Solved
Contributor
Posts: 30

# Clustering Categorical Variables

Hi,
Need some tips about how to do clustering for categorical variables.

Any epaper or thoughts are appreciated.

Thanks,

_kamal

Accepted Solutions
Solution
‎07-03-2017 09:53 AM
Posts: 5,049

## Re: Clustering Categorical Variables

Proc Corresp calculates coordinates for the levels of two or more categorical variables based on their crosstabulation. If you fed distances derived from those coordinates to Proc Cluster, you could cluster together the levels of two or more categorical variables. I never tried doing that.

PG

PG

All Replies
Posts: 5,049

## Re: Clustering Categorical Variables

You could use proc distance and choose a measure appropriate for nominal variables to get a distance matrix. Then use that distance matrix in proc cluster.

PG

PG
Posts: 2,655

## Re: Clustering Categorical Variables

I wonder if you could get the output from PROC CORRESP, or the necessary internal datasets, and feed those to PROC CLUSTER.

Steve Denham

Solution
‎07-03-2017 09:53 AM
Posts: 5,049

## Re: Clustering Categorical Variables

Proc Corresp calculates coordinates for the levels of two or more categorical variables based on their crosstabulation. If you fed distances derived from those coordinates to Proc Cluster, you could cluster together the levels of two or more categorical variables. I never tried doing that.

PG

PG
Contributor
Posts: 30

Thanks guys

New Contributor
Posts: 3

## Re: Clustering Categorical Variables

Hello,

I am also having a similar problem. As far as I can see using proc distance first and then apply Proc cluster seems appropriate.

What about in Miner? How can I do this with FASTCLUS and MODECLUS?

🔒 This topic is solved and locked.