4
$\begingroup$

Besides the ado provided by Brendan Halpin for Stata, is there a way to pursue an Optimal Matching using the R-package TraMineR which weights OM’s elementary operations inversely with episode length [1]?

[1]: See Halpin, B. (2010) 'Optimal Matching Analysis and Life-Course Data: The Importance of Duration', Sociological Methods & Research 38(3): 365–388.

$\endgroup$

1 Answer 1

3
$\begingroup$

TraMineR does not (yet) compute Duration weighted Optimal Matching Algorithm. Unfortunatly, this distance measure does not garantee the triangular inequality (in French, see chapter 2 of http://archive-ouverte.unige.ch/vital/access/manager/Repository/unige:22054). Depending on the distance analysis procedure (clustering) you plan to use, this may be problematic.

$\endgroup$
1
  • 2
    $\begingroup$ Aren't there some cluster algorithms which do not rely on triangle inequality? Besides, there is a recent master's thesis which presents a modified k-means algorithm without triangle inequality. Maybe, this will be more interesting in the future if someone writes/updates a R-package with this modified k-means. $\endgroup$ May 29, 2013 at 9:15

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge that you have read and understand our privacy policy and code of conduct.

Not the answer you're looking for? Browse other questions tagged or ask your own question.