LimitLine

Learn · updated 2026-10-28

EWMA Chart: Catch a Small, Slow Drift

By Nicholas Williford, Lean Six Sigma Black Belt · About LimitLine

An I-MR chart reacts to each point on its own, so it catches big jumps fast but can miss a shift of half to one standard deviation for a long time. An EWMA (exponentially weighted moving average) chart plots a running average that remembers past points, so a small, steady drift builds up until it crosses a limit.

EWMAz(t) = λ·x(t) + (1 − λ)·z(t−1), starting at z(0) = targetSpread of zσ(z) = σ·√(λ ÷ (2 − λ))Limitstarget ± L·σ(z), usually L = 3

Worked Example: NIST's 20 Points

NIST's handbook uses a target of 50, a historical standard deviation of 2.0539 and λ = 0.3. Then σ(z) = 2.0539 × √(0.3 ÷ 1.7) = 0.8628, so the limits are 47.41 to 52.59.

PointxEWMA z
152.050.60
247.049.52
353.050.56
449.350.18
550.150.16
647.049.21
751.049.75
850.149.85
951.250.26
1050.550.33
1149.650.11
1247.649.36
1349.949.52
1451.350.05
1547.849.38
1651.249.92
1752.650.73
1852.451.23
1953.651.94
2052.151.99
UCL 52.59LCL 47.41CL 50.00Point 1: 50.6Point 2: 49.52Point 3: 50.564Point 4: 50.1848Point 5: 50.15936Point 6: 49.211552Point 7: 49.7480864Point 8: 49.85366048Point 9: 50.257562336Point 10: 50.3302936352Point 11: 50.1112055446Point 12: 49.3578438812Point 13: 49.5204907169Point 14: 50.0543435018Point 15: 49.3780404513Point 16: 49.9246283159Point 17: 50.7272398211Point 18: 51.2290678748Point 19: 51.9403475123Point 20: 51.9882432586135791113151720
Every EWMA value is inside the limits, but the last five climb steadily from 49.92 to 51.99: NIST notes the upward trend. Keep plotting: if the level has really moved up, the EWMA keeps climbing toward 52.59.

On an I-MR chart the same 20 points stay inside limits of 44.43 to 56.50, and no single point stands out: the drift shows up only as a pattern, which is what the EWMA is built to see.

Choosing λ and L

Three Common Mistakes

  1. Using the wide, long-run limits from point 1. The spread of z grows from λσ toward its limit over the first points; the exact limits use σ·√(λ ÷ (2 − λ) · (1 − (1 − λ)^(2t))). The plain formula is fine once t is past about 10.
  2. Estimating σ from the data being judged. Take σ from a stable history (or the moving range of a stable period), or a drift inflates σ and hides itself.
  3. Replacing the I-MR chart. EWMA is slower on a large, sudden jump. Many plants run both: I-MR for big jumps, EWMA for slow drift.
Make an EWMA chart in LimitLineThe EWMA · CUSUM tool (Pro) takes your data, λ and L; the example data is free to try.

Sources

  1. NIST/SEMATECH e-Handbook of Statistical Methods, 6.3.2.4 “EWMA Control Charts”
  2. S. W. Roberts (1959), “Control Chart Tests Based on Geometric Moving Averages”, Technometrics 1(3)
  3. J. M. Lucas and M. S. Saccucci (1990), “Exponentially Weighted Moving Average Control Schemes”, Technometrics 32(1)

The LimitLine Newsletter

About one email a month: new guides, tool updates and one practical SPC tip. Unsubscribe in one click.

We'll email you once to confirm before anything else is sent. Privacy