of the above

52

Why do we replicate our experimental runs?

A)

So we can look for special causes

B)

To obtain a better estimate of the error and look at interactions

C)

To determine the factor levels

D)

So we can look at the same thing run again

53

To use a center point in your experimental design, at least one factor must be able to be set at its midpoint coded value = 0.

A)

True

B)

False

54

Why use center points in your experimental design?

A)

To check for linearity

B)

To check for interactions

C)

To detect curvature

55

If a center point is significant, its p-value in the ANOVA table will be greater than 0.05.

A)

True

B)

False

56

Fractional factorial designs require more runs than full factorial designs given the same number of factors.

A)

True

B)

False

57

What is the main reason for using a fractional factorial design?

A)

Allows you to test and screen a large number of factors in fewer runs

B)

Gives you good estimates of low order interactions

C)

Gives you relative significance of the factors

D)

All of the above

58

Given three factors, A, B, and C, the highest-order interaction would be ABC.

A)

True

B)

False

59

In a four-factor 1/2 fractionated design, the AB interaction is confounded with the CD interaction.

A)

True

B)

False

60

What does it mean when A is confounded with BC?

A)

A is contributing to the result.

B)

BC is contributing to the result.

C)

The computed coefficients are related to the sum of the two individual effects.

D)

The sums of squares are related to the sum of the two individual effects.

61

In a resolution IV design, two-factor interactions are aliased with three-factor interactions.

A)

True

B)

False

62

In a resolution III design, single factors are not aliased with any other factors.

A)

True

B)

False

63

The identity expression I + ABCD is used to generate the confounding pattern.

A)

True

B)

False

64

Why are resolution V designs preferred over resolution III and resolution IV designs?

A)

No main effect is confounded with any other main effect or second-order interactions.

B)

No second-order interactions are confounded with any other second-order interaction, and second-order interactions are confounded with third-order interactions.

C)

Allows for the differentiation of the effects down to the second order, assuming that the effects of third-order interactions are negligible.

D)

All of the above

65

Why should you do a hypothesis test before running a DOE?

A)

Statistically test for the correct factors

B)

Find the trivial many

C)

To ensure that your measurement system is good

D)

To ensure that you have all the process steps identified

E)

To identify as many of the vital few factors prior to DOE

66

What is the mission of the Improve phase?

A)

Find the relationships between X and Y

B)

Validate hypothesis tests

C)

Which inputs to control in the next phase

D)

Run a pilot to validate experiment

E)

All of the above

67

Can you calculate epsilon-square percent contribution for the DOE given that the degree of freedom for each factor is different in the ANOVA?

A)

Yes

B)

No

68

The WECO (Western Electric Company) rules are based on probability. We know that for a normal distribution, the probability of encountering a point outside ±2.5 is 0.3 percent. This is a rare event. Therefore, if we observe a point outside the control limits, we conclude that the process has shifted and is unstable.

A)

True

B)

False

69

Outliers usually have a significant effect on an equation derived with regression analysis.

A)

True

B)

False

70

Using Y = f(X), do we set tolerance limits for Y?

A)

Yes

B)

No

71

What is the residual?

A)

It is the equation from the data.

B)

It is the standard error of the equation.

C)

It indicates how well the equation fits.

D)

It is a calculation of the expected value minus the observed value.

E)

c and d

72

What are control charts?

A)

Design of experiment (DOE)

B)

A plot showing the Y over time

C)

Charts showing average control

D)

Charts used to routinely monitor quality

E)

None of the above

73

What does a P-chart track?

A)

Process chart showing the main factors

B)

Sample size of the process over time

C)

Simple chart used to track the number of nonconforming units, percentage of defective parts, assuming that sample size is not necessarily constant

D)

None of the above

74

A DOE is always needed to solve process issues.

A)

True

B)

False

75

The purpose of performing a designed experiment is to determine what?

A)

The mathematical relationship Y = F(x1, x2, x3, . . .)

B)

Which X’s most impact Y and therefore need to be controlled

C)

The level of each X to achieve the desired mean Y

D)

The level of each X to minimize the variability of Y

E)

All of the above

76

Within the DOE, the easiest way to test for curvature is to include center points.

A)

True

B)

False

77

The most common response surface design is called the central composite design.

A)

True

B)

False

78

Control plans provide a written description of the actions that are required at each phase of the process to ensure that all process inputs and outputs will be in a state of control.

A)

True

B)

False

79

Control plans are only generated at the start of the life cycle of a product.

A)

True

B)

False

80

SPC is a statistically based graphing technique that compares current process data to a set of stable control limits established from normal process variation.

A)

True

B)

False

81

Control limits and specification limits are the same thing:

A)

True

B)

False

82

Control limits are typically set at plus or minus 2 standard deviations from the target of the control chart.

A)

True

B)

False

83

Regular residuals are the actual values of the residuals calculated by subtracting the expected value from the observed value.

A)

True

B)

False

84

What is the best description of a data transform?

A)

A transformation of the data using a power table to treat linearity in the data

B)

A transformation of the data using a power table to treat nonlinearity in the data

C)

Improves the variance within the data

D)

A transformation of the data using a power table to treat the units of the data

E)

It transforms data into a more approximate normal distribution

85

Outliers usually have a significant effect on an equation derived with regression analysis.

A)

True

B)

False

86

When an “out of control” situation is signaled on a control chart, the person using the chart will know why the data are giving the signal.

A)

True

B)

False

87

Once the special causes of variation in a process have been discovered and eliminated, the long-term goal of anyone managing a process will be to reduce common cause variation by improving the process or system itself.

A)

True

B)

False

88

An "out of control" situation in a production process may be signaled by a sample f output that generates a data point outside the control limits on either the Xbar–R range chart.

A)

True

B)

False

89

Mistakeproofing seeks to gain permanence by eliminating or rigidly controlling human intervention in a process.

A)

True

B)

False

90

Six Sigma product and process design or process changes made to the product or process that eliminate the error condition from occurring are called what?

A)

TQM

B)

Mistakeproofing

C)

Mistake elimination

D)

Foolproofing

E)

All of the above

91

Systems that monitor the process and automatically adjust critical X’s to correct settings are called what?

A)

Full automation

B)

Process interruption

C)

Mechanism

D)

SPC

92

In order for mistakeproofing systems to operate effectively, the following rules must not be observed.

A)

The systems must be installed and properly adjusted before process startup.

B)

The systems must be periodically audited and maintained.

C)

Systems are periodically disabled.

D)

Inoperative or missing systems must be repaired or replaced before operating the process.

E)

System overrides must not be used except in an emergency.

93

The EWMA or Exponentially Weighted Moving Average chart is a variable data control chart.