Label or score outliers in R -
i'm looking easy use algorithms in r label (outlier or not) or score (say, 7.5) outliers row-wise. meaning, have matrix m
contains several rows , want identify rows represent outliers compared other rows.
m <- matrix( data = c(1,1,1,0,0,0,1,0,1), ncol = 3 )
to illustrate more, want compare (complete) rows in matrix each other spot outliers.
here's simple outlier detection (using either boxplot statistics or quantiles of data) wrote few years ago.
but, noted, helpful if you'd describe problem greater precision.
edit:
also want row-wise outliers. mean you're interested in identifying whole rows vs observations within variable (as typically done)? if so, you'll want use sort of distance metric, though metric choose depend on data.
Comments
Post a Comment