outlier: Multivariate outlier detection

In GabrielHoffman/dreamlet: Scalable differential expression analysis of single cell transcriptomics datasets with complex study designs

Multivariate outlier detection

Description

Detect multivariante outliers using Mahalanobis distance using mean and covariance estimated either with standard or robust methods.

Usage

outlier(data, robust = FALSE, ...)

Arguments

data	matrix of data
robust	use robust covariance method, defaults to FALSE
...	arguments passed to MASS::cov.rob()

Details

The distance follow a chisq distrubtion under the null with standard method for mean and covariance. It is approximate if the robust method is used. So use qchisq(p = 0.999 , df = k) to get cutoff to keep 99.9% of samples under the null for data with k=2 columns.

Value

data.frame storing chisq and z-score for each entry indicating deviation from the mean. The z-score is computed by evaluating the p-value of chisq statistic and converting it into a z-score

Examples

data <- matrix(rnorm(200), 100, 2)

res <- outlier(data)

res[1:4,]

GabrielHoffman/dreamlet documentation built on May 20, 2024, 2:05 p.m.