All use cases

Prepare a process-capability data review.

Check population stability, specification versions and measurement context before interpreting process-capability calculations.

Book a demo
Illustration of a seal comparing study vessels and their recorded response curves.

You: Prepare the capability analysis for these 40 batches. Can we calculate one Cpk?

neil

The mixing process changed after batch 24, leaving 24 pre-change and 16 post-change batches. Unchanged specification limits do not make those observations one stable process. I would inspect the time-ordered data and the change before choosing the analysis population.

Configuration change splits the data
Configuration change splits the data. 24, 16, Before change, After change. Example records.24→16Before changeAfter change

You: What should be plotted first?

neil

The actual observations in time order, with the process change marked and rational subgroups preserved. I would check the measurement system, stability and distribution assumptions before reporting capability. The supplied counts alone cannot support a Cpk calculation or a claim of improvement.

You: Write this up for review, with the sources and the follow-up work we need.

neil

Here is the draft. I have kept the supported finding separate from the open questions, and prepared the evidence requests for the responsible roles.

CPV-211 analysis population and capability planReview draft · source evidence and assessment

CPV-211 analysis population and capability plan

The configuration change divides the dataset into 24 earlier batches and 16 later batches. Identical specification limits do not establish a single stable process across that boundary. Review time order, subgroup definitions and measurement context within each period before deciding whether pooling is justified. A capability index calculated from all 40 values could otherwise obscure the effect of the change.

Source evidence and search scope

CPV-211 (Measurement series); CHG-211 (Process change); SPEC-211 (Specification history)

CPV-211 / Measurement series

Recorded evidence
40 batches in time order

CHG-211 / Process change

Recorded evidence
Mixing configuration changed after batch 24

SPEC-211 / Specification history

Recorded evidence
Same numeric limits across both periods
Inputs needed for your own records
  • Time-ordered process measurements with subgroup identifiers
  • Specification versions and measurement-system evidence
  • Process changes, exclusions and the approved analysis approach

A qualified reviewer determines the suitable statistical approach and verifies stability and assumptions. A single pooled capability number may be misleading.

Fictional source snapshots. No live query, assignment or approval.

Follow-up work and evidence requests2 proposed tasks · not assigned

Evidence to request

Assess stability and subgroup structure
Process statistician
Obtain the 40 individual observations, measurement context and subgroup identities. Examine the pre- and post-change populations separately.
Document the process-change boundary
Process owner
Link CHG-211 to actual implementation and explain any transition batches before selecting data for a capability conclusion.
Example conversation · prepared replies

See this job with your team.

Tell us how your team handles this job today. We’ll walk through the analysis, supporting evidence and review steps in a demo.

Book a demo
What to bring for this job
  • Time-ordered process measurements with subgroup identifiers
  • Specification versions and measurement-system evidence
  • Process changes, exclusions and the approved analysis approach

Source access, permissions and permitted actions are agreed for your environment.

Source excerpt

CPV-211

Measurement series

Recorded evidence
40 batches in time order

Selected fictional record, not a live source-system view.

Browse all use cases