Calculators

Trimmed Mean Calculator

Calculate a trimmed mean by removing a chosen percentage from each end of a sorted dataset, privately in your browser.

Remove a percentage of the lowest and highest values, then average the remaining numbers. Your data stays in your browser.

Separate values with commas, semicolons, spaces, or newlines. Use decimal points without thousands separators. Scientific notation is supported. Enter up to 10000 finite signed numbers, including zero.

Use 0 to less than 50%. The number removed from each end is rounded down. For five values and 20%, one value is removed from each end.

Your trimmed mean will appear here.

Average data after trimming both extremes.

Sort the data and remove floor(n × p / 100) values from each end, where p is the percentage per end. Average the retained values. For 1, 2, 3, 4, and 100 with 20% trimming per end, remove 1 and 100; the trimmed mean of 2, 3, and 4 is 3. The total removed fraction is twice the per-end fraction, subject to rounding down separately at each end. A 0% trim gives the arithmetic mean; small datasets may remove no values. Trimming reduces the influence of extremes but discards observations, so report the trim percentage with the result. This differs from a winsorized mean, which replaces extremes rather than removing them. Enter 1 to 10000 finite signed numbers with consistent units, separated by commas, semicolons, spaces, or newlines. Scientific notation is accepted; omit thousands separators. Results use browser floating-point arithmetic displayed to 12 significant digits. All processing stays in your browser.

Frequently Asked Questions

Everything you need to know about this tool, how it works, and privacy.

How is a trimmed mean calculated?

Sort the data and remove floor(n × p / 100) values from each end, where p is the percentage per end. Average the retained values. For 1, 2, 3, 4, and 100 with 20% trimming per end, remove 1 and 100; the trimmed mean of 2, 3, and 4 is 3.

Is the percentage per end or in total?

It is per end. A 10% trim removes up to 10% of observations from each end, about 20% overall. Each count is rounded down independently.

Can trimming remove every value?

No. The percentage must be at least zero and less than 50. At least one observation remains. A single value returns itself.

How does trimming differ from winsorization?

Trimming removes extreme observations. Winsorization replaces them with boundary values and retains the original observation count.

What inputs and precision are supported?

Enter up to 10000 finite signed numbers. Scientific notation is supported. Results use approximate floating-point arithmetic with 12 significant digits. Your data stays in your browser.