ECPR

Install the app

Install this application on your home screen for quick and easy access when you’re on the go.

Just tap Share then “Add to Home Screen”

ECPR

Install the app

Install this application on your home screen for quick and easy access when you’re on the go.

Just tap Share then “Add to Home Screen”

Back to Panel Details
Back to Panel Details

Advanced Sequence Analysis

Philippe Blanchard
p.blanchard@warwick.ac.uk

University of Warwick

Philippe Blanchard, University of Warwick, works on green politics, political communication, and methods for social and political sciences: multivariate statistics, longitudinal methods, interviewing, content analysis and digital data. He has taught methods in Austria, Denmark, France, Germany, Singapore, Switzerland, the UK and the USA.

He is currently director of Warwick's BA in Politics, International Studies and Quantitative Methods and MA in Politics, Big Data & Quantitative Methods.

Philippe is the Chair of the ECPR Methods School Academic Advisory Board.


Course Dates and Times

Monday 25 February – Friday 1 March, 09:00–12:30
15 hours over 5 days

Prerequisite Knowledge

You should be familiar with the principles of sequence analysis, and have applied them to a research project of your own.

You may have used R, Stata or any other software for your application, although this course will mainly rely on R and TraMineR.

By the end of the course, the level reached may differ between participants, but you should at very least have performed optimal matching and built a typology of sequences.

Please refer to the introductory-level readings to check or refresh your knowledge of the basics.

I will make sure the group is able to move on together on topics of a common interest to all.

By registering for this course, you confirm that you possess the knowledge required to follow it. The instructor will not teach these prerequisite items. If in doubt, contact the instructor before registering.


Short Outline

Sequence analysis is the systematic descriptive and causal study of sequences; that is, successions of standard categorical states or events.

Numerous fields in the social and political sciences are concerned with sequences, including life course, the sociology of professional careers, political sociology, the evolution of regimes and elections. Yet so far, most of the applied literature in sequence analysis is limited to a few basic methods, namely descriptive sequential statistics, individual and distribution graphs, and typologies.

This course welcomes scholars from any disciplinary background, and those using any kind of research design.

You should have an interest in one or more of the following advanced topics:

  • multichannel (aka multiple) sequence analysis, including multichannel sequence comparison and graphs
  • various methods for extracting or creating typical/ideal-typical sequences
  • smart sequential graphs
  • variations in sequence comparison
  • variations in relating sequential outputs to covariates

I will propose a blend of published case studies and new methodological solutions.

Tasks for ECTS Credits

2 credits (pass/fail grade) Attend at least 90% of course hours, participate fully in in-class activities, and carry out the necessary reading and/or other work prior to, and after, class.

3 credits (to be graded) As above, plus write a 5,000- to 6,000-character report within two weeks after the course about how sequence analysis is contributing, and/or will contribute, to your personal research project(s).

4 credits (to be graded) As above, plus complete a take-home examination based on knowledge gained from the course, and personal readings.


Long Course Outline

Sequence analysis is still in its infancy. Researchers engaging with it are in for an exciting journey, with plenty of room for innovation.

The best applied articles that make use of this method usually propose at least minor tweaks that adapt the existing tools to their own research questions and data.

On the other hand, a major part of the available literature does not always provide ready-to-use solutions, adequate to one’s needs, beyond the fundamentals of the 'core programme' (Gauthier, Bühlmann and Blanchard 2014): optimal matching with standard cost options, chained up with a typology and individual and distribution plots.

In this native state of the method, journals and publishers often require more than these basics to convince a wide audience in a given field that a sequential approach is relevant and fruitful.

This course addresses this gap. It fishes out best practices in the applied and method-centred sequence analysis literatures and presents them in a condensed way, together with approaches developed by Philippe. You will review existing tools and approaches, and assess their value for various kinds of projects.

Currently, a promising avenue for developments is multichannel sequence analysis (MCSA). MCSA considers each case (individuals, countries, organisations, or other human artefacts) in two or more domains (such as individuals in private and political life spheres, or countries along their successive regime types and international agreements).

The resulting sequential combinatorics is several times more complex than mono-channel sequences, but at the same time much more realistic in many research settings.

Addressing this challenge will be core to the course, through comparing, classifying, mining and graphing multichannel sequences.

We will discuss the conditions at which MCSA can be used, the kind of theory that can be tested through it, the possibility of extending existing monochannel tools to MCSA, and new tools that need to be designed specifically it. We will also discuss specific MCSA strategies for displaying results and writing up a convincing story out of it.

Philippe will present other advanced approaches and tools, valid for either monochannel and multichannel situations, depending on participants’ needs. These include:

  • typical sequences, which enable concise yet revealing summaries of groups of sequences, defined either through clustering or covariates;
  • alternative sequence comparison algorithms, which allow you to address a variety of data structures and sample sizes;
  • smarter sequential graphs, which condense the meaningful aspects of the data or results, yet preserve the sequential nature of the data.

Beyond these three options, the course may also address:

  • organisation of sequences into pairs, groups or networks;
  • sequence mining;
  • ways to test the association between sequences and covariates (such as sequence discrepancy analysis and regression trees).

We may also devote some time to improving sequence data collection, formatting and management, all of which can be key to efficient sequence analyses, especially for larger and/or collaborative projects.

The course will rely on collaborative pedagogy. You will be asked about your research projects and puzzles beforehand, to determine which methods get prioritised. For those who wish to give one, there will be time for individual presentations, to gather feedback from the group, and possibly draw parallels between research designs, tools used and outcomes.

This course follows on from Analysing Political and Social Sequences offered at previous ECPR Methods Schools, but other introductory courses, or self-training, can meet the prerequisites.

Day Topic Details
Day 1 Reminders and tips for efficient basic treatments, including variations in sequence comparison methods

Hands-on session 1

Day 2 Multiple sequence analysis I

Hands-on session 2
Presentation 1

Day 3 Multiple sequence analysis II

Hands-on session 3
Presentation 2

Day 4 Typical sequences. Smart sequential graphs

Hands-on session 4
Presentation 3

Day 5 Other advanced topics, or more of the above (upon demand)

Hands-on session 5
Presentation 4

Day Readings

The list below gives a direction of the orientation of the course. More references will be provided and commented during the course.

Day 1

Refreshers (covers the basics)

1. Gauthier J.-A, F. Bühlmann and P. Blanchard. 2014. “Introduction: Sequence Analysis in 2014” Pp. 1-17 in Blanchard P., F. Bühlmann and J.-A. Gauthier (eds.). Advances in Sequence Analysis: Methods, Theories and Applications. London: Springer

2. Blanchard P. Forthcoming 2019. “Sequence analysis” in Encyclopaedia of Research Methods, Sage (will be provided by the instructor)

3. An introductory course in R, for example:

Venables W. N., D. M. Smith and the R Development Core Team. 2011. R: A Language and Environment for Statistical Computing. Reference Index, http://cran.r-project.org/doc/manuals/R-intro.pdf

or: Crawley M. J. 2005. Statistics: An Introduction using R. Chichester: Wiley and Sons, chapters 1 and 2.

or: Zuur A. F., E. N. Ieno and E. H.W.G. Meesters. A Beginner's Guide to R. Springer: Dordrecht, chapters 1 to 3. see http://www.r-project.org/doc/bib/R-books.html for more possibilities, in several languages

The field of sequence analysis

4. Aisenbrey S. and A. E. Fasang. 2010. “New Life for Old Ideas: The ‘Second Wave’ of Sequence Analysis Bringing the ‘Course’ Back Into the Life Course." Sociological Methods and Research 38(3):420–462.

5. Blanchard P., F. Bühlmann and J.-A. Gauthier (eds.). Advances in Sequence Analysis: Methods, Theories and Applications. London: Springer

Day 2 and 3

Multichannel sequence analysis

6. Pollock G. 2007. Holistic trajectories: a study of combined employment, housing and family careers by using multiple-sequence analysis. Journal of the Royal Statistical Society Series A 170, part 1: 167-183.

7. Fillieule o. and p. Blanchard. 2013. “Fighting Together. Assessing Continuity and Change in Social Movement Organizations Through the Study of Constituencies' Heterogeneity.” Pp. 79-108 in A Political Sociology of Transnational Europe, edited by N. Kauppi. Basingstoke: ECPR Press

8. Wiggins R. D., C. Erzberger, M. Hyde, P. Higgs and D. Blane. 2007. "Optimal Matching Analysis Using Ideal Types to Describe the Lifecourse: An Illustration of How Histories of Work, Partnerships and Housing Relate to Quality of Life in Early Old Age." International Journal of Social Research Methodology 10(4): 259–278.

Day 2 and 3

Multichannel sequence analysis

6. Pollock G. 2007. Holistic trajectories: a study of combined employment, housing and family careers by using multiple-sequence analysis. Journal of the Royal Statistical Society Series A 170, part 1: 167-183.

7. Fillieule o. and p. Blanchard. 2013. “Fighting Together. Assessing Continuity and Change in Social Movement Organizations Through the Study of Constituencies' Heterogeneity.” Pp. 79-108 in A Political Sociology of Transnational Europe, edited by N. Kauppi. Basingstoke: ECPR Press

8. Wiggins R. D., C. Erzberger, M. Hyde, P. Higgs and D. Blane. 2007. "Optimal Matching Analysis Using Ideal Types to Describe the Lifecourse: An Illustration of How Histories of Work, Partnerships and Housing Relate to Quality of Life in Early Old Age." International Journal of Social Research Methodology 10(4): 259–278.

Day 3, 4 and 5

Various tools to work with typologies

9. Salmela-Aro K., N. Kiuru, J.-E. Nurmi, M. Eerola. 2001. Mapping pathways to adulthood among Finnish university students: Sequences, patterns, variations in family- and work-related roles, Advances in Life Course Research 16: 25-41

Typical sequences

10. Aassve A., Billari F. & Piccarreta R. 2007. Strings of Adulthood: A Sequence Analysis of Young British Women's Work-family Trajectories. European Journal of Population 23: 369-88

11. Gabadinho A., Ritschard G., Müller N.S. and Studer M. 2011. "Analyzing and visualizing state sequences in R with TraMineR", Journal of Statistical Software. Vol. 40 (4): 1-37

Smart graphs

12. Piccarreta R. and O. Lior. 2010. “Exploring sequences: a graphical tool based on multi-dimensional scaling. Journal of the Royal Statistical Society Series A 173 (part 1):165–184

13. Piccarreta R. 2012. “Graphical and Smoothing Techniques for Sequence Analysis”. Sociological Methods & Research 41(2): 362–380

14. Colombi D. and S. Paye. 2014. “Synchronising Sequences. An Analytic Approach to Explore Relationships Between Events and Temporal Patterns” Pp. 249-264 in Blanchard P., F. Bühlmann and J.-A. Gauthier (eds.). Advances in Sequence Analysis: Methods, Theories and Applications. London: Springer

Linked and networked sequences

15. Buton F., Lemercier C. and Mariot N. 2012. The household effect on electoral participation. A contextual analysis of voter signatures from a French polling station (1982–2007), Electoral Studies 31 (2): 434-447

16. Cornwell B. 2015. Social Sequence Analysis. Methods and Applications. New York: Cambridge University Press: Chapter 6

Cases alternative to individuals

17. Abbott A. and S. Deviney. 1992. The Welfare State as Transnational Event: Evidence from Sequences of Policy Adoption. Social Science History 16 (2): 245‑274

18. Casper G. and M. Wilson. 2014. Using Sequences to Model Crises. Political Science Research and Methods 3 (2): 381-397

Linking sequences with covariates

19. Studer M., G. Ritschard, A. Gabadinho and N. S. Müller. 2011. Discrepancy Analysis of State Sequences. Sociological Methods and Research 40 (3): 471‑510

 

Friday

Compulsory

  1. Pollock Gary. 207. Holistic trajectories: a study of combined employment, housing and family careers by using multiple-sequence analysis. Journal of the Royal Statistical Society Series A 170, part 1: 167-183.

Optional

  1. Lelièvre Eva and Nicolas Robette, A Life Space Perspective to Approach Individual Demographic Processes. Canadian Studies of Population 37 (1-2): 207-244.
  2. Piccarreta Raffaella and Orna Lior. 2010. Exploring sequences: a graphical tool based on multi-dimensional scaling, Journal of the Royal Statistical Society Series A 173, part 1 : 165–184.
  3. Colombi D. and S. Paye. 2014. “Synchronising Sequences. An Analytic Approach to Explore Relationships Between Events and Temporal Patterns” Pp. 249-264 in Blanchard P., F. Bühlmann and J.-A. Gauthier (eds.). Advances in Sequence Analysis: Methods, Theories and Applications. London: Springer

Software Requirements

R, plus the following packages (please instal prior to the course):

  • boot
  • cluster
  • colorspace
  • foreign
  • graphics
  • RcolorBrewer
  • questionr
  • TraMineR

Hardware Requirements

Please bring your own laptop

Literature

See 'Optional readings' in Day-to-Day Reading list, above.

Recommended Courses to Cover Before this One

<p><strong>Summer School</strong><br /> Analysing Political and Social Sequences<br /> Introduction to R<br /> Introduction to Statistics for Political and Social Scientists</p> <p><strong>Winter School</strong><br /> Introduction to R<br /> &nbsp;</p>

Recommended Courses to Cover After this One

<p><strong>Summer School</strong><br /> Intermediate R<br /> Data Management with R</p>


Additional Information

Disclaimer

This course description may be subject to subsequent adaptations (e.g. taking into account new developments in the field, participant demands, group size, etc). Registered participants will be informed in due time.

Note from the Academic Conveners

By registering for this course, you confirm that you possess the knowledge required to follow it. The instructor will not teach these prerequisite items. If in doubt, contact the instructor before registering.