Skip to main content

Posts

Showing posts from October, 2022

Seminar 21 Oct @2pm

Do you have a moment? Bayesian inference using estimating equations via empirical likelihood Speaker: Professor Howard Bondell, University of Melbourne Time: 2-3PM Friday 21 Oct Zoom link at  https://uni-sydney.zoom.us/j/89779295453 Bayesian inference typically relies on specification of a likelihood as a key ingredient. Recently, likelihood-free approaches have become popular to avoid specification of potentially intractable likelihoods. Alternatively, in the Frequentist context, estimating equations are a popular choice for inference corresponding to an assumption on a set of moments (or expectations) of the underlying distribution, rather than its exact form. Common examples are in the use of generalised estimating equations with correlated responses, or in the use of M-estimators for robust regression avoiding the distributional assumptions on the errors. In this talk, I will discuss some of the motivation behind empirical likelihood, and how it can be used to incorporate a fully

Seminar 26 October @6:30pm

  On behalf of SSA NSW branch, we would like to invite you to join the virtual event we are holding on Wednesday 26th October at 6.30 pm. Brian Cullis from University of Wollongong will speak about optimal design of Comparative Experiments and the odw R Package. Date:  Wednesday, 26th October Time:  6.30 pm Location:  F10A.01.105.Law Building Annex.Law Annex Seminar Room 105, The University of Sydney and on Zoom. Attendance:  Please  RSVP here  if attending in person to help us cater for the talk and make dinner reservations. Please  register here  if joining virtually for the Zoom link. Speaker:  Brian Cullis Title:  On the Optimal Design of Comparative Experiments and the odw R Package   Abstract The optimal design of experiments has enjoyed a rich theoretical development, with elements dating back to 1918. While able to reproduce (or validate the properties of) classical experimental designs, the technology is particularly useful for constructing designs in non-standard situations.

Seminar 11 October @ 16:00 (UTC)

    Bayesian model selection for likelihood-based and simulation-based inference Date: Tuesday, 11 October 2022   Time: 16:00 (UTC)   Speaker:  Prof. Jason McEwen (University College London, UK)    Contact the organizer: Andriy Olenko a.olenko@latrobe.edu.au Abstract: In the study of cosmology, where we seek to uncover an understanding of the fundamental physical processes underlying the origin, content, and evolution of our Universe, we are not blessed with the ability to perform experiments -- rather, we have only one Universe to observe.  In this scenario, while we are of course interested in estimating the parameters of models describing the physical processes observed, we are often most interested in selecting the best underlying model, which has given rise to the prevalence of Bayesian model selection in cosmology and astrophysics.  While I will motivate recent developments in Bayesian model selection from problems in cosmology and astrophysics, I will mostly focus on new method

Seminar @4pm Friday 14th October

Stochastic spatial random forest for detecting remotely sensed forest cover change despite missing data Date: 14 October 2022, Friday Time: 4pm AEDT Speaker: Dr Jacinta Holloway-Brown (University of Adelaide) Abstract: Forest cover is an indicator of species habitat and biodiversity that can be monitored effectively using satellite images. The benefits of using satellite images for large scale forest monitoring are that they are freely available globally and frequently updated, which reduces the need for extensive field data collection. Field data collection to monitor forest change can be prohibitively costly in many places around the world. A challenge of working with these images is missing data due to clouds, particularly in tropical regions where forest monitoring is essential. Existing methods for interpolating missing data based on only past observations, such as compositing, are effective for stable land cover but inaccurate for dynamic and substantially changing landscapes. In