Here’s an update on not one, not two, not three, but four papers!

An in-person Sunbelt conference at Paris. This time I’ve fortunately got a prime time slot to present on the soon-to-be-wrapped-up work on “evidencing preferential attachment in dependency network evolution”; slides are in pdf and html.

2025 is off to a good start. I will be working (again) with Freegle to continue where we were last time when collaborating under the RSS Statisticians for Society scheme. I have previously made a post about this. This time we’ve got funded by ICMS KE Catalyst!

The paper on conditional extremes model for graphs, led by my PhD student Aiden Farrell (jointly supervised with Emma Eastoe) is now on arXiv. While there have been multivariate extremes model for data observed on graphs, the novelty is the new approach for the residual distribution, which has usually been assumed multivariate gaussian. Here, we applied the multivariate asymmetric generalised Gaussian (MVAGG) distribution instead that enables fully parametric prediction. This complicates the computational inference, but Aiden developed a multi-step algorithm to address this issue.

Thank you to Teresa Lee at the Young Statisticians Section to invite me to present (slides) at the session “Getting your work to work” at the RSS conference. It’s a good opportunity for me to consolidate what I have been doing regarding reproducibility so far, in my teaching, research, and the current role of UKRN local network leads.

Fresh off the press, the paper on mixture distribution for network degrees is now available online on Statistica Neerlandica! The presentations I have recently made at Sunbelt Conference and an internal research day are based on the same paper, but we have changed the title to hopefully make it more appealing to the network science community.