Thesis: 5 tnet – Software for Analysis of Weighted and Longitudinal networks
As seen in the previous chapters of this thesis, information of tie weights as well as on the exact time ties are created or severed enables us to uncover and study interesting network properties through novel methods. However, not only are few network measures applicable to weighted and/or longitudinal networks, but there is also a lack of integrated software programmes that can deal with these types of networks. To the best of our knowledge, there are no network analysis programmes that can deal with weighted networks and allow for users to create their own functions. On the one hand, programmes like UCINET and Pajek have a small set of functions for weighted networks, but they do not allow for users to programme additional functions (Batagelj and Mrvar, 2007; Borgatti et al., 2002). Therefore, researchers proposing new measures must create stand-alone programmes to deal with a single aspect of weighted networks (e.g., Newman, 2001c).
On the other, a number of packages dealing with network analysis have been created within the open-source statistical programme R, notably the sna and statnet-packages (Butts, 2006; Handcock et al., 2003). These packages allow researchers to create additional functions on top of existing ones. This ability reduces the time spent on programming greatly, and let researchers focus on the contribution to the literature instead. For example, if someone has already written a function for identifying the shortest paths in a network, a researcher that would like to extend this measures can simply work on this code without programming the function from scratch. However, the sna and statnet-packages rely on the basic network-package for data structures to represent networks (Butts et al., 2008). This basic package does not have data classes for weighted or longitudinal networks. Therefore, to allow researchers to easily create new functions for weighted and longitudinal networks, a new platform is needed.
This new platform should be able to handle both types of datasets. To this end and to disseminate the methods proposed in this thesis, tnet was created. Although this is a user-written package in R similar to the sna and statnet-packages, it does not rely on the network-package. It utilises its own data structures: one for weighted static networks and one for longitudinal networks. The longitudinal network structure can represent both binary and weighted networks.
For each of these two structures, tnet contains a set of functions. First, for the analysis of weighted networks, in addition to the functions to calculate the measures proposed in Chapter 2 and Chapter 3, a set of centrality measures (Barrat et al., 2004; Newman, 2001c), random network generators, and support functions are included. Second, for the analysis of longitudinal networks, functions include the framework proposed in Chapter 4 to study the tie generating mechanisms in longitudinal networks as well as random network generators and support functions.
The rest of this chapter is organised as follows. First, the two data structures and their supporting functions are introduced. Then, the functions for studying structural properties of weighted networks are presented. Only functions which have not been thoroughly described in previous chapters will be presented in detail. In Section 5.3, functions to deal with longitudinal networks are presented. Finally, we will highlight the contributions of this package to the scientific community and offer some concluding remarks. Appendix C includes the source code and the specific details for running the various functions within tnet. Moreover, the supporting website includes download instructions, examples, and guides to transfer data from other software programmes.