University of Rochester Medical Center
SearchDirectoryNewsEventsStrong HealthURMC Home

SAS Helpful Hints

Biostat Macro Library

Finding Multivariate Outliers

%Outliers resides in the departments SAS Macro Library and is enabled with the following SAS statements:

Libname biostat '\\BIO2\example\SASMacrosWindows';
Options Mstored SasMstore=biostat;

%Outliers uses Proc PLS(Partial Least Squares) to find multivariate outliers in a dataset. It creates scatterplots of tsquare and qres along with barcharts of the outling observations to show which variables are responsible for creating the outlier.

Syntax:
%Outliers(dataset,factor,varlist);
    dataset:       Dataset to use.
    factor:         Factor of the standard deviation that defines an outlier.
    varlist:         List of variables to Boxplot(All Numeric).

Example:
%Outliers(work.A,4.0,A B C D E);

The default font of centx may be changed on all text by defining a macro variable named “Font”:

%Let Font=Simplex;

 

Please send your comments and suggestions about this web page to A. Watts (watts@bst.rochester.edu)