I recently provided advice on the precision to be expected from a trial of a new method of luring mammalian pests (feral cats, possums, and stoats, for example), to be carried out in Hikaroroa Reserve, near Karitane, NZ. This work was carried out for Thomas Hayward of Mammalian Corrections Unit (Dunedin, NZ), and was valuable in assessing the number of traps, and number of days trapping, that would be required to obtain a precise estimate of the increase in the kill-rate from using the new method.
I am delighted to be part of the five-year research project “Te Weu o te Kaitiaki – Indigenous Regeneration Pathways” that has just been funded by the Aotearoa New Zealand government. The proposal for this research was co-led led by Phil Lyver and Johanna Yletyinen of Manaaki Whenua (Landcare Research). It will use te ao Māori worldview and whakapapa frameworks alongside the integration of value and ecological networks to re-imagine biocultural solutions that simultaneously restore ecological systems, reinforce identity, reconnect people to place, enhance community wellbeing, and deliver sustainable economic growth for communities.
There is now an online course to go with my book on model averaging. This course provides an up-to date overview of the topic, from both the Bayesian and frequentist perspective, including methods that are popular in machine learning, such as bagging and stacking. Recent developments, published since the book came out in 2018, are also covered, including confidence distributions, the frequentist analogue of posterior distributions. There is emphasis on understanding the theory underlying the methods and on experience using the methods in RStudio.
Cost: US$200 (+ applicable taxes) for 30 days access. You can find more information and registration details here
I have recently been providing advice to Mark Herse, a PhD student at the University of Canterbury, on statistical issues relating to population modelling of black swans.
I am looking forward to collaborating with Darryl MacKenzie and Stefan Meyer of Proteus Wildlife Research Consultants early next year on a project funded by the New Zealand Ministry of Primary Industries looking at the risk from fisheries bycatch to marine mammal species.
I recently provided advice on the use of “single-fit” bootstrapping to obtain confidence intervals for indices of relative abundance, when fitting a delta-lognormal model to fisheries data. The key idea is that of resampling the model parameters from a multivariate normal distribution. This is computationally nice as it allows a parametric bootstrap confidence interval to be calculated without refitting the model. You can find more details about “single-fit” bootstrapping in these seminar slides.
I have recently been providing advice to STIMBR (Stakeholders in Methyl Bromide Reduction) on the estimation of percentiles when modelling the dispersion of chemicals in the atmosphere. It was interesting to see just how unreliably the highest upper percentiles of a skewed distribution are estimated, even from a very large sample. This has implications for the use of such percentiles in setting environmental health regulations.
It’s great to be able to use my research experience in estimating overdispersion on an important scientific problem. One of the key aspects of the problem is the sparseness in the data, which are multinomial with a very large number of categories.
Joint work with Farzana Afroz and Matt Parry will be particularly useful in this setting, as we were able to derive an estimate of overdispersion that works really well for sparse multinomial data: the paper we published can be found here.
It’s been great to have these two papers come out in the last couple of weeks:
Model-averaged confidence distributions: https://link.springer.com/article/10.1007/s10651-019-00432-5
Estimating overdispersion in sparse multinomial data: