Google

A key characteristic of the mean is its high sensitivity to extreme scores, or outliers. In highly skewed distributions, the mean is pulled away from the median in the direction of the skew (the longer tail). Because extreme scores heavily influence its value, the mean may cease to be an accurate representation of the typical score in such datasets, leading researchers to often prefer the median for skewed distributions.

Sensitivity of the Mean to Outliers

A real estate agent is marketing a neighborhood of 10 homes. Nine of the homes are valued at approximately $200,000 each, while one newly built mansion is valued at $3,200,000. The agent advertises the 'average home value' in the neighborhood as $500,000. Which statement best evaluates the agent's use of this figure?

Consider a dataset of four reaction times: $$200$$, $$250$$, $$280$$, and $$250$$ milliseconds (ms), which has a mean of $$245$$ ms. If an outlier score of $$5,000$$ ms is added—perhaps due to participant inattention—the mean drastically increases to $$1,445$$ ms. This new mean is larger than $$80\%$$ of the scores in the dataset, demonstrating how a single extreme outlier can pull the mean so far that it no longer accurately represents the typical behavior in the distribution.

Example of the Mean's Sensitivity to Outliers

In a highly skewed distribution, how does the presence of extreme scores typically affect the mean?

In a distribution of reaction times, the mean will typically be more significantly shifted by the presence of a few extreme outliers than the median will.

Learn Before

Related