Multiple Comparisons and Outliers

Grubbs' Test Table: Critical Values for Detecting an Outlier

Critical values for Grubbs' test, which checks whether the most extreme value in a normally distributed sample is an outlier.

  • n = 3 to 500
  • One- and two-sided
  • Test your data

Grubbs' Test Table

Rows: sample size n · Columns: α for a two-sided or one-sided test · Cells: critical G. The value is an outlier if G > the cell.

Grubbs' Test Table (Critical Values for Outliers)
Two-sided test (largest or smallest)One-sided test
nα = 0.10α = 0.05α = 0.01α = 0.05α = 0.025α = 0.01
31.15311.15431.15471.15311.15431.1546
41.46251.48131.49621.46251.48131.4925
51.67141.71501.76371.67141.71501.7489
61.82211.88711.97281.82211.88711.9442
71.93812.02002.13911.93812.02002.0973
82.03172.12662.27442.03172.12662.2208
92.10962.21502.38682.10962.21502.3231
102.17612.29002.48212.17612.29002.4097
112.23392.35472.56412.23392.35472.4843
122.28502.41162.63572.28502.41162.5494
132.33052.46202.69902.33052.46202.6070
142.37172.50732.75542.37172.50732.6585
152.40902.54832.80612.40902.54832.7049
162.44332.58572.85212.44332.58572.7470
172.47482.62002.89402.47482.62002.7854
182.50402.65162.93252.50402.65162.8208
192.53122.68092.96802.53122.68092.8535
202.55662.70823.00082.55662.70822.8838
212.58042.73383.03142.58042.73382.9121
222.60282.75773.05992.60282.75772.9385
232.62392.78033.08662.62392.78032.9633
242.64392.80163.11172.64392.80162.9866
252.66292.82173.13532.66292.82173.0086
262.68092.84083.15772.68092.84083.0295
272.69812.85893.17882.69812.85893.0492
282.71452.87623.19892.71452.87623.0680
292.73012.89273.21792.73012.89273.0859
302.74512.90853.23612.74512.90853.1029
352.81182.97823.31562.81182.97823.1778
402.86753.03613.38072.86753.03613.2395
452.91533.08543.43542.91533.08543.2916
502.95703.12823.48252.95703.12823.3366
603.02693.19973.55983.02693.19973.4111
703.08393.25763.62173.08393.25763.4710
803.13193.30613.67293.13193.30613.5208
903.17333.34773.71643.17333.34773.5633
1003.20953.38413.75403.20953.38413.6002
1203.27063.44513.81663.27063.44513.6619
1503.34293.51703.88943.34293.51703.7340
2003.43243.60553.97773.43243.60553.8221
3003.55243.72364.09353.55243.72363.9385
5003.69523.86314.22833.69523.86314.0749

Tip: click any value to highlight its row and column.

How to read this table

  1. Compute the mean x̄ and standard deviation s of all n values, including the suspect value.
  2. Compute G = |xsuspect − x̄| / s for the value farthest from the mean.
  3. Use the two-sided columns if the outlier could be either the largest or the smallest value, and the one-sided columns if you decided in advance to test only one end.
  4. The value is an outlier if G is greater than the table value.

Worked example

Twelve assay results have mean 10.25 and SD 0.767, and the largest value, 12.6, gives G = (12.6 − 10.25) / 0.767 = 3.06. Row n = 12, two-sided α = 0.05 gives 2.4116. Because 3.06 > 2.4116, 12.6 is an outlier at the 5% level. Paste these values into the calculator above to see the full calculation.

Click the underlined links to highlight the value in the table.

Calculator

For values between the rows and columns of the table. Results update as you type.

Formula and how the values were computed

G = max|xᵢ − x̄| / s  ·  Gcrit = ((n − 1)/√n) √(t² / (n − 2 + t²))

Critical values use the exact relationship with the t-distribution: G = ((n − 1)/√n) √(t² / (n − 2 + t²)), where t is the upper α/(2n) (two-sided) or α/n (one-sided) critical value with n − 2 df.

Frequently asked questions

Can I apply Grubbs' test repeatedly?

It is designed to detect one outlier. Repeating it after removing a value is common but can miss outliers that mask each other; the generalized ESD test handles several suspected outliers properly.

Should I delete a value that Grubbs' test flags?

Not automatically. A flagged value should be investigated for data entry or measurement errors. In clinical trials, outliers are normally kept in the primary analysis and handled with a pre-specified sensitivity analysis.

Related calculators and tutorials