Difference between revisions of "Outlier index - DatLab"
Line 1: | Line 1: | ||
{{MitoPedia | {{MitoPedia | ||
|abbr=''OI'' | |abbr=''OI'' | ||
|description=An '''outlier index''' (''OI'') is defined for DatLab analysis, derived from [http://www.statisticshowto.com/pearsons-coefficient-of-skewness/ Pearson’s coefficient of skewness], but more specific in targeting outliers in data series recorded with the O2k. At the limit of a zero value, ''Y'' = ABS( | |description=An '''outlier index''' (''OI'') is defined for DatLab analysis, derived from [http://www.statisticshowto.com/pearsons-coefficient-of-skewness/ Pearson’s coefficient of skewness], but more specific in targeting outliers in data series recorded with the O2k. At the limit of a zero value, ''Y'' = ABS(Average + Median)/2, the ''OI'' equals Pearson’s coefficient of skewness #2 (without the multiplication factor of 3). At high ''Y'' with small standard deviation (SD), the outlier index is effectively the difference between the Average and the Median normalized for the absolute value, (Average-Median)/''Y''. The definition of the outlier index is, | ||
: ''OI'' = ( | : ''OI'' = (Average-Median)/(''Y'' + SD) | ||
: ''OI'' = ( | : ''OI'' = (Average-Median)/[ABS(Average+Median)/2 + SD] | ||
By comparison, | |||
: Pearson’s coefficient of skewness #2 = 3 x (Average-Median)/SD | |||
The threshold of the absolute value of the ''OI'' is set at 0.05. If ABS(''OI'')>0.05 calculated for the data points within a defined [[Marks in DatLab |mark]], the Mark window indicates the likely occurrence of outliers in the data sequence. The threshold can be set to a lab-specific or session-specific value different from the default value. | The threshold of the absolute value of the ''OI'' is set at 0.05. If ABS(''OI'')>0.05 calculated for the data points within a defined [[Marks in DatLab |mark]], the Mark window indicates the likely occurrence of outliers in the data sequence. The threshold can be set to a lab-specific or session-specific value different from the default value. | ||
Line 15: | Line 19: | ||
|mitopedia O2k and high-resolution respirometry=DatLab | |mitopedia O2k and high-resolution respirometry=DatLab | ||
}} | }} | ||
Communicated by [[Gnaiger E]] 2016-10-03 | Communicated by [[Gnaiger E]] 2016-10-03; updated 2016-10-22. | ||
== Outlier == | == Outlier == | ||
::::» [[Outlier]] | ::::» [[Outlier]] | ||
::::» [http://www.statisticshowto.com/pearsons-coefficient-of-skewness/ Pearson’s coefficient of skewness], [https://ww2.amstat.org/publications/jse/v19n2/doane.pdf Doane_2011_J Statistics Education: Measuring skewness: a forgotten statistic?] | ::::» [http://www.statisticshowto.com/pearsons-coefficient-of-skewness/ Pearson’s coefficient of skewness], [https://ww2.amstat.org/publications/jse/v19n2/doane.pdf Doane_2011_J Statistics Education: Measuring skewness: a forgotten statistic?] |
Revision as of 10:47, 22 October 2016
Description
An outlier index (OI) is defined for DatLab analysis, derived from Pearson’s coefficient of skewness, but more specific in targeting outliers in data series recorded with the O2k. At the limit of a zero value, Y = ABS(Average + Median)/2, the OI equals Pearson’s coefficient of skewness #2 (without the multiplication factor of 3). At high Y with small standard deviation (SD), the outlier index is effectively the difference between the Average and the Median normalized for the absolute value, (Average-Median)/Y. The definition of the outlier index is,
- OI = (Average-Median)/(Y + SD)
- OI = (Average-Median)/[ABS(Average+Median)/2 + SD]
By comparison,
- Pearson’s coefficient of skewness #2 = 3 x (Average-Median)/SD
The threshold of the absolute value of the OI is set at 0.05. If ABS(OI)>0.05 calculated for the data points within a defined mark, the Mark window indicates the likely occurrence of outliers in the data sequence. The threshold can be set to a lab-specific or session-specific value different from the default value.
Abbreviation: OI
MitoPedia concepts: "MitoFit Quality Control System" is not in the list (MiP concept, Respiratory state, Respiratory control ratio, SUIT concept, SUIT protocol, SUIT A, SUIT B, SUIT C, SUIT state, Recommended, ...) of allowed values for the "MitoPedia concept" property.
MitoFit Quality Control System"MitoFit Quality Control System" is not in the list (Enzyme, Medium, Inhibitor, Substrate and metabolite, Uncoupler, Sample preparation, Permeabilization agent, EAGLE, MitoGlobal Organizations, MitoGlobal Centres, ...) of allowed values for the "MitoPedia topic" property.
MitoPedia O2k and high-resolution respirometry:
DatLab
Communicated by Gnaiger E 2016-10-03; updated 2016-10-22.