• home

Abstract: We develop a method for estimating population abundance for difficult to count populations. This is made possible using an easy to count auxiliary population with a known link to the target population. We apply the new methods to estimate the breeding population of a particular Ancient Murrelet seabird colony, using Ancient Murrelet chicks as an auxiliary population. We compare our results to those of the established survey methodology from the Canadian Wildlife Service (CWS), which similarly shows a decrease in population over 1995 to 2006. Our methods improve upon the CWS survey methods by allowing density differences across sampling sites, and by allowing estimates to be made between CWS survey years.

TBA

Abstract: Thanks to the advancement of modern technology in acquiring data, massive data with diverse features and big volume are becoming more accessible than ever. The impact of big data is significant. While the abundant volume of data presents great opportunities for researchers to extract useful information for new knowledge gain and sensible decision making, big data present great challenges. A very important, sometimes overlooked challenge is the quality and provenance of the data. Big data are not automatically useful; big data are often raw and involve considerable noise.

Typically, the challenges presented by noisy data with measurement error, missing observations and high dimensionality are particularly intriguing. Noisy data with these features arise ubiquitously from various fields including health sciences, epidemiological studies, environmental studies, survey research, economics, and so on. In this talk, I will discuss some issues induced from noisy data and how these features may challenge inferential procedures.

Abstract: The endangered population of BC’s southern resident killer whales (SRKW) is facing imminent threats to their survival, with an urgent need for science knowledge to inform management and recovery plans. Underwater noise and ship strikes are significant threats to this species' survival. During the past three summers, the Port of Vancouver has slowed the speed of commercial vessels in the Salish Sea to reduce underwater noise. We’ve been building simulation models to better understand how these vessel slowdowns and noise reductions impact the SRKW population. In this talk, I will present some studies designed to provide input information for these models. First, results from a spatial-temporal point-process model for whale distributions is presented. This accounts for highly heterogeneous effort associated with the collections of presence-only sightings from citizen scientists. Second, predictive whale movement models are being developed. I will present some new methodological approaches for simulating the 3-D movement of whales that takes into account the cumulative behavioural response to noise. We have also started to build the methodological framework for a 3-D stochastic movement model for whale pod locations based in auto-regressive dynamics and MCMC. It is designed to work as a component of a real-time ensemble prediction system for determining probable whale pathways using opportunistic sightings and underwater acoustic data. Collectively, these studies aim to quantify risk and impacts from anthropogenic noise to help define policy around where, when and what mitigation actions should be prioritized.

ABSTRACT: Spatial capture-recapture can be applied to acoustic monitoring using a grid of microphones where the call is "recaptured" across the grid. However, currently it is only able to estimate "call" and not "caller" density due to the uncertainty in individual ID between calls. For species that stay relatively close to the same location throughout the study, we observe clusters of calls around their activity centre. Using this spatial information can help differentiate the unique individuals in the population. I will introduce some new ideas using Dirichlet Process Mixture Models to partition the set of latent capture histories to the most likely group of calls in the context of terrestrial acoustics.

ABSTRACT: The problem of testing for the order of finite mixture models has a long history and remains a hot research topic for a foreseeable future. Since Ghosh (1985) pointed out the undesirable asymptotic properties of the likelihood ratio test in this context, there have been marked progresses toward addressing this challenging problem. The seemingly neat and well-defined problem is challenging numerically, mathematically and statistically. The most proud development of of my research team have been the modified likelihood ratio test and the EM-test. The idea of EM-test has been extensively explored for independent and identically distributed observations, for data from hidden Markov model, and for data from regression mixtures. It possesses neat solutions to finite mixture of univariate normal distributions and several other mixtures. At the same time, it seems to be less powerful when handling mixtures of general multi-parameter distributions. In this talk, we present our recent work on finite mixture of distributions from location-scale families. We show that the EM-test has manageable limiting distributions in general, and neat chi-square limiting distributions for some important examples.