<div dir="ltr"><div>There are multiple methods for determining the 'optimal' number of clusters.<br>The issue is ... which one?<br><br>A statistician was asked for suggestions. In classic 'statistician-speak', he
rambled on about assorted methods to estimate the optimal number of
clusters. It was a bit confusing. Esentially, his answer was 'try a
bunch and see what you like.'<br><br></div>NCL is not 'R' or Matlab or .... NCL can not provide and support multiple methods. NCL would like to include one optimal cluster function. BUT don't have the time
to really look at this issue. However, if you find something you like,
we will see what we can do.uses
clustering ("classification") methods. <br><div><div><br>===<br><br>Several papers, which uses classification/clustering are: <br><br><a href="http://www.cgd.ucar.edu/staff/cdeser/docs/cassou.natlregimes.jclim04.pdf" target="_blank">http://www.cgd.ucar.edu/staff/<wbr>cdeser/docs/cassou.<wbr>natlregimes.jclim04.pdf</a><br></div><div>**See Part 2 (Classification)**<br></div><div><br><a href="http://www.nature.com/nature/journal/v455/n7212/full/nature07286.html" target="_blank">http://www.nature.com/nature/<wbr>journal/v455/n7212/full/<wbr>nature07286.html</a><br><br><a href="ftp://ftp.cerfacs.fr/pub/globc/exchanges/cassou/DCLIM/cassou_et_al_climdyn_regime_ocean_part1.pdf" target="_blank">ftp://ftp.cerfacs.fr/pub/<wbr>globc/exchanges/cassou/DCLIM/<wbr>cassou_et_al_climdyn_regime_<wbr>ocean_part1.pdf</a><br><br><br></div><div>HTH<br></div><div>D<br></div><br><br></div></div><div class="gmail_extra"><br><div class="gmail_quote">On Wed, Aug 17, 2016 at 7:02 AM, Carl Schreck <span dir="ltr"><<a href="mailto:cjschrec@ncsu.edu" target="_blank">cjschrec@ncsu.edu</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr">I'm just starting to play around with the new <a href="http://www.ncl.ucar.edu/Document/Functions/Built-in/kmeans_as136.shtml" target="_blank">kmeans_as136</a> function. I'm very much a novice at clustering and am wondering if anyone has used this function and has guidance on how best to choose the number of clusters. <div><br></div><div>Most of what I'm finding is similar to <a href="https://en.wikipedia.org/wiki/Determining_the_number_of_clusters_in_a_data_set" target="_blank">this wikipedia article</a>. I think the elbow method is the only one that we can do with the output from kmeans_as136, but I'm not exactly sure how to relate ss2 to %variance.</div><div><br></div><div>I'm sure this is simple and I've just not read up enough on it, but I figured I'd ask you guys. Thanks!</div><div><br></div><div>Carl<br clear="all"><div><br></div>-- <br><div data-smartmail="gmail_signature"><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><br><table style="max-width:100%;border-collapse:collapse;border-spacing:0px;color:rgb(51,51,51);font-size:14px;border:3px solid rgb(170,170,170);font-family:Times;line-height:12px;background-color:transparent" border="0" cellpadding="2" cellspacing="2"><tbody><tr><td height="71" align="center" width="71"><span style="font-size:11px"><span style="font-family:arial,helvetica,sans-serif"><a href="http://www.cicsnc.org/" style="color:rgb(38,58,143);text-decoration:none;font-weight:bold" target="_blank"><img src="http://www.cicsnc.org/assets/images/cicsnc-logo.png" height="93" width="96"></a> <a href="http://www.researcherid.com/rid/B-8711-2011" target="_blank"><br></a></span></span><br><font size="4"><b style="text-align:start;color:rgb(38,58,143);font-family:arial,helvetica,sans-serif"> <a href="http://www.cyclonecenter.org/" style="color:rgb(38,58,143);text-decoration:none" target="_blank">Cyclone</a></b><a href="http://www.cyclonecenter.org/" style="text-align:start;color:rgb(38,58,143);font-family:arial,helvetica,sans-serif;text-decoration:none" target="_blank">Center.org</a> </font></td><td valign="top"><span style="font-size:11px"><span style="font-family:arial,helvetica,sans-serif"><b>Carl J. Schreck III, PhD</b><br></span></span><span style="font-size:11px"><span style="font-family:arial,helvetica,sans-serif"><b>Research Scholar / Research </b></span></span><b style="font-family:arial,helvetica,sans-serif;font-size:11px">Assistant Professor</b><span style="font-size:11px"><span style="font-family:arial,helvetica,sans-serif"><br></span></span><a href="http://www.cicsnc.org/" style="font-family:arial,helvetica,sans-serif;font-size:11px;color:rgb(38,58,143);text-decoration:none;font-weight:bold" target="_blank">Cooperative Institute for Climate and Satellites NC (CICS</a><b><a href="http://www.cicsnc.org/" style="font-family:arial,helvetica,sans-serif;font-size:11px;color:rgb(38,58,143);text-decoration:none" target="_blank">-NC)</a> /</b><br><span style="font-size:11px"><span style="font-family:arial,helvetica,sans-serif"><a href="https://meas.sciences.ncsu.edu/" style="color:rgb(38,58,143);text-decoration:none;font-weight:bold" target="_blank">Department of Marine, Earth, and Atmospheric Sciences (MEAS)</a> <br><a href="http://ncsu.edu/" style="color:rgb(38,58,143);text-decoration:none;font-weight:bold" target="_blank">North Carolina State University</a><br><a href="http://ncei.noaa.gov/" style="color:rgb(38,58,143);text-decoration:none;font-weight:bold" target="_blank">NOAA National Centers for Environmental Information (NCEI)</a><br>151 Patton Ave, Asheville, NC 28801<br>e: </span></span><a href="mailto:carl_schreck@ncsu.edu" style="color:rgb(38,58,143);font-family:arial,helvetica,sans-serif;font-size:11px;text-decoration:none;font-weight:bold" target="_blank">carl_schreck@ncsu.edu</a><br style="font-family:arial,helvetica,sans-serif;font-size:11px"><span style="font-size:11px"><span style="font-family:arial,helvetica,sans-serif">o: <a href="tel:%2B1%20828%20257%203140" value="+18282573140" target="_blank">+1 828 257 3140</a><br></span></span><span style="font-family:arial,helvetica,sans-serif;font-size:11px">c: <a href="tel:%2B1%20828%20484%201702" value="+18284841702" target="_blank">+1 828 484 1702</a><br></span><a href="http://scholar.google.com/citations?hl=en&user=th8ONEcAAAAJ&view_op=list_works&sortby=pubdate" style="color:rgb(38,58,143);font-family:arial,helvetica,sans-serif;font-size:11px;text-decoration:none;font-weight:bold" target="_blank">Publications</a><br><a href="http://monitor.cicsnc.org/mjo/" style="color:rgb(38,58,143);font-family:arial,helvetica,sans-serif;font-size:11px;text-decoration:none;font-weight:bold" target="_blank">monitor.cicsnc.org/mjo</a><br style="font-family:arial,helvetica,sans-serif;font-size:11px"></td></tr></tbody></table></div></div></div></div></div></div></div></div></div></div></div></div></div></div></div></div></div></div></div></div></div></div></div></div></div></div>
</div></div>
<br>______________________________<wbr>_________________<br>
ncl-talk mailing list<br>
<a href="mailto:ncl-talk@ucar.edu">ncl-talk@ucar.edu</a><br>
List instructions, subscriber options, unsubscribe:<br>
<a href="http://mailman.ucar.edu/mailman/listinfo/ncl-talk" rel="noreferrer" target="_blank">http://mailman.ucar.edu/<wbr>mailman/listinfo/ncl-talk</a><br>
<br></blockquote></div><br></div>