Abstract
A sequence is an ordered list of categorical values of a variable which, in the social sciences, corresponds to social processes or trajectories, such as school-to-work transitions or family formation. Sequence analysis presents the possibility of dealing with complex information because sequences are usually based on longitudinal data and cover a large number of cases. Even scholars who apply elaborated methodological statistical approaches necessarily need to reduce this complexity by restricting their analyses to certain events. For example, many researchers within the field of school-to-work transitions who apply event history analysis reduce the event “labour market entrance” to the status change into employment. The algorithmic approach of sequence analysis has the ability to handle the complexity of social processes empirically. However, the problem of graphical representation persists because the use of categorical time series involving many individuals requires multidimensional visualisation, but the general form of (printed) scientific publications is still black and white.
This article explores the different visualisation possibilities of sequential information that are typically used in the social science literature. It presents conventional (e.g., sequence index plots) as well as less common types of graphs (such as parallel coordinates plots, status proportion plots, and transition plots) and discusses their particular advantages and limitations. The arguments for this assessment are based on the particular scientific interest in certain features of sequences and on Cleveland’s rules of perception. Additionally, an attempt is made to find practical solutions to avoid problems in the depiction of sequential and transition data.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
One major objective of the life-course approach is the examination of the embedding of aggregate individual life courses into macro-level contexts and in the linkage between life-courses (cp. Elder et al. 2004).
- 2.
This is only true for those sequences based on a time-scale mostly used in sociology. But, there are also studies about sequences that have no time dimension, such as the original application of optimal matching (OMA) on distance or DNA strands.
- 3.
- 4.
The majority of the principles are already implemented by the most statistical software packages, such as Stata. For example, the principle that the data rectangle should be smaller than the scale-line rectangle (Cleveland 1994, p. 31) is followed by Stata for every graphical command.
- 5.
- 6.
- 7.
In Stata, the graph command plots the graph category by category, so that categories (statuses) with a higher number overplot those with a lower number.
- 8.
- 9.
- 10.
In Stata, the standard colors are chosen in order to provide more contrast on color screen and when converted to black-and-white. However, apart from the explorative research procedure being an iterative, experimental process, the choice of the best color scheme is also iterative, and the proof of the pudding is in the eating. For more discussion on the choice of colors for representation of categorical data, see Zeileis et al. (2009).
- 11.
The user-written package TraMineR available for the software R (see footnote 8) offers the possibility to produce so-called sequence frequency plots (Gabadinho et al. 2011a). These plots also show most frequent sequences, and have the form of a weighted bar chart.
- 12.
However, the original application differs a bit regarding the structure, because each of the vertical axes refers to another dimension, whereas the usage in sequence analysis mixes the Cartesian system with the ‘real’ parallel coordinates in a way that the time points are represented by the horizontal axis.
References
Abbott, A. (1983). Sequences of social events: Concepts and methods for the analysis of order in social processes. Historical Methods, 16, 129–147.
Aisenbrey, S., & Fasang, A. (2010). New life for old ideas: The ‘‘Second Wave’’ of sequence analysis bringing the ‘‘Course’’ back into the life course. Sociological Methods & Research, 38, 420–462.
Anscombe, F. J. (1973). Graphs in statistical analysis. The American Statistician, 27, 17–21.
Blasius, J., & Greenacre, M. (Eds.). (1998). Visualization of categorical data. London: Academic Press.
Brzinsky-Fay, C. (2007). Lost in transition? Labour market entry sequences of school leavers in Europe. European Sociological Review, 23, 409–422.
Brzinsky-Fay, C., Kohler, U., & Luniak, M. (2006). Sequence analysis using Stata. Stata Journal, 6, 435–460.
Cleveland, W. S. (1994). The elements of graphing data. Summit: Hobart Press.
Elder, J., Glen, H., Kirkpatrick Johnson, M., & Crosnoe, R. (2004). The emergence and development of life course theory. In J. T. Mortimer & M. J. Shanahan (Eds.), Handbook of the life course (pp. 3–19). New York: Springer.
Fasang, A. E., & Liao, T. F. (Forthcoming). Visualizing Sequences in the social sciences: Relative frequency sequence plots. Sociological Methods & Research doi:10.1177/0049124113506563.
Gabadinho, A., Ritschard, G., Müller, N. S., & Studer, M. (2011a). Analyzing and visualizing state sequences in R with TraMineR. Journal of Statistical Software, 40, 1–37.
Gabadinho, A., Ritschard, G., Studer, M., & Müller, N. S. (2011b). Mining sequence data in R with the TraMineR package: A user’s guide. Geneva: University of Geneva.
George, L. K. (2009). Conceptualizing and measuring trajectories. In G. E. Elder & J. Z. Giele (Eds.), The craft of life course research (pp. 163–186). New York/ London: Gulidford Press.
Good, P. I., & Hardin, J. W. (2003). Common errors in statistics (and how to avoid them). New York: Wiley.
Heinz, W. R. (2003). Combining methods in life-course research: A mixed blessing? In W. R. Heinz & V. W. Marshall (Eds.), Social dynamics of the life course (pp. 73–90). New York: Aldine de Gruyter.
Piccarreta, R. (2012). Graphical and smoothing techniques for sequence analysis. Sociological Methods & Research, 41, 362–380.
Piccarreta, R., & Lior, O. (2010). Exploring sequences: A graphical tool based on multi-dimensional scaling. Journal of the Royal Statistical Society (Series A: Statistics in Society), 173, 165–184.
Theus, M. (2006). Statistical Graphics. In A. Unwin, M. Theus, & H. Hofmann (Eds.), Graphics of large datasets. Visualizing a million (pp. 31-54). New York: Springer.
Tufte, E. R. (1983). The visual display of quantitative information. Cheshire: Graphic Press.
Tukey, J. W. (1977). Exploratory data analysis. Reading: Addison-Wesley Pub.Co.
Wallgren, A., Wallgren, B., Persson, R., Jorner, I., & Haaland, J.-A. (1996). Graphing statistics & data. Creating better charts. Newbury Park: Sage.
Zeileis, A., Hornik, K., & Murrell, P. (2009). Escaping RGBland: selecting colors for statistical graphics. Computational statistics and data analysis, 53, 3259–3270.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendix
Appendix
This list contains a selection of graphing principles developed and assembled by Cleveland (1994). It is limited to those principles that are relevant for the graphs usually applied to sequence analyses.
Elementary principles of graph construction:
-
Make the data stand out & avoid superfluity.
-
Use visually prominent graphical elements to show the data.
[…]
-
Overlapping plotting symbols must be visually distinguishable.
-
Superposed data sets must be readily visually assembled.
-
Visual clarity must be preserved under reduction and reproduction.
Principles of clear understanding:
-
Put major conclusions into graphical form.
[…]
General strategy:
-
A large amount of quantitative information can be packed into a small region.
-
Graphing data should be an iterative, experimental process.
[…]
Rights and permissions
Copyright information
© 2014 Springer New York Heidelberg Dordrecht London
About this chapter
Cite this chapter
Brzinsky-Fay, C. (2014). Graphical Representation of Transitions and Sequences. In: Blanchard, P., Bühlmann, F., Gauthier, JA. (eds) Advances in Sequence Analysis: Theory, Method, Applications. Life Course Research and Social Policies, vol 2. Springer, Cham. https://doi.org/10.1007/978-3-319-04969-4_14
Download citation
DOI: https://doi.org/10.1007/978-3-319-04969-4_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-04968-7
Online ISBN: 978-3-319-04969-4
eBook Packages: Humanities, Social Sciences and LawSocial Sciences (R0)