k mean cluster vs proc rank

monster90 · Posted 07-30-2018 08:11 AM

Hi guys,

If I use proc rank with grouping function, what is the different between this method and the k mean clustering method?

Actually i do not see any other differentiation only that with using proc rank (with group) the procedure wants to divide the groups in equal part...

Thanks your answer,

Steve

mkeintz · Posted 07-30-2018 09:51 AM

I won't comment on k-means clustering method, but ...

proc rank cares about order, but not distance, however distance is defined. And of course this is associated with only permitting equal-size groups.
proc rank doesn't do multi-dimensional "clustering", however defined. I presume the clustering method does do multi-dimensional.

--------------------------
The hash OUTPUT method will overwrite a SAS data set, but not append. That can be costly. Consider voting for Add a HASH object method which would append a hash object to an existing SAS data set

Would enabling PROC SORT to simultaneously output multiple datasets be useful? Then vote for
Allow PROC SORT to output multiple datasets

--------------------------

PaigeMiller · Posted 07-30-2018 10:14 AM

PROC RANK computes ranks on individual variables.

K-mean clusters finds groupings of observations in your data set using multiple variables.

These don't do the same things.

--
Paige Miller

k mean cluster vs proc rank

Re: k mean cluster vs proc rank

Re: k mean cluster vs proc rank

k mean cluster vs proc rank

Re: k mean cluster vs proc rank

Re: k mean cluster vs proc rank

Registration is open

SAS Training: Just a Click Away