Cp and Cpk calculator

Paste your measurements and enter the spec limits. You get Cp, Cpk, Pp, Ppk, expected PPM and a normality check, with what each number means in plain English and the formulas behind it.

  • Runs in your browser; nothing is uploaded
  • Checked against NIST and Montgomery examples
  • Launch, ongoing or your customer's criteria
  • No signup

Your data

Paste a column from Excel, or type one value per line, in the order they were measured.

No measurements yet

How were the parts measured?

This sets how short-term variation (Cp, Cpk) is estimated. Not sure? Choose one at a time.

Base the verdict on

Most initial PPAP studies use Ppk.

Judge it against

PPAP initial study: above 1.67 acceptable, 1.33 to 1.67 with customer approval. Many customers accept 1.33 in ongoing production.

Results

Your results appear here. No data? Load the example to see how it works.

Early access

The free tools give you the numbers. Mensuro gives you the study.

A screenshot shows a result. Your customer wants the whole study, traceable and signed off, and you want to know what to do about it.

  • Sigmi, your study assistant. Helps you pick the right study, explains every result in plain English and what to fix first, using the engine's numbers. It never makes one up.
  • Your brand on every report. Your logo, company and customer on a customer-ready PDF: verdict, charts, the method behind every number, and the raw data.
  • Is your gage good enough to trust this Cpk? Gage R&R with a recheck when you reuse it on another part, Type 1 gage studies, and capability for each cavity of a multi-cavity tool.
  • Your spreadsheet as it is. Upload Excel or CSV. Mensuro finds the columns and you confirm before anything runs.
  • Validated, with a receipt. Every analysis reproduces published reference results, and every report shows its method, constants and sample size, so reviewers don't come back with questions.

Free to join. Founding members get the first year for $199. We only email you about Mensuro, and you can unsubscribe anytime. Your measurements above are not sent with this form.

Is this good enough for PPAP?
Sigmi
Conditionally. Ppk is 1.41, between 1.33 and 1.67, so it needs your customer's approval. The process is well centered and Cpk is close at 1.46, so reducing spread, not re-centering, is what will raise it.
Ran: process capability, normal, n = 100 · example data
Can I trust the gage on a tolerance this tight?
Sigmi
Worth checking before you submit. Upload your Gage R&R data and I'll compare %GRR with this 0.060 mm tolerance and add it to the same report.
Example conversation using the example data above. Sigmi arrives with the beta.
How it's calculated

The formulas, in plain English.

Standard definitions, nothing proprietary. Open any topic for the formula and what it means for your process.

How we check it

On every change, automated tests compare this calculator with the NIST worked example and reject-rate table, Montgomery Examples 6.1 and 8.1–8.2, and the Mensuro statistics engine (built on SciPy and statsmodels). It must agree with the engine to at least 9 significant digits. See the tests.

Sources

  • NIST/SEMATECH e-Handbook of Statistical Methods, 6.1.6, What is process capability?
  • D. C. Montgomery, Introduction to Statistical Quality Control, 6th ed. (Wiley, 2009), Sections 6.2 and 8.3; d2 from Appendix VI.
  • AIAG, Production Part Approval Process (PPAP), 4th ed., initial process study criteria.
  • R. B. D'Agostino and M. A. Stephens, Goodness-of-Fit Techniques (Marcel Dekker, 1986).
Cp and Cpk: short-term capability

Cp and Cpk use within (short-term) sigma: the variation from one part to the next, without slow drift or shifts.

σwithin = MR̄ / 1.128  (one at a time)
σwithin = R̄ / d2  (in groups; d2 depends on group size)

Cp = (USL − LSL) / 6σwithin
Cpk = min(USL − x̄, x̄ − LSL) / 3σwithin

MR̄ is the average difference between consecutive measurements; R̄ is the average range within each group.

Pp and Ppk: long-term capability

Pp and Ppk use the standard deviation of every measurement, so they include drift and shifts over the whole study.

s = √[Σ(x − x̄)² / (n − 1)]

Pp = (USL − LSL) / 6s
Ppk = min(USL − x̄, x̄ − LSL) / 3s

Cpk or Ppk: which does my customer want?

Same formula, different sigma. Ppk is usually the one asked for in an initial PPAP study; Cpk shows what the process can do short-term. If Ppk is much lower than Cpk, the process is drifting or shifting over time.

Cp vs Cpk: why centering matters

Cp compares the tolerance width with the process spread and ignores where the process sits. Cpk measures from the mean to the nearer limit. A high Cp with a low Cpk means the process is capable but off-center, often an easy fix.

What's a good Cpk? (the verdict)

The verdict uses PPAP-style criteria on Ppk by default:

  • Above 1.67 acceptable
  • 1.33 to 1.67 may be acceptable with customer approval
  • Below 1.33 not acceptable

That's the default, Launch (PPAP). A short launch study usually looks better than months of production, so 1.67 up front leaves room for tool wear, material lots and shift changes. Once a process is approved, many customers accept 1.33 or more for ongoing production: choose Ongoing production. If your customer sets its own minimum, choose Customer minimum and enter it.

Expected and observed PPM

Expected PPM is the share of a normal distribution beyond each limit, in parts per million, shown for both sigmas:

PPM = [Φ((LSL − x̄) / σ) + 1 − Φ((USL − x̄) / σ)] × 1,000,000

Observed PPM counts the measurements actually outside the limits.

Is my data normal? (Anderson-Darling)

With 8 or more measurements, an Anderson-Darling test checks whether a normal curve fits, using the D'Agostino-Stephens small-sample adjustment. If p is below 0.05, the data may not be normal, and the indices and expected PPM should be read with caution.

One at a time or in groups?

Choose one at a time if each measurement is a separate part taken in sequence. Choose in small groups if you pulled several parts together at each check, for example 5 parts every hour, and enter the measurements group by group. This only changes the short-term sigma behind Cp and Cpk; Pp and Ppk are the same either way.

What if I only have one spec limit?

Leave the other limit blank. You get the one-sided index (Ppu or Ppl, Cpu or Cpl); Cp and Pp need both limits and aren't shown.

What has to be true for the results to hold?

The process should be stable (in statistical control), and the measurements in the order they were taken, because the short-term sigma depends on order. Use 30 or more measurements for a dependable estimate; with fewer, the result carries a warning.

Is my data stored anywhere?

No. The calculation runs in your browser. The measurements and limits you enter are never sent to Mensuro or anyone else, and this page doesn't save them.