Sigma Level Calculator
DPMO, yield and sigma level from your own defect counts, with the one thing most sigma calculators leave out: how sure you can be of the answer. A sigma level from a small sample is a range, not a number, and this page shows the range.
A second calculator below checks whether a drop in defects after a kaizen or a process change is a real improvement or ordinary noise.
Nothing you type here leaves your browser. Every calculation runs in this page. The page itself counts visits, like every page on this site, but never what you enter.
1. Your sigma level, and how sure you can be of it
Sigma level, 95% confidence interval
2. Did the kaizen work, or is it noise?
Enter the defect count and the amount of work for the period before the change and the period after. The amount of work can be units, orders, shifts or hours, as long as both periods use the same measure.
The arithmetic, with your numbers
Shown so you can check it, or redo it in a spreadsheet.
What this does not tell you
- It assumes your process was stable while you counted. A sigma level describes a process that behaves the same way from one day to the next. If something changed partway through the count, the result describes neither half. Plot the defects over time before you trust a single figure.
- The 1.5 sigma shift is a convention, not a measurement. Six Sigma practice adds 1.5 to the sigma level on the assumption that a process drifts that far over the long run. That assumption comes from Motorola's experience in the 1980s, not from your process. This page shows both figures so you can see which one a report is using.
- The answer depends on what you call an opportunity. Counting more opportunities per unit makes the same defects look rarer and the sigma level higher. Agree the definition before you compare two lines, two sites or two years.
- The before and after test does not prove the change caused the drop. It tells you whether the drop is larger than chance alone would produce. A new supplier, a quieter month or a different inspector can move the count just as well. It also assumes defects arrive independently, and a single bad batch breaks that.
- A 95% interval is wrong about one time in twenty. It is a statement about the method, not a guarantee about your number.
The rest of the Lean Six Sigma toolkit
- Control Chart Maker: I-MR, c and p Charts with Run Rules: I-MR, c and p charts with the four Western Electric run rules.
- Process Capability Calculator: Cp, Cpk, Pp, Ppk: Cpk with its confidence interval, a Cpk against Ppk drift check and a normality test.
- Takt Time and Line Balance Calculator: Takt time, line balance and the bottleneck, with stations that miss takt on slow cycles.
- OEE Calculator: Availability, Performance, Quality Losses: OEE with each loss in minutes, and the one fix worth most.