|
> From: Aj [mailto:ajaya_u2002@YAHOO.COM]
> I am trying to find the ways to find outliers in data. I have
> used proc univariate option.
>
> I would like to know simple options where I can find easily.
> I would appriciate your time.
SAS Books By User author Ron Cody
has a book which explains how to use various procedures to produce your
-- what's the right word here?: threshhold or limit --
basically you run a proc
assign the limit to a macro variable
and then check your data for rows above/below the limit
keyword: algorithm method OOP return an object
something like:
%LET LIBREF = LIBRARY;
%LET DATA = MYDATA;
%LET VAR = Var-A;
%LET OP = lt;%*less than;
%LET OP = le;%*less than or equal;
%LET OP = gt;%*greater than;
%LET OP = ge;%*greater than or equal;
proc SOMETHING data = &LIBREF..&DATA.;
*number-crunching happens here to &VAR.;
out = LIMIT
(keep = Limit);
%*assign Limit to macro variable;
DATA _NULL_;
set LIMIT;
call symput('LIMIT',Limit);
stop;run;
%*or;
proc SQL noprint;
select Limit
into :LIMIT
from WORK.LIMIT
;quit;
%PUT LIMIT<&LIMIT.>;
PROC PRINT data = &LIBREF..&DATA.
(where = (&VAR. &OP. &LIMIT.
));
TITLE "&LIBREF..&DATA. &VAR. &OP. &LIMIT.";
run;
for a summary report of values in a data set that are not defined by formats
see my paper
NESUG 2001
Adv Tutor pg 53
%INVALID: a data review macro
using proc FORMAT option other=INVALID to identify and list outliers
http://www.pace.edu/nesug/proceedings/nesug01/at/At1008.pdf
for use of statistical procedures
see my colleague Handsfield's paper:
check our most excellent archives:
http://www.listserv.uga.edu/archives/sas-l.html
search for:
subject contains: outliers
author's address: RJF2
since: Jan 2003
until: Jan 2003
Ron Fehd the macro maven CDC Atlanta GA USA RJF2@cdc.gov
| 
