topic Re: Normalty transformation for cluster analysis in Statistical Procedures

Normalty transformation for cluster analysis

lionking19063 — Tue, 31 May 2016 20:49:47 GMT

Hi,

I am going to conduct a cluster analysis on some skewed data with K-means or hierarchical analysis method.I wonder if I need to do some variable tranformation on skewed variables to make them normal. Could someone provide some suggestion how to choose the tranformation method sicne there is no dependent varibale?

Thanks.

Re: Normalty transformation for cluster analysis

ballardw — Tue, 31 May 2016 21:00:01 GMT

You might look into Proc STDIZE to transform the variables before going to the cluster analysis.

But I would tend to take a quick look at the data using FASTCLUS before transforming to see if you get something interesting first. You may not need to transform if the units of measure are similar for all of the variables.

Re: Normalty transformation for cluster analysis

PGStats — Tue, 31 May 2016 21:51:33 GMT

If your data is clustered (with more than one cluster) then it cannot be multinormal. Transformations can help homogenize cluster covariances, but shouldn't aim at normalizing the data.

Re: Normalty transformation for cluster analysis

Reeza — Tue, 31 May 2016 21:51:55 GMT

I think it's more important to make sure the scales are the same or comparable than for normality.

The assumptions for clustering depend on what type of clustering you intend to implement.

http://stats.stackexchange.com/questions/8148/assumptions-of-cluster-analysis

Re: Normalty transformation for cluster analysis

Ksharp — Wed, 01 Jun 2016 01:02:15 GMT

Box-Cox transformation is used for Normal transformation . Check PROC TRANSREG.

TRANSREG fits univariate and multivariate linear models, optionally with spline, Box-Cox, and
other nonlinear transformations. Models include regression and ANOVA, conjoint
analysis, preference mapping, redundancy analysis, canonical correlation, and penalized
B-spline regression. PROC TRANSREG supports CLASS variables.

Re: Normalty transformation for cluster analysis

lionking19063 — Wed, 01 Jun 2016 01:11:42 GMT

Dose Box-Cox transformation require dependent variable? However, There is no dependent variable in my cluster analysis.

Re: Normalty transformation for cluster analysis

lionking19063 — Wed, 01 Jun 2016 01:15:13 GMT

I saw someone did the transformation before standardization. Not sure if it makes sense or not.

Re: Normalty transformation for cluster analysis

Ksharp — Wed, 01 Jun 2016 01:28:09 GMT

No. I think it does not require dependent variable.

Interesting thing is you also can use PROC MCMC to do it .Check its example.

Example 73.2: Box-Cox Transformation