Textbooks and review papers to add

[krivit]

@FATelarico , @jhollway , to avoid further crowding cran-task-views/ctv#61, I am creating a ticket to discuss reference/text books and review papers to add. Here are my suggestions so far.

ERGMs:

• Text book: Lusher, D., Koskinen, J. and Robins, G. (2012) Exponential Random Graph Models for Social Networks: Theory, Methods, and Applications. Cambridge University Press. doi:10.1017/CBO9780511894701
• Review paper: Schweinberger, M., Krivitsky, P. N., Butts, C. T. and Stewart, J. R. (2020) Exponential-family Models of Random Graphs: Inference in Finite, Super and Infinite Population Scenarios. Statistical Science, The Institute of Mathematical Statistics, 35(4): 627-662. doi:10.1214/19-STS743
• Statnet Workshops site (probably better than just the one intro workshop, since it covers a bunch of topics): https://statnet.org/workshops/ .

More general statistical network methods:

• Text book: Kolaczyk, E. D. (2009) Statistical Analysis of Network Data: Methods and Models. Springer. doi:10.1007/978-0-387-88146-1

[FATelarico]

@krivit Thank you for your dedication.

I would say that:

• we can include (Lusher, Koskinen, and Robins 2012) in the first ergm entry as a guide for the users. However, also the package vignettes are pretty good as an introduction IMHO.

• (Kolaczyk 2009) could fit in somewhere in the introductory paragraph.

• The Statnet Workshops site can replace that specific workshop I picked if you find it too generic.

[jhollway]

@krivit @FATelarico this seems like a good start to me. Can I clarify what our reference inclusion criteria is?

[FATelarico]

@jhollway thank you for the follow up!

I'd say to include only references that can help users understand which pakages amongst a given set is the best choice for a certain use case or that compare package.

That notwithstanding, several sources about comparison are already in there, and @krivit put out some good general references (plus the one on ergm & co.). Also, we should keep them at a minimum, so it's best to be parsimonious and only include references only if the 'right’ package is neither obvious nor undeterminable in a general fashion.

[krivit]

Any other network analysis texts worth referencing? Most of what I know is ERGM-centric.

[jhollway]

There's at least one SAOM-related textbook on the way. Handbooks are also useful general references. Though I hear Achim's points about focusing CTVs on providing software overviews rather than a bibliography. I'm happy to adapt to whatever we institute as a policy.

[FATelarico]

There's at least one SAOM-related textbook on the way. Handbooks are also useful general references. Though I hear Achim's points about focusing CTVs on providing software overviews rather than a bibliography. I'm happy to adapt to whatever we institute as a policy.

More than textbooks or handbooks I think the most relevant sources are comparisons between packages/material that highlights use cases.

For instace, although Kolaczyk was the textbook I studied on, as a general intro I would have suggested eithet Holster's chapter in Introduction to R for Data Science (2022) or McNulty's new Handbook of Graphs and Networks in People Analytics (2022), which has a lot of practical guidelines about R packages among other stuff

I have already put a recent comparison of blockmodeling methods (since they are implemented in different packages, that's also a comparison of R packages).

Also, we've covered the non-trivial statnet-igraph dilemma.

So, I don't feel particularly strongly about other issues atm.

[FATelarico]

I'd suggest to close 'internal' open issues after 10d of inactivity. Feel free to reopen with new comments if something new comes up!

[jhollway]

Thanks @FATelarico , will you set this up automatically?: https://docs.github.com/en/actions/use-cases-and-examples/project-management/closing-inactive-issues

[krivit]

I'd suggest to close 'internal' open issues after 10d of inactivity. Feel free to reopen with new comments if something new comes up!

Ten days seems far too short. Consider that even in the initial development stage, we've had multiple months without any activity.