[Traminer-users] combining short sequences with long sequences

[Rimantas Vosylis]

Dear Traminer users and experts,

 

I am using Traminer for my PhD data analyses, but I am stuck with some
issues that I cannot find answer to. Hopefully You will be able to help me
with this.

 

I am interested in transitions to adulthood. I have two groups one is called
30-year-olds and another one -  25-year-olds, as participants of these
groups are very close to those ages.

I have gathered data with Life History Calendar on various life statuses in
areas of parenthood, partner, education, work and living situation. From
this data I have created two sequences for each participant. There are now
two sequences, one for work-education transitions, another for family
transitions. Apart of LHC data I have also collected various data from these
participants on psychosocial functioning. 

 

My original idea was to first find the typology of transitions to adulthood
by using only 30-year-olds that have sequences of about 24 objects (1 object
represents some life situation status in 6-months period at some point after
finishing school; 24 statuses represent change in these statuses during 12
years after finishing school). Then I would find some representative
sequences (ideal types) in each cluster and then I would somehow assign the
25-year-olds (about 16 objects per sequence) based on similarity of their
sequence to the ideal type sequences, that were found in older group. This
way I would have participants of two age groups assigned to the same
transitional typology. After that I would compare how all these groups
differ on psychosocial indicators (e.g. identity issues). 

 

So the main issue for me is how can I assign the 25-year-olds that have
shorter sequences to the clusters that were found based on 30-year-old group
analyses. 

 

I came up with several strategies, but I am not sure which on is better, or
maybe there is something else I can do but I don't know.

 

1.       The first strategy is that I simply run optimal matching
calculations for the full dataset (including the ones that have long
sequences and shorter ones) and those that have shorter ones' are already
assigned to some cluster. When I specify missing values in right end cells
as void, it does seem to work ok. 

 

Q1. My first question to You is: does this seem like a valid strategy to
assign 25-year-olds to the clusters that are actually created using also
30-year-olds? 

 

2.       The second strategy is that I first analyze only 30-year-olds, then
I extract ideal types representing each cluster, then I include these ideal
types into dataset of only 25-year-olds and I rerun Optimal matching
analysis. Then based on the shortest distance from each ideal type sequence
to each participants' sequence I assign them to those clusters. Something
similar was discussed by Martin, P., Schoon, I., Ross, A., Beyond
Transitions: Applying Optimal Matching to Life Course Research 

 

Q2. Does this seem like a more valid strategy than the first one? 

 

Q3. Perhaps You could provide another option on how to do such assigning?

 

Q4. Could anyone please specify on how do I actually find the "ideal types"?
Are they the central sequences in the cluster? With smallest average
distance? I look everywhere but I couldn't  really find any "possible to
understand" answer :(

 

 

I would really appreciate any help on any of these questions. 

 

 

Sincerely,

 

Rimantas Vosylis

PhD student, lecturer

Insitute of Psychology

Faculty of Social Technologies

Mykolas Romeris University

 

e-mail: rimantasv at mruni.eu <mailto:rimantasv at mruni.eu> 

e-mail2: rvosylis at yahoo.co.uk <mailto:rvosylis at yahoo.co.uk> 

 

 

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.r-forge.r-project.org/pipermail/traminer-users/attachments/20150128/f84405ce/attachment.html>