Author Archives: djc24

Uncategorized

Congratulations to Emily Dennis for Honourable Mention from the judges of the 2017 Young Biometrician’s Award

Congratulations to Emily Dennis who received an “Honourable Mention” from the judges of the 2017 Young Biometrician’s Award, jointly run by the British & Irish Region of the International Biometric Society and the Fisher Memorial Trust. This was for her contribution to the 2016 Biometrics paper “A generalised abundance index for seasonal invertebrates”, which was written whist at the University of Kent. 

The panel comprised Professor R A Bailey, on behalf of the Fisher Memorial Trust, Dr G Hepworth from the University of Melbourne as international judge and Professor S G Thompson representing the British & Irish Region.

 

Standard
Uncategorized

Congratulations to Natoya

Congratulations to Natoya Jourdain for passing her PhD.

Natoya’s PhD was on New Analytical Methods for Camera Trap Data.

Abstract

Density estimation of terrestrial mammals has become increasingly important in ecology, and robust analytical tools are required to provide results that will guide wildlife management. This thesis concerns modelling encounters between unmarked animals and camera traps for density estimation. We explore Rowcliffe et al. (2008) Random Encounter Model (REM) developed for estimating density of species that cannot be identied to the individual level from camera trap data. We demonstrate how REM can be used within a maximum likelihood framework to estimate density of unmarked animals, motivated by the analysis of a data set from Whipsnade Wild Animal Park (WWAP), Bedfordshire, south England. The remainder of the thesis focuses on developing and evaluating extended Random Encounter Models, which describe the data in an integrated population modelling framework. We present a variety of approaches for modelling population abundance in an integrated Random Encounter Model (iREM), where complicating features are the variation in the encounters and animal species. An iREM is a more exible and robust parametric model compared with a nonparametric REM, which produces novel and meaningful parameters relating to density, accounting for the sampling variability in the parameters required for density estimation. The iREM model we propose can describe how abundance changes with diverse factors such as habitat type and climatic conditions. We develop models to account for induced-bias in the density  from faster moving animals, which are more likely to encounter camera traps, and address the independence assumption in integrated population models. The models we propose consider a functional relationship between a camera index and animal density and represent a step forward with respect to the current simplistic modeling approaches for abundance estimation of unmarked animals from camera trap data. We illustrate the application of the models proposed to a community of terrestrial mammals from a tropical moist forest at Barro Colorado Island (BCI), Panama.

 

Standard
Uncategorized

New Perspectives on State Space Models

From 27th Aug – 1st Sept Diana attended the BIRS workshop New Perspectives on State Space Models in Oaxaca, Mexico.

On Monday Diana gave the 5 minute lightening talk: Talk Slides

Then on Thursday Diana presented a 2 hour workshop on parameter identifiability: Work shop slides

The recording of the workshop session is available at

http://www.birs.ca/events/2017/5-day-workshops/17w5120/videos/watch/201708310917-Cole.html 

Standard
Uncategorized

EURING 2017 Analytical Meeting

From 2nd to 7th July Marina, Ming and Alex attended the EURING Analytical Meeting in Barcelona, Spain.

Marina gave a talk on Ring-Recovery Methods for Historical Ringing Data. Talk slides are available at: Jimenez-Munoz Slides

Ming presented a poster on The use of penalised likelihood to improve estimation in removal models. The poster is available at: Zhou Poster

Alex gave a talk on A hierarchical Bayesian nonparametric model for bird migration patterns in UK breeding sites.

 

Standard
Uncategorized

NCSE Summer Meeting

From the 26th June to 29th June, at Kent we hosted the 7th NCSE summer meeting. We hosted 37 statisticians and ecologists from across the UK and beyond.

On Monday Byron gave a talk on a stochastic dynamic model for longitudinal butterfly data, Ming presented work on the use of penalised likelihood to improve estimation in removal models, Alex talked about a Polya Tree based model for counts of unmarked individuals in an open population and Eleni gave a talk on modelling temporary emigration using a Bayesian nonparametric changepoint process for capture-recapture data. On Tuesday  Diana presented work on problems with using data cloning to investigate identifiability. On Wednesday Marina talked about integrated population models incorporating spatial information and Takis presented work on estimation of roe deer population density in a mountainous Mediterranean area using hierarchical distance sampling. The full program of talks and abstracts can be found at http://tiny.cc/ncsemeeting.

 

Standard
Uncategorized

Statistics Gone Wild

On 23rd June the SE@K group hosted 110 school pupils in years 7 to 9 at the event Statistics Gone Wild.

The event started with an introduction, on counting animals, given by Diana, where each of the students were given animal cards representing one of the above six species. (More information on the research done on these six species is given here  http://blogs.kent.ac.uk/seak/2017/05/22/statistics-gone-wild-animals/)

There were then 3 interactive sessions:

–Capture-Recapture (throwing birds in the air) given by Alex;

–Occupancy Modelling (looking for hidden penguins) given by Marina;

–Removal Modelling (digging for lizards in the sand) given by Ming.

The day ended with an interactive quiz, given by Eleni.

 

Thank you to Joe Watkins for organizing and running the day, thank you to the 3 ambassadors, John, Kezia & Patrick, for their support throughout the day. And thank you to Kerry, Judith and Amy for their admin support.

Standard
Uncategorized

Statistics Gone Wild – Animals

As part of our Statistics gone wild event for schools on 23rd June 2017 we highlighted six animal species that our group has been working with. Below you can find out more information about the work the group has been doing on each of these animals.

Small Copper Butterfly (Lycaena phlaeas)

Emily Dennis (formerly University of Kent, currently Butterfly Conservation) and Byron Morgan (University of Kent)  working with Butterfly Conservation and the Centre for Ecology and Hydrology have been developing and improving statistical models for monitoring butterfly populations. This includes a recent paper that was published in the journal Ecological Indicators with Tom Brereton (Butterfly Conservation) and David Roy (Centre for Ecology and Hydrology),  and the articles in several newspapers:

https://www.theguardian.com/environment/2017/feb/16/urban-butterfly-declines-69-compared-to-45-drop-countryside

http://www.dailymail.co.uk/sciencetech/article-4229306/Paving-gardens-hits-city-butterflies.html

http://butterfly-conservation.org/48-14855/butterflies-declining-faster-in-urban-areas.html

 

Great Crested Newt (Triturus cristatus)

The Durrell Institute for Conservation and Ecology (DICE) at the University of Kent has a long running project that collects data on newt populations breeding in ponds located near the Canterbury campus. Several of the group have helped to collect this data (https://www.kent.ac.uk/smsas/statistics/research/seak-news.html?view=429) . Richard Griffiths, David Sewell and Rachel McCrea looked at statistical models that examine the effect the climate has on the survival of newts, which has been published in Biological Conservation (http://www.sciencedirect.com/science/article/pii/S0006320709004820).

Other studies on Great Crested Newts have looked at removing (and relocating) newts from sites that are being developed. Recent work published in the Annals of Applied Statistics  by Eleni Matechou, Rachel McCrea, Byron Morgan, Darryn Nash and Richard Griffiths has developed better statistical models for this type of data (https://kar.kent.ac.uk/55734/7/AOAS949.pdf).

 

Early Bumblebee (Bombus pratorum)

 

Eleni Matechou has been collaborating with the Bumblebee Conservation Trust and the Centre for Ecology and Hydrology to develop new models for monitoring bumblebee populations using data collected as part of the citizen science scheme BeeWalk. The newly developed models allow us for the first time to estimate bumblebee  phenology, defined  as the study of cyclic and seasonal natural phenomena, especially in relation to climate and plant and animal life, and within-season productivity, defined as the number of individuals in each caste per colony in the population in that year. The results give a means of considerable ecological detail in examining temporal changes in the complex life-cycle of a social insect in the wild.

 

Semipalmated Sandpiper (Calidris pusilla)

Eleni Matechou in collaboration with researchers from the Department of Statistics, University of Oxford in the UK, the North Carolina Cooperative Fish and Wildlife Research Unit and the Patuxent Wildlife Research Center in the USA, has developed models for estimating the number of migratory birds present at a site each day of the season as well as the total population size.  The approach is shown to provide new ecological insights about the stopover behaviour of semipalmated sandpipers as it can distinguish between birds that use multiple stopover sites for brief periods of time and birds that visit fewer sites but have longer stopovers. The work has resulted in two published papers in the Journal of Agricultural, Environmental and Ecological Statistics  and in the journal Environmental and Ecological Statistics.

 

 

Galapagos Penguin (Spheniscus mendiculus)

Marina Jimenez-Munoz, with Eleni Matechou and Diana Cole, have been working on modeling data from the Charles Darwin Foundation on the Galapagos Penguin collected by Gustavo Jimenez (Charles Darwin Foundation). The Galapagos Penguin is an endangered species which is very vulnerable weather fluctuations (particularly to strong El Niño events), and human activities. These penguins nest in islands, often in cavities which are of difficult access to biologists. For this reason data collection may be at times challenging, resulting in low capture probabilities and/or misleading counts. The aim is to build an integrated analysis which combines multilevel occupancy and mark-recapture data in order to estimate the change in abundance and survival for this species. ​​

Alpine Ibex (Capra ibex)

Rachel McCrea has been working with Achaz von Hardenberg from University of Chester on modeling data on the Alpine Ibex. The Alpine ibex population in Gran Paradiso National Park (Northwestern Italian Alps) has suffered a dramatic decline over the last 20 years. Previous models, based on total count data available since 1956, identified density dependence and winter snow cover as the main drivers of the population dynamics until it reached its peak in 1993, but were unable to predict the subsequent decline. The population fall-off is associated with a strong decline in kid survival which passed from an average of 0.58 (rate of kids which reach the yearling stage in 1981-1990) to an average of 0.35 in the last 10 years. Two main hypotheses have been proposed to explain this decline: i) Ageing of the population: in ungulates older females are known to have lower fertility and produce less viable kids; ii) Mismatch between trophic and breeding phenology due to climate change. Current research involves fitting integrated population models to determine which of these hypotheses drives the observed dynamics. Integrated population modeling involves combining two or more different types of data, with different models, in one integrated analysis.

 

 

 

Standard
Papers

Biometrics Paper: Hidden Markov Models for Extended Batch Data

The paper Hidden Markov Models for Extended Batch Data by Laura L. E. Cowen, Panagiotis Besbeas, Byron J. T. Morgan and Carl J. Schwarz has been published online early in Biometrics

Summary. Batch marking provides an important and efficient way to estimate the survival probabilities and population sizes of wild animals. It is particularly useful when dealing with animals that are difficult to mark individually. For the first time, we provide the likelihood for extended batch-marking experiments. It is often the case that samples contain individuals that remain unmarked, due to time and other constraints, and this information has not previously been analysed. We provide ways of modelling such information, including an open N-mixture approach. We demonstrate that models for both marked and unmarked individuals are hidden Markov models; this provides a unified approach, and is the key to developing methods for fast likelihood computation and maximisation. Likelihoods for marked and unmarked individuals can easily be combined using integrated population modelling. This allows the simultaneous estimation of population size and immigration, in addition to survival, as well as efficient estimation of standard errors and methods of model selection and evaluation, using standard likelihood techniques. Alternative methods for estimating population size are presented and compared. An illustration is provided by a weather-loach data set, previously analysed by means of a complex procedure of constructing a pseudo likelihood, the formation of estimating equations, the use of sandwich estimates of variance, and piecemeal estimation of population size. Simulation provides general validation of the hidden Markov model methods developed and demonstratestheir excellent performance and efficiency. This is especially notable due to the large numbers of hidden states that may be typically required​

 

Standard