Analyze carries 22% of the Green Belt exam under the current PeopleCert syllabus. It covers patterns of variation, inferential statistics, and hypothesis testing with normal data (t-tests, ANOVA) and non-normal data (Mann-Whitney, Kruskal-Wallis, chi-square). Our bank holds 330 Analyze questions; these five worked questions are drawn from that bank, with the correct answer and a full explanation for each.
Worked questions
1. Before collecting data, a team agrees on alpha of 0.05. After seeing a p-value of 0.06, a member proposes switching alpha to 0.10 so the finding counts. What is the problem?
A. Moving the threshold after seeing results inflates the real false alarm rate beyond its stated value.
B. Alpha values above 0.05 are mathematically forbidden in any workplace improvement investigation.
C. The proposal fails because p-values of 0.06 must always be reported as exactly zero instead.
D. Switching is harmless provided the team votes unanimously and records the change in meeting notes.
Correct: A. Alpha must be set in advance. Raising it after seeing p equal to 0.06 turns a non-result into a rejection and breaks the advertised error rate.
2. Two clinics are compared on mean wait time with samples of 40 patients each drawn independently. Which assumption deserves a quick check of how patients were sampled within each clinic?
A. Wait times must be identical across clinics, because comparisons require matching outcomes first.
B. Patients must arrive in alphabetical order, because t-tests process names before processing times.
C. Observations within each clinic should be independent, not clustered around one chaotic morning.
D. Each clinic must contribute exactly the same wait times, because balance means copying values.
Correct: C. Independence within samples matters. If one clinic sample all came from a single disrupted morning, the readings would not represent that clinic fairly.
3. A median comparison shows no shift for skewed income-like process data, while the mean moved noticeably. How can both be true?
A. Both cannot be true, because medians and means are chained together by a fixed constant offset.
B. A few extreme values can drag the mean upward while the typical middle value stays unmoved.
C. Medians ignore all data by design, so their stillness carries absolutely no evidential weight.
D. Means respond only to sample size, so the movement reflects headcount rather than any values.
Correct: B. Means chase extremes; medians track the middle. In skewed data a handful of large values can lift the mean while typical experience is unchanged.
4. In a multi-vari plot for machined pins, each hour's cluster sits higher than the last, while pins within an hour agree closely. What pattern is shown?
A. A strong position effect, with pins from one end of the fixture consistently outweighing the others.
B. A steady time-based climb, with hour-to-hour movement dwarfing the spread inside any single hour.
C. A repeating cycle tied to lot changes, with clusters alternating high and low in a regular rhythm.
D. A gauge problem, with the same pin yielding wildly different readings on successive measurements.
Correct: B. Clusters marching upward over time signal temporal variation. Tight within-hour grouping rules out positional dominance.
5. A rational subgroup plan for moulded parts takes one part from each of four cavities every cycle. What does that grouping achieve?
A. Each subgroup isolates a single cavity over time, letting its wear trend be followed without interference from others.
B. Each subgroup randomises cavity identity, letting cavity labels be dropped from records without losing useful detail.
C. Each subgroup spans all cavity positions at one moment, letting cavity effects appear consistently within the snapshot.
D. Each subgroup merges several cycles, letting short-lived cavity problems average away before anyone investigates them.
Correct: C. All positions at one instant form a rational snapshot. Cavity differences show inside subgroups; time shifts show between them.
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 Green Belt exam guide, then see the full IASSC Lean Six Sigma Green Belt Exam Prep program — 1,500 original questions covering all five DMAIC phases of IASSC’s Body of Knowledge, 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.
