A Comparison of Bayesian and Sampling Theory Inferences in a Probit Model

HE PROBIT MODEL IS A POPULAR DEVICE for explaining binary choice decisions in econometrics. It has been used to describe choices such as labor force participation, travel mode, home ownership, and type of education. These and many more examples can be found in papers by Amemiya (1981) and Maddala (1983). Given the contribution of economics towards explaining such choices, and given the nature of data that are collected, prior information on the relationship between a choice probability and several explanatory variables frequently exists. Bayesian inference is a convenient vehicle for including such prior information. Given the increasing popularity of Bayesian inference it is useful to ask whether inferences from a probit model are sensitive to a choice between Bayesian and sampling theory techniques. Of interest is the sensitivity of inference on coefficients, probabilities, and elasticities. We consider these issues in a model designed to explain choice between fixed and variable interest rate mortgages. Two Bayesian priors are employed: a uniform prior on the coefficients, designed to be noninformative for the coefficients, and an inequality restricted prior on the signs of the coefficients. We often know, a priori, whether increasing the value of a particular explanatory variable will have a positive or negative effect on a choice probability. This knowledge can be captured by using a prior probability density function (pdf) that is truncated to be positive or negative. Thus, three sets of results are compared:those from maximum likelihood (ML) estimation, those from Bayesian estimation with an unrestricted uniform prior on the coefficients, and those from Bayesian estimation with a uniform prior truncated to accommodate inequality restrictions on the coefficients.

Robust parameter settings of evolutionary algorithms for the optimisation of agricultural systems models

Numerical optimisation methods are being more commonly applied to agricultural systems models, to identify the most profitable management strategies. The available optimisation algorithms are reviewed and compared, with literature and our studies identifying evolutionary algorithms (including genetic algorithms) as superior in this regard to simulated annealing, tabu search, hill-climbing, and direct-search methods. Results of a complex beef property optimisation, using a real-value genetic algorithm, are presented. The relative contributions of the range of operational options and parameters of this method are discussed, and general recommendations listed to assist practitioners applying evolutionary algorithms to the solution of agricultural systems. (C) 2001 Elsevier Science Ltd. All rights reserved.

The effects of copper on the microbial community of a coral reef sponge

Marine sponges often harbour communities of symbiotic microorganisms that fulfil necessary functions for the well-being of their hosts. Microbial communities associated with the sponge Rhopaloeides odorabile were used as bioindicators far sublethal cupric ion (Cu2+) stress. A combined strategy incorporating molecular, cultivation and electron microscopy techniques was adopted to monitor changes in microbial diversity. The total density of sponge-associated bacteria and counts of the predominant cultivated symbiont (alpha -proteobacterium strain NW001) were significantly reduced in response to Cu2+ concentrations of 1.7 mug l(-1) and above after 14 days of exposure. The number of operational taxonomic units (OTUs) detected by restriction fragment length polymorphism (RFLP) decreased by 64% in sponges exposed to 223 mug l(-1) Cu2+ for 48 h and by 46% in sponges exposed to 19.4 mug l(-1) Cu2+ for 14 days. Electron microscopy was used to identify 17 predominant bacterial morphotypes, composing 47% of the total observed cells in control sponges. A reduction In the proportion of these morphotypes to 25% of observed cells was evident in sponges exposed to a Cu2+ concentration of 19.4 mug l(-1). Although the abundance of most morphotypes decreased under Cu2+ stress, three morphotypes were not reduced in numbers and a single morphotype actually increased in abundance. Bacterial numbers, as detected using fluorescence in situ hybridization (FISH), decreased significantly after 48 h exposure to 19.4 mug l(-1) Cu2+. Archaea, which are normally prolific in R. odorabile, were not detected after exposure to a Cu2+ concentration of 19.4 mug l(-1) for 14 days, indicating that many of the microorganisms associated with R. odorabile are sensitive to free copper. Sponges exposed to a Cu2+ concentration of 223 mug l(-1) became highly necrosed after 48 h and accumulated 142 +/- 18 mg kg(-1) copper, whereas sponges exposed to 19.4 mug l(-1) Cu2+ accumulated 306 +/- 15 mg kg(-1) copper after 14 days without apoptosis or mortality. Not only do sponges have potential for monitoring elevated concentrations of heavy metals but also examining changes in their microbial symbionts is a novel and sensitive bioindicator for the assessment of pollution on important microbial communities.

Tactics at the interface: Australian Aboriginal and Torres Strait Islander health managers

Over the past thirty years in Australia, there has been a recognition of the need for increasing Aboriginal and Torres Strait Islander participation in the management of their health services as part of the strategy to improve the poor health of Australia's indigenous peoples. The proliferation of Aboriginal Community-Controlled Health Services and the vigorous advocacy of groups such as the National Aboriginal Community Controlled Health Organisation have significantly contributed to this recognition. This, combined with additional management opportunities in government service, has drawn attention to difficulties in recruiting and retaining appropriately experienced Aboriginal and Torres Strait Islander managers, particularly in the northern states of Australia. (C) 2001 Elsevier Science Ltd. All rights reserved.