topic clustering similar behaviour in SAS Procedures https://communities.sas.com/t5/SAS-Procedures/clustering-similar-behaviour/m-p/48210#M13029 <HTML><HEAD></HEAD><BODY><P>Hi,&nbsp; I am doing a time series (Autoreg) model, which I have over 100 models with 10 years of monthly data.&nbsp; I have auto prices to over 100 FS's (FS are the 2 digits of a Canadian postal code eg. D2).&nbsp; I don't want to make 100 models so I need to find what FS's have prices movements in common that I can group them all, but also some cases where it is important to leave some open FS's to more granularity such as FSA's (the first 3 letters of the postal code, eg. D2Y)....so for example leave M5R, M5T, M5H..&nbsp; hope I've made it simple enough for a good answer.&nbsp; I basically need a procedure in SAS that allows me to close up some FS (commonality) and leave some open (more detail)..&nbsp; I was wondering if VARCLUS could work, or any other.&nbsp;&nbsp; Thanks</P><P></P><P>sample data</P><P></P><P><STRONG style=": ; color: #333333; text-decoration: underline;">FS&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; FSA</STRONG></P><P>M5&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; M5R</P><P>M5&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; M5T</P><P>M5&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; M5H</P><P>M4&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; M4R</P><P>M4&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; M4E</P><P>D2&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; D2K</P><P>D2&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; D2L</P><P>D4&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; D4G </P><P>D3&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; D3F</P><P></P><P>look something like this </P><P></P><P><STRONG style=": ; color: #333333; text-decoration: underline;">FS&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; FSA</STRONG></P><P>M5&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; M5O&nbsp;&nbsp;&nbsp; &lt;- was M5 and M4&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; </P><P>D2&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; D2K</P><P>D2&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; D2L</P><P>D4&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; D4O&nbsp;&nbsp;&nbsp; &lt;- was D4 and D3</P></BODY></HTML> Wed, 16 Nov 2011 03:55:18 GMT podarum 2011-11-16T03:55:18Z clustering similar behaviour https://communities.sas.com/t5/SAS-Procedures/clustering-similar-behaviour/m-p/48210#M13029 <HTML><HEAD></HEAD><BODY><P>Hi,&nbsp; I am doing a time series (Autoreg) model, which I have over 100 models with 10 years of monthly data.&nbsp; I have auto prices to over 100 FS's (FS are the 2 digits of a Canadian postal code eg. D2).&nbsp; I don't want to make 100 models so I need to find what FS's have prices movements in common that I can group them all, but also some cases where it is important to leave some open FS's to more granularity such as FSA's (the first 3 letters of the postal code, eg. D2Y)....so for example leave M5R, M5T, M5H..&nbsp; hope I've made it simple enough for a good answer.&nbsp; I basically need a procedure in SAS that allows me to close up some FS (commonality) and leave some open (more detail)..&nbsp; I was wondering if VARCLUS could work, or any other.&nbsp;&nbsp; Thanks</P><P></P><P>sample data</P><P></P><P><STRONG style=": ; color: #333333; text-decoration: underline;">FS&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; FSA</STRONG></P><P>M5&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; M5R</P><P>M5&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; M5T</P><P>M5&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; M5H</P><P>M4&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; M4R</P><P>M4&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; M4E</P><P>D2&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; D2K</P><P>D2&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; D2L</P><P>D4&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; D4G </P><P>D3&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; D3F</P><P></P><P>look something like this </P><P></P><P><STRONG style=": ; color: #333333; text-decoration: underline;">FS&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; FSA</STRONG></P><P>M5&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; M5O&nbsp;&nbsp;&nbsp; &lt;- was M5 and M4&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; </P><P>D2&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; D2K</P><P>D2&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; D2L</P><P>D4&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; D4O&nbsp;&nbsp;&nbsp; &lt;- was D4 and D3</P></BODY></HTML> Wed, 16 Nov 2011 03:55:18 GMT https://communities.sas.com/t5/SAS-Procedures/clustering-similar-behaviour/m-p/48210#M13029 podarum 2011-11-16T03:55:18Z