split.MADOutlier: Outliers using left and right MAD

Description Usage Arguments Details Value References Examples

Description

Identify features with outliers using left and right median absolute deviation (MAD).

Usage

1
splitMADOutlier(mat, filter0 = TRUE, threshold = 2)

Arguments

mat

mxn matrix of -omics data, where rows are features and columns samples.

filter0

Option to filter out features if they have at least one 0 value. Default is TRUE.

threshold

Threshold of how many MADs outside the left or right median is used to determine features with outliers.

Details

The purpose of this function is to determine outliers in non-symmetric distributions. The distribution is split by the median. Outliers are identifed by being however many median absolute deviations (MAD) from either split distribution.

Value

mat.filtered

Input matrix where features with outliers filtered out.

index

Index of features that have no outliers.

References

Leys C, Klein O, Bernard P and Licata L. "Detecting Outliers: Do Not Use Standard Deviation Around the Mean, Use Absolute Deivation Around the Median." Journal of Experimental Social Psychology, 2013. 49(4), 764-766. Magwene, PM, Willis JH, Kelly JK and Siepel A. "The Statistics of Bulk Segregant Analysis Using Next Generation Sequencing." PLoS Computational Biology, 2011. 7(11), e1002255.

Examples

1
2
3
4
5
## Simulate matrix of continuous -omics data.
data(TCGA_Breast_miRNASeq)

## Filter matrix based on outliers.
mat.filtered <- splitMADOutlier(TCGA_Breast_miRNASeq)$mat.filtered

discordant documentation built on Nov. 8, 2020, 4:52 p.m.