Measure carries 21% of the Black Belt exam under the official syllabus: process definition, Six Sigma statistics, measurement system analysis (including the ANOVA gage method and attribute agreement studies) and process capability, including attribute capability. Our bank holds 315 Measure questions; these seven worked questions are drawn from that bank, with the correct answer and a full explanation for each.
Worked questions
1. A histogram of weld strengths from a supposedly single process shows a plateau — roughly uniform heights across a wide span — rather than a peak. The likeliest structural explanation is:
A. The sample size is too large, because big samples smooth any distribution toward uniformity regardless of its true shape in the limit
B. The weld process is in perfect statistical control, since uniformity of outcomes indicates a stable, centered process
C. The measurement gauge lacks resolution, and finer measurement increments would reveal the underlying normal peak
D. Several distinct sub-processes or settings with different centers are pooled, flattening the combined shape into a plateau
Correct: D. Pooling populations with different centers smears their peaks into a plateau; stratification by machine, operator, or setting usually recovers the separate shapes.
2. A Black Belt must show whether a bottling line's output has drifted over a two-week production run. The data arrive in production order. Which display leads the analysis?
A. A histogram of all fills pooled together, because shape alone determines whether output moved during the run
B. A boxplot grouped by filler head, because grouping by equipment answers every question about change over time
C. A pie chart of fills by shift, because proportions by category are the standard way to display process drift
D. A run chart or time-ordered plot, because only a display preserving sequence can reveal drift across the run
Correct: D. Drift is a pattern in sequence; pooling the fills into a histogram destroys their order, while a run chart keeps production order visible so a gradual drift across the two weeks can actually be seen.
3. A Black Belt must choose between the average-and-range method and the ANOVA method for a gage study with three operators and varied part sizes. What does the ANOVA method add that decides the choice?
A. It estimates the operator-by-part interaction, which the average-and-range method cannot separate from reproducibility
B. It requires fewer measurements, because ANOVA extracts the same information from a single reading per part
C. It eliminates the need for operators to measure the same parts, since the model fills in missing combinations
D. It guarantees smaller gage percentages, because its variance estimates are systematically lower than range-based ones
Correct: A. The average-and-range method folds any operator-by-part interaction into its reproducibility estimate invisibly; ANOVA separates that interaction as its own component, which matters when operators handle different parts differently.
4. A Black Belt designs an attribute agreement study for final inspection. Which set of design choices is sound?
A. Parts whose status is unknown to everyone, because a standard for comparison would bias the appraisers' natural judgment, even if the process was drifting then
B. A single trial per appraiser, because repeat trials let appraisers memorize parts and corrupt the agreement estimates
C. Only parts the appraisers themselves select, since ownership of the sample improves their engagement with the study
D. Known-standard parts including borderline cases, blind repeat trials per appraiser, and enough parts to estimate agreement with useful precision
Correct: D. A sound study needs a truth reference (including hard borderline cases), blinded repeats to estimate within-appraiser consistency, and a sample large enough that the agreement and kappa figures are not guesswork.
5. A process is both out of control and not capable. Which sequencing is most defensible?
A. Reduce variation first with a redesign, because spread is the larger problem whenever both faults appear together
B. Center the mean on target first, because a centered unstable process will usually settle into control by itself
C. Replace the capability study with final inspection data, because indices are meaningless until the process is redesigned
D. Address assignable causes and stabilize first, then reassess spread and centering against the specification limits
Correct: D. An unpredictable process cannot be meaningfully centered or narrowed; removing assignable causes comes first, then capability is reassessed on the stabilized process.
6. While building a fishbone for late surgical starts, a facilitator notices every contribution blames another department and no branch contains a measurable variable. The most productive intervention is to:
A. End the session and interview department heads separately, since cross-functional blame makes group diagramming unworkable in hospitals, to avoid open conflict
B. Redirect each blame statement into a controllable, measurable factor the team can check, such as 'minutes from consent signed to patient ready'
C. Add a 'people' branch and let the team list individuals, because naming accountability openly clears the air for analysis
D. Accept the statements as causes and move to solutions, because late starts are a coordination problem rather than a data problem
Correct: B. Useful fishbone entries are specific factors that can be observed or measured; converting blame into variables like elapsed minutes between defined events makes causes testable.
7. A cause-and-effect matrix was built before the team confirmed which customer outcome the charter prioritizes, and the Y weights are contested in review. The soundest recovery is:
A. Freeze the matrix as scored, because re-scoring after review sets a precedent that any tollgate can reopen any tool
B. Average the contested weights and proceed, since small weight differences rarely change which Xs reach data collection
C. Ask the sponsor to pick the top three Xs directly, bypassing the matrix the team no longer fully trusts for this project
D. Revisit the Y set and weights with the customer evidence first, then re-score — X rankings built on unsettled Ys are unstable
Correct: D. X priorities inherit their meaning from Y importance; if the outcomes or their weights are wrong, every total beneath them is wrong, so the Y foundation must be settled first.
A note on format. The real IASSC exam mixes multiple-choice with true/false questions, while PassProfessor’s bank trains you with four-option multiple-choice questions throughout — the same knowledge, in a format that forces you to discriminate between close alternatives. No worked set on this page reproduces the real exam’s item-type mix.
These questions are drawn from the same bank as the full program. Start with the 20 free sample questions (also presented readably on the free sample questions page), read the IASSC Black Belt exam guide, then see the full IASSC Lean Six Sigma Black Belt Exam Prep program — 1,500 original questions built at the official syllabus weights (Define 13% · Measure 21% · Analyze 27% · Improve 17% · Control 22%), with an explanation for every answer, for $59 with 6 months of access.
Disclaimer
PassProfessor is an independent exam-preparation provider. This program is exam preparation only: it is not the real exam, it provides no education credit, and completing it does not by itself qualify you for any license or certification. The real exam is run by its own exam body — you register for it, pay its fees, and sit it through that body, not through PassProfessor. All practice questions in this program are original; they are not actual exam questions.
