128.135.100.106: /* The triangulated structure */

2013-10-23T19:32:40Z

The triangulated structure

← Older revision		Revision as of 21:32, 23 October 2013
Line 1:		Line 1:
	~~I would like~~ to ~~introduce myself to you~~, ~~I am Andrew~~ and ~~my wife doesn~~'~~t like it at all~~. ~~For years she~~'~~s been living~~ in ~~Kentucky but her husband wants them~~ to ~~move~~. ~~What me~~ and ~~my family love~~ is ~~performing ballet but I~~'~~ve been taking~~ on ~~new issues recently~~. ~~Invoicing~~ is ~~my occupation~~.<br><br>~~My blog post~~ ... [http://~~formalarmour~~.com/~~index~~.~~php?do~~=/~~profile-26947~~/~~info~~/ ~~best psychics~~]		In [[statistics]], the '''median absolute deviation (MAD)''' is a [[Robust statistics\|robust]] measure of the [[statistical dispersion\|variability]] of a [[univariate]] sample of [[quantitative data]]. It can also refer to the [[statistical population\|population]] [[parameter]] that is [[statistical estimation\|estimated]] by the MAD calculated from a sample.

			For a univariate data set ''X''<sub>1</sub>, ''X''<sub>2</sub>, ..., ''X<sub>n</sub>'', the MAD is defined as the [[median]] of the [[absolute deviation]]s from the data's median:

			:<math>
			\operatorname{MAD} = \operatorname{median}_{i}\left(\ \left\| X_{i} - \operatorname{median}_{j} (X_{j}) \right\|\ \right), \,
			</math>

			that is, starting with the [[Errors and residuals in statistics\|residuals]] (deviations) from the data's median, the MAD is the [[median]] of their [[absolute value]]s.

			==Example==

			Consider the data (1, 1, 2, '''2''', 4, 6, 9). It has a median value of 2. The absolute deviations about 2 are (1, 1, 0, 0, 2, 4, 7) which in turn have a median value of 1 (because the sorted absolute deviations are (0, 0, 1, '''1''', 2, 4, 7)). So the median absolute deviation for this data is 1.

			==Uses==
			The median absolute deviation is a measure of [[statistical dispersion]]. Moreover, the MAD is a [[robust statistic]], being more resilient to outliers in a data set than the [[standard deviation]]. In the standard deviation, the distances from the [[mean]] are squared, so large deviations are weighted more heavily, and thus outliers can heavily influence it. In the MAD, the deviations of a small number of outliers are irrelevant.

			Because the MAD is a more robust estimator of scale than the sample [[variance]] or [[standard deviation]], it works better with distributions without a mean or variance, such as the [[Cauchy distribution]].

			== Relation to standard deviation ==

			In order to use the MAD as a [[consistent estimator]] for the
			[[Scale_parameter#Estimation\|estimation]] of the [[standard deviation]] σ, one takes

			:<math>\hat{\sigma}=K\cdot \operatorname{MAD}, \, </math>

			where ''K'' is a constant [[scale factor]], which depends on the distribution.

			For normally distributed data ''K'' is taken to be 1/Φ<sup>−1</sup>(3/4) <math>\approx</math> 1.4826, where Φ<sup>−1</sup> is the inverse of the [[cumulative distribution function]] for the standard normal distribution, i.e., the [[quantile function]]. This is because the MAD is given by:

			:<math>\frac 12 =P(\|X-\mu\|\le \operatorname{MAD})=P\left(\left\|\frac{X-\mu}{\sigma}\right\|\le \frac {\operatorname{MAD}}\sigma\right)=P\left(\|Z\|\le \frac {\operatorname{MAD}}\sigma\right).</math>

			Therefore we must have that Φ(MAD/σ) − Φ(−MAD/σ) = 1/2. Since Φ(−MAD/σ) = 1 − Φ(MAD/σ) we have that MAD/σ = Φ<sup>−1</sup>(3/4) from which we obtain the scale factor K = 1/Φ<sup>−1</sup>(3/4).

			Hence

			:<math>\sigma \approx 1.4826\ \operatorname{MAD}. \, </math>

			In other words, the expectation of 1.4826 times the MAD for large samples of normally distributed ''X<sub>i</sub>'' is approximately equal to the population standard deviation.

			The factor <math>1.4826\ \approx 1/\left(\Phi^{-1}(3/4)\right)</math> results from the [[multiplicative inverse\|reciprocal]] of the [[Normal distribution\|normal]] [[inverse cumulative distribution function]], <math>\Phi^{-1}(P)</math>, evaluated at probability <math>P=3/4</math>.<ref>[http://books.google.com/books?id=i2bD50PbIikC&lpg=PA118&dq=1.4826&pg=PA118#v=onepage&q=1.4826&f=false]</ref>

			== The population MAD ==

			The population MAD is defined analogously to the sample MAD, but is based on the complete [[probability distribution\|distribution]] rather than on a sample. For a symmetric distribution with zero mean, the population MAD is the 75th [[percentile]] of the distribution.

			Unlike the [[population variance\|variance]], which may be infinite or undefined, the population MAD is always a finite number. For example, the standard [[Cauchy distribution]] has undefined variance, but its MAD is 1.

			The earliest known mention of the concept of the MAD occurred in 1816, in a paper by [[Carl Friedrich Gauss]] on the determination of the accuracy of numerical observations.<ref>{{cite journal
			\| last = Gauss \| first = Carl Friedrich \| authorlink = Carl Friedrich Gauss
			\| title = Bestimmung der Genauigkeit der Beobachtungen
			\| journal = Zeitschrift für Astronomie und verwandte Wissenschaften
			\| volume = 1 \| issue = \| pages = 187–197
			\| publisher = \| location = \| date = 1816 }}</ref><ref>{{cite book
			\| last = Walker \| first = Helen \| authorlink =
			\| title = Studies in the History of the Statistical Method
			\| publisher = Williams & Wilkins Co \| date = 1931 \| location = Baltimore, MD
			\| pages = 24–25 \| url = \| doi = \| isbn = }}</ref>

			==See also==
			* [[Deviation (statistics)]]
			* [[Robust measures of scale]]
			* MARD or [[mean absolute relative difference]]

			==Notes==
			{{reflist}}

			==References==

			* {{cite book \| last = Hoaglin \| first = David C. \| coauthors = Frederick Mosteller and John W. Tukey \| title = Understanding Robust and Exploratory Data Analysis \| publisher = John Wiley & Sons\| date = 1983 \| pages = 404–414 \| isbn = 0-471-09777-2 }}
			* {{cite book \| last = Russell\| first = Roberta S. \| coauthors = Bernard W. Taylor III. \| title = Operations Management \| publisher = John Wiley & Sons\| date = 2006 \| pages = 497–498 \| isbn = 0-471-69209-3 }}
			* {{cite book \| last = Venables \| first = W.N. \| coauthors = B.D. Ripley \| title = Modern Applied Statistics with S-PLUS \| publisher = Springer \| date = 1999 \| pages = 128 \| isbn = 0-387-98825-4 }}


			{{statistics}}
			[[Category:Statistical deviation and dispersion]]
			[[Category:Robust statistics]]

en>Wefdsf: /* Remarks */

2011-03-06T21:05:06Z

Remarks

New page

I would like to introduce myself to you, I am Andrew and my wife doesn't like it at all. For years she's been living in Kentucky but her husband wants them to move. What me and my family love is performing ballet but I've been taking on new issues recently. Invoicing is my occupation.<br><br>My blog post ... [http://formalarmour.com/index.php?do=/profile-26947/info/ best psychics]

Homotopy category of chain complexes - Revision history

128.135.100.106: /* The triangulated structure */

en>Wefdsf: /* Remarks */