TOPICS
Search

Trimmed Mean


A trimmed mean is the arithmetic mean computed after discarding specified proportions of the smallest and largest observations. If X_((1))<=...<=X_((n)) are the order statistics, the k-trimmed sample mean is

 X^__k=1/(n-2k)sum_(i=k+1)^(n-k)X_((i)),

for 0<=k<n/2. Symmetric trimming uses the same k at both ends; asymmetric trimmed means are also possible.

Trimming reduces sensitivity to extreme observations at the cost of discarding data. The ordinary sample mean is obtained when k=0, while increasingly heavy symmetric trimming moves the statistic toward the sample statistical median.


See also

Arithmetic Mean, Order Statistic, Statistical Median

Explore with Wolfram|Alpha

References

Huber, P. J. and Ronchetti, E. M. Robust Statistics, 2nd ed. Hoboken, NJ: Wiley, 2009.

Cite this as:

Weisstein, Eric W. "Trimmed Mean." From MathWorld--A Wolfram Resource. https://mathworld.wolfram.com/TrimmedMean.html

Subject classifications