<html><head>
<meta name="Generator" content="Novell Groupwise Client (Version 14.0.1 Build: 118418)">
<meta http-equiv="Content-Type" content="text/html; charset=utf-8"></head>
<body style="font: 10pt/normal Segoe UI; margin: 16px 16px 4px; font-size-adjust: none; font-stretch: normal;"><div class="GroupWiseMessageBody" id="GroupWiseSection_1433933505000_Gerhard.Wuehrer@jku.at_2FDEB7900D0600008FFD18000A004500_"><div>Hello,</div><div><br></div><div>please try the R - package 'nbclust' do decide how many clusters are feasable. In addition to that statistical measures, inspect the different cluster solutions by content and how meaningful interpretations are. You can also do some kind of x-square test where you align the clusters with variables not used in the cluster analysis. At least you have some kind of face validity. </div><div><br></div><div>Best regards - Gerhard A. Wührer</div><div><br></div><div><br></div><span id="GWSignatureSent" style="padding-right: 0px; padding-left: 0px; margin-bottom: 5px; display: block;"><span style="display: block;"><br><span style="font-size: 10pt; display: inline-block; -ms-word-wrap: normal;"><div>o. Univ.-Prof. Dkfm. Dr. Gerhard A. Wührer<br>Institut für Handel, Absatz und Marketing<br>Johannes Kepler Universität Linz<br>Altenberger Str. 69<br>4040 Linz/Austria<br>tel.: 004373224689401<br>fax.:004373224689404<br>mail: <a href="mailto:gerhard.wuehrer@jku.at">gerhard.wuehrer@jku.at</a></div>
<div>URL: <a href="http://www.marketing.jku.at">www.marketing.jku.at</a></div>
<div> </div></span></span></span><span style="margin-bottom: 5px; display: block;"><br></span><div class="GroupWiseMessageBody" id="GroupWiseSection_1433932238000_rvosylis@live.com"><span class="GroupwiseReplyHeader">>>> Rimantas Vosylis <rvosylis@live.com> 10.06.2015 12:30 >>><br></span><div><div class="WordSection1"><div class="MsoNormal"><span lang="EN-US">Dear Traminer users,<o:p></o:p></span></div><div class="MsoNormal"><span lang="EN-US"><o:p> </o:p></span></div><div class="MsoNormal"><span lang="EN-US">I am trying to build a typology of sequences by using cluster analysis with OM and Ward algorith.<o:p></o:p></span></div><div class="MsoNormal"><span lang="EN-US"><o:p> </o:p></span></div><div class="MsoNormal"><span lang="EN-US">I have a problem of choosing the number of clusters. I use several empirical indexes, but they don‘t help me a lot. I use Calinski and harabasz (CH) index, but it has a peak at two cluster solution and the goes down. I also use average shilloute width but it gives me the similar results as CH index. I also run pseudo ANOVA to see which cluster solution explains most variance, but it tells me the opposite – the more the clusters the higher the pseudo R2 gets. When I look at the various plots (e.g. seqdplot) I see that the most meaningful solutions (I have several types of sequences) lie somewhere between 4-6 clusters.<o:p></o:p></span></div><div class="MsoNormal"><span lang="EN-US"><o:p> </o:p></span></div><div class="MsoNormal"><span lang="EN-US">Could You perhaps suggest which indexes worked best for You and matched Your expectations / theoretical knowledge and that I could use in my analysis?<o:p></o:p></span></div><div class="MsoNormal"><span lang="EN-US"><o:p> </o:p></span></div><div class="MsoNormal"><span lang="EN-US">Thank You in advance!!<o:p></o:p></span></div><div class="MsoNormal"><span lang="EN-US"><o:p> </o:p></span></div><div class="MsoNormal"><o:p> </o:p></div><div class="MsoNormal"><span lang="EN-US" style="mso-fareast-language: LT;">Sincerely,<o:p></o:p></span></div><div class="MsoNormal"><span lang="EN-US" style="mso-fareast-language: LT;"><o:p> </o:p></span></div><div class="MsoNormal"><span lang="EN-US" style="mso-fareast-language: LT;">Rimantas Vosylis<o:p></o:p></span></div><div class="MsoNormal"><span lang="EN-US" style="mso-fareast-language: LT;">PhD student, lecturer<o:p></o:p></span></div><div class="MsoNormal"><span lang="EN-US" style="mso-fareast-language: LT;">Insitute of Psychology<o:p></o:p></span></div><div class="MsoNormal"><span lang="EN-US" style="mso-fareast-language: LT;">Faculty of Social Technologies<o:p></o:p></span></div><div class="MsoNormal"><span lang="EN-US" style="mso-fareast-language: LT;">Mykolas Romeris University<o:p></o:p></span></div><div class="MsoNormal"><span lang="EN-US" style="mso-fareast-language: LT;"><o:p> </o:p></span></div><div class="MsoNormal"><span lang="EN-US" style="mso-fareast-language: LT;">e-mail: <a href="mailto:rimantasv@mruni.eu">rimantasv@mruni.eu</a><o:p></o:p></span></div><div class="MsoNormal"><span lang="EN-US" style="mso-fareast-language: LT;">e-mail2: <u><span style="color: rgb(5, 99, 193);"><a href="mailto:rvosylis@live.com">rvosylis@live.com</a></span></u><o:p></o:p></span></div><div class="MsoNormal"><o:p> </o:p></div><div class="MsoNormal"><span lang="EN-US"><o:p> </o:p></span></div></div></div></div></div></body></html>