Six Sigma & Quality Statistics: DPMO, Cp/Cpk & Control Charts

What you'll build

What you will be able to do

Each lab ends with a concrete result that you build yourself and the checker confirms, cell by cell.

• Measure one month of final inspection at Kestrel Valve Co.: defects per unit, defects per million opportunities and first-pass yield, per product line and for the whole plant.
• Uncover the hidden factory on the V10 line with rolled throughput yield and convert yields and DPMO into sigma levels with NORM.S.INV and the 1.5 shift.
• Rank one quarter of V10 defects, compute shares and the cumulative percentage, count the vital few and draw a Pareto chart.
• Judge whether the V10 bore can meet its ±50 µm tolerance: within and overall standard deviation, Cp, Cpk and Ppk.
• Set the control limits for the seal kit fill weight from 12 subgroups with the A2/D3/D4 constants and chart the means to spot a signal.
• Build a p-chart for 15 days of actuator testing with a different sample size every day, and find the day that signals a special cause.
• Before trusting any capability number, you test the bore gauge: repeatability, reproducibility and %GRR of the tolerance from a 5 × 3 × 2 study.
• Prove that the porosity project really cut scrap with a t-test, then put a dollar value on the cost of poor quality, the annual saving and the payback.