rare event" and similar cases.
Martin
> -
> David L Carlson
> Associate Professor of Anthropology
> Texas A&M University
> College Station, TX 77840-4352
> -Original Message-
> From: Li, Yan [
Thanks David, This is very useful!
-Original Message-
From: David Carlson [mailto:dcarl...@tamu.edu]
Sent: Tuesday, August 06, 2013 11:27 AM
To: Li, Yan; r-help@r-project.org
Subject: RE: [R] algorithm for clustering categorical data
What do you mean by representing the categorical
ases.
Martin
> -
> David L Carlson
> Associate Professor of Anthropology
> Texas A&M University
> College Station, TX 77840-4352
> -Original Message-
> From: Li, Yan [mailto:yan...@ibi.com]
> Sent: T
--
David L Carlson
Associate Professor of Anthropology
Texas A&M University
College Station, TX 77840-4352
-Original Message-
From: Li, Yan [mailto:yan...@ibi.com]
Sent: Tuesday, August 6, 2013 9:36 AM
To: dcarl...@tamu.edu; r-help@r-project.org
Subject: RE: [R] algorithm for clu
hat is the draw back?
Thanks you,
Yan
-Original Message-
From: David Carlson [mailto:dcarl...@tamu.edu]
Sent: Thursday, August 01, 2013 12:08 PM
To: Li, Yan; r-help@r-project.org
Subject: RE: [R] algorithm for clustering categorical data
Read up on Gower's Distance measures (a
c: r-help@r-project.org
Subject: Re: [R] algorithm for clustering categorical data
On Aug 1, 2013, at 9:00 AM, Li, Yan wrote:
> Hi All,
>
> Does anyone know what algorithm for clustering categorical variables?
> R packages?
Many.
http://cran.r-project.org/web/views/Cluster.html
&g
On Aug 1, 2013, at 9:00 AM, Li, Yan wrote:
> Hi All,
>
> Does anyone know what algorithm for clustering categorical variables? R
> packages?
Many.
http://cran.r-project.org/web/views/Cluster.html
> Which is the best?
For what purpose?
>
> If a data has both numeric and categorical data, wh
: RE: [R] algorithm for clustering categorical data
Read up on Gower's Distance measures (available in the ecodist
package) which can combine numeric and categorical data. You didn't give us any
information about how you numerically transformed the categorical variables,
but the usual a
Read up on Gower's Distance measures (available in the ecodist
package) which can combine numeric and categorical data. You
didn't give us any information about how you numerically
transformed the categorical variables, but the usual approach
is to create indicator variables that code presence/abse
9 matches
Mail list logo
