<html xmlns:v="urn:schemas-microsoft-com:vml" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:w="urn:schemas-microsoft-com:office:word" xmlns:m="http://schemas.microsoft.com/office/2004/12/omml" xmlns="http://www.w3.org/TR/REC-html40">
<head>
<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1">
<meta name="Generator" content="Microsoft Word 14 (filtered medium)">
<style><!--
/* Font Definitions */
@font-face
{font-family:Wingdings;
panose-1:5 0 0 0 0 0 0 0 0 0;}
@font-face
{font-family:"Cambria Math";
panose-1:2 4 5 3 5 4 6 3 2 4;}
@font-face
{font-family:Calibri;
panose-1:2 15 5 2 2 2 4 3 2 4;}
@font-face
{font-family:Consolas;
panose-1:2 11 6 9 2 2 4 3 2 4;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{margin:0cm;
margin-bottom:.0001pt;
font-size:11.0pt;
font-family:"Calibri","sans-serif";
mso-fareast-language:EN-US;}
a:link, span.MsoHyperlink
{mso-style-priority:99;
color:blue;
text-decoration:underline;}
a:visited, span.MsoHyperlinkFollowed
{mso-style-priority:99;
color:purple;
text-decoration:underline;}
span.EmailStyle17
{mso-style-type:personal-compose;
font-family:"Calibri","sans-serif";
color:windowtext;}
.MsoChpDefault
{mso-style-type:export-only;
font-size:10.0pt;
font-family:"Calibri","sans-serif";
mso-fareast-language:EN-US;}
@page WordSection1
{size:612.0pt 792.0pt;
margin:70.85pt 70.85pt 70.85pt 70.85pt;}
div.WordSection1
{page:WordSection1;}
/* List Definitions */
@list l0
{mso-list-id:107895995;
mso-list-template-ids:1615727720;}
@list l0:level1
{mso-level-number-format:bullet;
mso-level-text:\F0B7;
mso-level-tab-stop:36.0pt;
mso-level-number-position:left;
text-indent:-18.0pt;
mso-ansi-font-size:10.0pt;
font-family:Symbol;}
@list l0:level2
{mso-level-number-format:bullet;
mso-level-text:o;
mso-level-tab-stop:72.0pt;
mso-level-number-position:left;
text-indent:-18.0pt;
mso-ansi-font-size:10.0pt;
font-family:"Courier New";
mso-bidi-font-family:"Times New Roman";}
@list l0:level3
{mso-level-number-format:bullet;
mso-level-text:\F0A7;
mso-level-tab-stop:108.0pt;
mso-level-number-position:left;
text-indent:-18.0pt;
mso-ansi-font-size:10.0pt;
font-family:Wingdings;}
@list l0:level4
{mso-level-number-format:bullet;
mso-level-text:\F0A7;
mso-level-tab-stop:144.0pt;
mso-level-number-position:left;
text-indent:-18.0pt;
mso-ansi-font-size:10.0pt;
font-family:Wingdings;}
@list l0:level5
{mso-level-number-format:bullet;
mso-level-text:\F0A7;
mso-level-tab-stop:180.0pt;
mso-level-number-position:left;
text-indent:-18.0pt;
mso-ansi-font-size:10.0pt;
font-family:Wingdings;}
@list l0:level6
{mso-level-number-format:bullet;
mso-level-text:\F0A7;
mso-level-tab-stop:216.0pt;
mso-level-number-position:left;
text-indent:-18.0pt;
mso-ansi-font-size:10.0pt;
font-family:Wingdings;}
@list l0:level7
{mso-level-number-format:bullet;
mso-level-text:\F0A7;
mso-level-tab-stop:252.0pt;
mso-level-number-position:left;
text-indent:-18.0pt;
mso-ansi-font-size:10.0pt;
font-family:Wingdings;}
@list l0:level8
{mso-level-number-format:bullet;
mso-level-text:\F0A7;
mso-level-tab-stop:288.0pt;
mso-level-number-position:left;
text-indent:-18.0pt;
mso-ansi-font-size:10.0pt;
font-family:Wingdings;}
@list l0:level9
{mso-level-number-format:bullet;
mso-level-text:\F0A7;
mso-level-tab-stop:324.0pt;
mso-level-number-position:left;
text-indent:-18.0pt;
mso-ansi-font-size:10.0pt;
font-family:Wingdings;}
@list l1
{mso-list-id:1324895662;
mso-list-template-ids:-992544642;}
@list l1:level1
{mso-level-number-format:bullet;
mso-level-text:\F0B7;
mso-level-tab-stop:36.0pt;
mso-level-number-position:left;
text-indent:-18.0pt;
mso-ansi-font-size:10.0pt;
font-family:Symbol;}
@list l1:level2
{mso-level-number-format:bullet;
mso-level-text:\F0B7;
mso-level-tab-stop:72.0pt;
mso-level-number-position:left;
text-indent:-18.0pt;
mso-ansi-font-size:10.0pt;
font-family:Symbol;}
@list l1:level3
{mso-level-number-format:bullet;
mso-level-text:\F0B7;
mso-level-tab-stop:108.0pt;
mso-level-number-position:left;
text-indent:-18.0pt;
mso-ansi-font-size:10.0pt;
font-family:Symbol;}
@list l1:level4
{mso-level-number-format:bullet;
mso-level-text:\F0B7;
mso-level-tab-stop:144.0pt;
mso-level-number-position:left;
text-indent:-18.0pt;
mso-ansi-font-size:10.0pt;
font-family:Symbol;}
@list l1:level5
{mso-level-number-format:bullet;
mso-level-text:\F0B7;
mso-level-tab-stop:180.0pt;
mso-level-number-position:left;
text-indent:-18.0pt;
mso-ansi-font-size:10.0pt;
font-family:Symbol;}
@list l1:level6
{mso-level-number-format:bullet;
mso-level-text:\F0B7;
mso-level-tab-stop:216.0pt;
mso-level-number-position:left;
text-indent:-18.0pt;
mso-ansi-font-size:10.0pt;
font-family:Symbol;}
@list l1:level7
{mso-level-number-format:bullet;
mso-level-text:\F0B7;
mso-level-tab-stop:252.0pt;
mso-level-number-position:left;
text-indent:-18.0pt;
mso-ansi-font-size:10.0pt;
font-family:Symbol;}
@list l1:level8
{mso-level-number-format:bullet;
mso-level-text:\F0B7;
mso-level-tab-stop:288.0pt;
mso-level-number-position:left;
text-indent:-18.0pt;
mso-ansi-font-size:10.0pt;
font-family:Symbol;}
@list l1:level9
{mso-level-number-format:bullet;
mso-level-text:\F0B7;
mso-level-tab-stop:324.0pt;
mso-level-number-position:left;
text-indent:-18.0pt;
mso-ansi-font-size:10.0pt;
font-family:Symbol;}
ol
{margin-bottom:0cm;}
ul
{margin-bottom:0cm;}
--></style><!--[if gte mso 9]><xml>
<o:shapedefaults v:ext="edit" spidmax="1026" />
</xml><![endif]--><!--[if gte mso 9]><xml>
<o:shapelayout v:ext="edit">
<o:idmap v:ext="edit" data="1" />
</o:shapelayout></xml><![endif]-->
</head>
<body lang="FR-CH" link="blue" vlink="purple">
<div class="WordSection1">
<p class="MsoNormal"><span lang="EN-US">Dear TraMineR Users,<br>
<br>
I have the pleasure to announce the first official release of the WeightedCluster R library. This library greatly facilitates the clustering of state's sequences and, more generally, weighted data. The main functionalities of this library include:
<o:p></o:p></span></p>
<ul type="disc">
<li class="MsoNormal" style="mso-margin-top-alt:auto;mso-margin-bottom-alt:auto;mso-list:l0 level1 lfo3">
<b><span lang="EN-US">Aggregation of identical sequences</span></b><span lang="EN-US"> (in order to save memory and cluster a bigger number of sequences).<o:p></o:p></span></li><li class="MsoNormal" style="mso-margin-top-alt:auto;mso-margin-bottom-alt:auto;mso-list:l0 level1 lfo3">
<span lang="EN-US">Computation of several <b>clustering quality measure</b>.<o:p></o:p></span></li><li class="MsoNormal" style="mso-margin-top-alt:auto;mso-margin-bottom-alt:auto;mso-list:l0 level1 lfo3">
<span lang="EN-US">Methods facilitating the <b>choice</b> of the <b>number of groups</b> and
<b>cluster algorithm</b> based on cluster quality measures.<o:p></o:p></span></li><li class="MsoNormal" style="mso-margin-top-alt:auto;mso-margin-bottom-alt:auto;mso-list:l0 level1 lfo3">
<b><span lang="EN-US">Clustering of weighted data</span></b><span lang="EN-US"> using a distance matrix (for instance, using sampling weights or aggregated sequences).<o:p></o:p></span></li><li class="MsoNormal" style="mso-margin-top-alt:auto;mso-margin-bottom-alt:auto;mso-list:l0 level1 lfo3">
<span lang="EN-US">An <b>optimized PAM clustering</b> algorithm.<o:p></o:p></span></li><li class="MsoNormal" style="mso-margin-top-alt:auto;mso-margin-bottom-alt:auto;mso-list:l0 level1 lfo3">
<b><span lang="EN-US">Graphical representation</span></b><span lang="EN-US"> of hierarchical clustering of state sequence (you need to install GraphViz
<a href="http://www.graphviz.org">http://www.graphviz.org</a> before launching R)<o:p></o:p></span></li></ul>
<p class="MsoNormal" style="margin-bottom:12.0pt"><span lang="EN-US">The library comes with the “<a href="http://mephisto.unige.ch/weightedcluster/WeightedCluster.pdf">WeightedCluster</a><span class="MsoHyperlink"> Library Manual</span>: A practical guide to
creating typologies of trajectories in the social sciences with R”, also <a href="http://mephisto.unige.ch/weightedcluster/WeightedCluster-fr.pdf">
available in French</a>. Aside from presenting the library, this manual discusses several important issues when clustering state's sequences (or any other object) in the social sciences, such as cluster validation and the usual sociological assumptions, for
instance.<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US">A short script (that can be easily reproduced) illustrating the functionalities of the library is available at the WeightedCluster website:
</span><a href="http://mephisto.unige.ch/weightedcluster/"><span lang="EN-US">http://mephisto.unige.ch/weightedcluster/</span></a><span lang="EN-US"> or below<br>
<br>
The library can be installed with the following command (R version 2.15 or higher is mandatory):<br>
</span><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas">install.packages("WeightedCluster")<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas">library(WeightedCluster)<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas">## To get the manuals, please run:<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas"> vignette("WeightedCluster") ## complete manual in English<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas"> vignette("WeightedCluster-fr") ## complete manual in French<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas"> vignette("WeightedClusterPreview") ## short preview in English<br>
</span><span lang="EN-US"><br>
Any comments, suggestions or bug reports are very welcome.<br>
<br>
Kind regards,<br>
Matthias Studer</span><span lang="EN-US" style="font-size:12.0pt;font-family:"Times New Roman","serif""><o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas">## Loading the library<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas">library(WeightedCluster)<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas">## Loading the mvad dataset<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas">data(mvad)<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas">## aggregating identical sequence<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas">aggMvad <- wcAggregateCases(mvad[, 17:86])<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas">print(aggMvad)<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas">uniqueMvad <- mvad[aggMvad$aggIndex, 17:86]<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas">## defining the state sequence object<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas">mvad.seq <- seqdef(uniqueMvad, weights=aggMvad$aggWeights)<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas">## Computing Hamming distance between sequence<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas">diss <- seqdist(mvad.seq, method="HAM")<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas">## Clustering the sequences using "average" hierarchical clustering<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas">## Here, we need to set the weights (members argument) to account for identical sequence aggregation<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas">averageClust <- hclust(as.dist(diss), method="average", members=aggMvad$aggWeights)<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas">## Representing the hierarchical clustering as a tree<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas">averageTree <- as.seqtree(averageClust, seqdata=mvad.seq, diss=diss, ncluster=6)<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas">## Graphical representation of the tree (you need to have Graphviz installed before lauchning R)<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas">seqtreedisplay(averageTree, type="d", border=NA, showdepth=TRUE)<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas">## Compute several clustering quality measure for partition in 2, 3, 4, ... 10 groups.<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas">avgClustQual <- as.clustrange(averageClust, diss, weights=aggMvad$aggWeights, ncluster=10)<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas">## Plot the evolution of the clustering quality according to number of clusters.<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas">plot(avgClustQual)<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas">## The same, but using normalized values.<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas">plot(avgClustQual, norm="zscore")<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas">## Print the 2 best number of group according to each quality measure<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas">summary(avgClustQual, max.rank=2)<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas">## Compute PAM clustering and cluster quality measure for different number of groups (ranging from 2 to 10)<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas">pamClustRange <- wcKMedRange(diss, kvals=2:10, weights=aggMvad$aggWeights)<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas">## Print the 2 best number of group according to each quality measure for the PAM clustering<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas">summary(pamClustRange, max.rank=2)<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas">## The best clustering was found using average clustering in 5 groups according to ASW (average silhouette width)<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas">seqdplot(mvad.seq, group=avgClustQual$clustering$cluster5, border=NA)<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas">## Clustering was made on distinct sequences<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas">## Recover the clustering solution in the original (full) dataset<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas">uniqueCluster5 <- avgClustQual$clustering$cluster5<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas">mvad$cluster5 <- uniqueCluster5[aggMvad$disaggIndex]<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas">## Compute association between clustering and father unemployment<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas">chisq.test(table(mvad$funemp, mvad$cluster5))<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt;font-family:Consolas"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="font-size:10.0pt"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-size:10.0pt">---<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:10.0pt">Matthias Studer<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:10.0pt">Institut d'études démographiques et du parcours de vie<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:10.0pt">et Département des sciences économiques<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:10.0pt">Uni-Mail, bureau 5205<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:10.0pt">40, bd du Pont d’Arve<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:10.0pt">1211 Genève 4<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:10.0pt">Tel: +41 22 379 82 15<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:10.0pt">Fax: +41 22 379 82 99<o:p></o:p></span></p>
<p class="MsoNormal"><o:p> </o:p></p>
</div>
</body>
</html>