madOutPair {factDesign}R Documentation

A function to determine if the pair with the largest difference between replicates is the result of a single outlier.

Description

This function is intended to be used in conjunction with outlierPair. After outlierPair detects a pair of replicate observations with a significantly large difference between the observations, madOutPair uses median absolute deviation criteria for determining if one of the replicates is a single outlier.

Usage

madOutPair(x, whichPair, c = 4)

Arguments

x A vector of observations.
whichPair A result of outlierPair, recording which pair has largest difference between replicate observations.
c The number of median absolute deviations to be used as a cutoff for determining single outliers.

Details

Once pairs with significantly large differences are identified using outlierPair, madOutPair is applied. If only one of the tagged replicates falls outside the range of (med(x)-c*mad(x),med(x)+c*mad(x)), the observation is designated the single outlier.

Value

The index of the single outlier observation, or "NA" if no single outliers are detected.

Author(s)

Denise Scholtens

References

Scholtens et al. Analyzing Factorial Designed Microarray Experiments. Journal of Multivariate Analysis. To appear.

See Also

outlierPair

Examples


data(estrogen)
outP <- outlierPair(exprs(estrogen)[247,],INDEX=pData(estrogen))[["whichPair"]]
madOutPair(exprs(estrogen)[247,],outP)
outP <- outlierPair(exprs(estrogen)[495,],INDEX=pData(estrogen))[["whichPair"]]
madOutPair(exprs(estrogen)[495,],outP)


[Package Contents]