You are on page 1of 4

Absolute deviation

From Wikipedia, the free encyclopedia

In statistics, the absolute deviation of an element of a data set is the absolute difference between that element and a given point. Typically the point from which the deviation is measured is a measure of central tendency, most often the median or sometimes the mean of the data set.

Di = | xi − m(X) |
where Di is the absolute deviation, x i is the data element and m(X) is the chosen measure of central tendency of the data set—sometimes the mean ( ), but most often the median.

1 Measures of dispersion 1.1 Average absolute deviation 1.1.1 Mean absolute deviation 1.2 Median absolute deviation (MAD) 1.3 Maximum absolute deviation 2 Minimization 3 Estimation 4 See also 5 External links

Measures of dispersion
Several measures of statistical dispersion are defined in terms of the absolute deviation.

Average absolute deviation
The average absolute deviation, or simply average deviation of a data set is the average of the absolute deviations and is a summary statistic of statistical dispersion or variability. It is also called the mean absolute deviation, but this is easily confused with the median absolute deviation. The average absolute deviation of a set {x 1, x 2, ..., x n } is

The choice of measure of central tendency, m(X), has a marked effect on the value of the average deviation. For example, for the data set {2, 2, 3, 4, 14}:

8 times the standard deviation. The equation for MAD is as follows: MAD = 1/n ∑(|ei|) . is the mean of the absolute deviations of a set of data about the data’s mean.Di Median absolute deviation (MAD) Main article: Median absolute deviation The median absolute deviation is the median of the absolute deviation from the median. Mean absolute deviation The mean absolute deviation (MAD). . Thus if X is a normally distributed random variable with expected value 0 then In other words.Di This method forecast accuracy is very closely related to the mean squared error (MSE) method which is just the average squared error of the forecasts. For the normal or "Gaussian" distribution. for a Gaussian. the ratio of mean absolute deviation to standard deviation is . also referred to as the mean deviation. In fact. where ei = Fi . In other words. Although these methods are very closely related MAD is more commonly used because it does not require squaring.Measure of central tendency m (X) Mean = 5 Median = 3 Mode = 2 Average absolute deviation The average absolute deviation from the median is less than or equal to the average absolute deviation from the mean. The equation for MSE is as follows: MSE = 1/n Σ(ei2) . it is the average distance of the data set from its mean during certain number of time periods. where ei = Fi . the average absolute deviation from the median is always less than or equal to the average absolute deviation from any other fixed number. It is a robust estimator of dispersion. mean absolute deviation is about 0. one way of proving this relies on Jensen's inequality. The average absolute deviation from the mean is less than or equal to the standard deviation.

The average of all the sample standard deviations of size 3 that can be drawn from the population is 40/81. Estimation The mean absolute deviation of a sample is a biased estimator of the mean absolute deviation of the population. in this case unaffected by the value of the outlier 14. the midhinge (average of first and third quartiles) which minimizes the median absolute deviation of the whole distribution.For the example {2. 1. See also Deviation (statistics) Errors and residuals in statistics Least absolute deviations Loss function Median absolute deviation External links Advantages of the mean absolute deviation (http://www. Therefore the absolute deviation is a biased estimator. 2.wikipedia. the expected value (average) of all the sample absolute deviations must equal the population absolute deviation. It is realized by the sample maximum or sample minimum and cannot be less than half the range.htm) Retrieved from "http://en. 4. in that L2 norm statistics just as the mean minimizes the standard deviation. it does not. 1. also minimizes the maximum absolute deviation of the distribution after the top and bottom 25% have been trimmed off. 3.leeds. 1. In order for the absolute deviation to be an unbiased estimator. so the absolute deviations from the median are {1. 14}: 3 is the median. Maximum absolute deviation The maximum absolute deviation about a point is the maximum of the absolute deviations of a sample from that point. For the population 1. 0.3 the population absolute deviation is 2/3. 11}) with a median of 1. and trimmed L∞ norm statistics for example. 11} (reordered as {0. so the median absolute deviation (also called MAD) is 1." Categories: Statistical deviation and dispersion . ∞ norm statistics L the mid-range minimizes the maximum absolute deviation.2. Minimization The measures of statistical dispersion derived from absolute deviation characterize various measures of central tendency as minimizing dispersion: The median is the measure of central tendency most associated with the absolute deviation. L1 norm statistics the median minimizes average absolute deviation.

Inc. Text is available under the Creative Commons Attribution-ShareAlike License. See Terms of use for details. a non-profit organization. additional terms may apply..This page was last modified on 6 September 2011 at 23:27. Wikipedia® is a registered trademark of the Wikimedia Foundation. .