Talk:Truncated mean

Winsorized mean

The Windsor mean or, more often, Winsorized mean is somewhat different, see the page for that measurePlf515 (talk) 02:01, 13 March 2008 (UTC)

What are the advantages/disadvantages of the two approaches? —Preceding unsigned comment added by 203.206.162.148 (talk) 05:27, 23 September 2010 (UTC)

Drawbacks of Trimmed Mean??

This source (http://davidmlane.com/hyperstat/A11971.html) points out the fact that trimmed mean is actually better estimator of central tendency with highly skewed samples, since a median essentially is a 100% trimmed mean.

extract from the source: A trimmed mean is obviously less susceptible to the effects of extreme scores than is the arithmetic mean. It is therefore less susceptible to sampling fluctuation than the mean for extremely skewed distributions. It is less efficient than the mean for normal distributions

Unless I missunderstood something, please correct me if I did (it's not quite clear explanation), then the statement in the articlee is contradictory here!

thanks, --Martindavidsigi 21:07, 27 June 2011 (UTC) — Preceding unsigned comment added by Martindavidsigi (talk • contribs)

The statement "Unless the underlying distribution is symmetric, the truncated mean of a sample is unlikely to produce an unbiased estimator for either the mean or the median." is not contradicting your cited article, it is however completely redundant. It could just as easily read: "the median of a sample is unlikely to produce an unbiased estimator for the mean." or "the mean of a sample is unlikely to produce an unbiased estimator for the median.", in other words the claimed draw back of the trimmed mean is that it is not the mean or the median, which is just silly; I will remove the whole section accordingly. --Unruffled haslett (talk) 19:07, 26 June 2023 (UTC)

The variance of the trimmed mean

This should probably be added to the article: https://www.sciencedirect.com/science/article/pii/016771529400052A

Tal Galili (talk) 10:33, 14 June 2020 (UTC)