topic problem with sas code in Statistical Procedures

problem with sas code

atulsingh — Mon, 10 Jul 2017 12:27:23 GMT

Hi all,

I have analysed the correlation between two variables: hp and cyl and i'm writing a code for cluster analysis for the same varibles but ending up with error, need help. The code is:

proc corr data=rank_mtcars out=cluster_mtcars; /*Here rank_mtcars is a predefined dataset*/
var hp cyl;run;
proc cluster data= cluster_mtcars method=centroid rmsstd
outtree=cluster_mtcars;
var cyl hp;run;

ERROR: TYPE=ACE, CORR, COV, EST, FACTOR, SSCP, UCORR, or UCOV data sets must be converted to TYPE=DISTANCE. Note that CLUSTER

ignores the _NAME_ and _TYPE_ variables, if any.

Re: problem with sas code

PaigeMiller — Mon, 10 Jul 2017 12:41:10 GMT

Don't you want to do the clustering on the original data set rank_mtcars? It doesn't make sense to me to cluster the correlation matrix.

Re: problem with sas code

atulsingh — Mon, 10 Jul 2017 12:46:54 GMT

Thanks Sir.

One more question: After clustering i got the output as dendogram.

How to obtain the optimum number of clusters from the dendogram?

Re: problem with sas code

PaigeMiller — Mon, 10 Jul 2017 12:52:42 GMT

PROC CLUSTER documentation explains the common ways to do this:

http://documentation.sas.com/?cdcId=statcdc&cdcVersion=14.2&docsetId=statug&docsetTarget=statug_cluster_gettingstarted.htm&locale=en

Re: problem with sas code

atulsingh — Mon, 10 Jul 2017 12:53:42 GMT

Thanks Sir..!!

Re: problem with sas code

Ksharp — Mon, 10 Jul 2017 13:03:07 GMT

BTW, Maybe you need 1-rho to make CORR matrix looks like Distance matrix .

Re: problem with sas code

vijaylaxmi — Wed, 09 Jan 2019 01:41:49 GMT

Hi,

Can you please provide me dataset rank_mtcars. I am not able to find it anywhere.

Thanks!!

Vijay