Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: Observations in Sequence analysis

From   Brendan Halpin <>
Subject   Re: st: Observations in Sequence analysis
Date   Wed, 03 Oct 2012 23:25:38 +0100

On Wed, Oct 03 2012, Sarah Park wrote:

> However, when I run the cluster analysis based
> on the dissimilarity matrix afterwards, I have Stata categorizing some
> of the sequence with same elements (ex. 333, 333333, 333333333) into
> the same cluster, some into different clusters when they are clearly
> the same sequence. 

These are not the same sequence: they have different length. If you are
using the optimal matching algorithm to compare sequences, the indel
cost is incurred for each unit difference in length. If you want these
sequences to be considered the same, you need another approach. If you
really want to consider these sequences as the same, you could remove
consecutive duplicates (so that they would all be the same as the
sequence "3"). 

Brendan Halpin,   Department of Sociology,   University of Limerick,   Ireland
Tel: w +353-61-213147  f +353-61-202569  h +353-61-338562;  Room F1-009 x 3147    ULSociology on Facebook:         twitter:@ULSociology
*   For searches and help try:

© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index