Design and analysis of quasi-experiments in landscape ecology

The context for this PhD is the application of statistical science in the study of interrelationships between fauna and environments undergoing change in landscape ecology. The core of the thesis is a collection of papers, arising from four major studies that can be viewed in two ways:  1) a set of studies in statistical practice in the field of ecology, and 2) as contributions to new knowledge on the effects of landscape vegetation transformation on fauna, in particular birds, in south-eastern Australia. The focus in this thesis is as much on scientific process as it is on biological outcomes. Emphasis is on collaborative contributions to ecology and conservation of wildlife through an understanding of ecological issues from a statistical perspective.

In this talk I will present some of the statistical thinking behind the research through statistical design and statistical modelling.  I begin by summarising important statistical differences between true experiments and quasi and natural experiments. Focusing on the South west slopes (NSW) vegetation restoration study I will then discuss several statistical analysis of data arising from this study and highlight some subsequent ecological outcomes. These include new insights into effects of revegetation establishment and subsequent maturation on different groups of biota, in particular birds.  Cross-sectional and temporal responses to revegetation, regrowth, and remnant vegetation at multiple spatial scales will be discussed. 

About the speaker

Ross is an Adjunct Professor in the Fenner School. Among many career highlights he was Head, Statistical Consulting Unit, ANU 1982-2001; discovered of a new species of possum; published over 280 papers in referreed journals in many scientific fields and was involved in election night forecasting for Channel 10 and the ABC 1980-2000.