Dr James Martin
|Themes||Multivariate and High Dimensional Data, Stochastic Modelling and Time Series|
I am a Research Associate within the Stochastic Processes Group at UCL, where I am carrying out work with large-scale populations of point processes under the direction of Professor Sofia Olhede. I completed my PhD in 2012 at Imperial College London, where my primary focus was likelihood-free approaches to filtering and smoothing problems.
I am currently exploring the nature of the dependence relationships involved in large populations of spatial point processes. Our interest lies predominantly in a theoretical examination of such relationships and the development of useful tools for quantifying the dependence present in these large populations. We are also interested in the application of this work to tropical forest census data collected from the Barro Colorado Island, Panama.
As well as carrying out research in point process theory, I maintain a strong interest in Monte Carlo methodology, particularly sequential Monte Carlo methods, and the use of approximate Bayesian computation in facilitating likelihood-free statistical analysis. For more details on this work, please see my publications, below.
- Martin, J. S., Jasra, A., Singh, S. S., Whiteley, N., Del Moral, P., McCoy, E. (2014). Approximate Bayesian Computation for Smoothing. Stochastic Analysis and Applications 32, 397-422 doi:10.1080/07362994.2013.879262.
- Martin, J. S., Jasra, A., McCoy, E. (2013). Inference for a class of partially observed point process models. Annals of the Institute of Statistical Mathematics 65(3), 413-437 doi:10.1007/s10463-012-0375-8.
- Jasra, A., Singh, S. S., Martin, J. S., McCoy, E. (2012). Filtering via approximate Bayesian computation. Statistics and Computing 22(6), 1223-1237 doi:10.1007/s11222-010-9185-0.