Standard errors of fitted component means of normal mixtures

In this paper use consider the problem of providing standard errors of the component means in normal mixture models fitted to univariate or multivariate data by maximum likelihood via the EM algorithm. Two methods of estimation of the standard errors are considered: the standard information-based method and the computationally-intensive bootstrap method. They are compared empirically by their application to three real data sets and by a small-scale Monte Carlo experiment.

Developments in the understanding of South African style SAG mills

The South African style SAG (RoM) mills operate in a window that is almost exclusive from the operation of the Australian and North American mills that have been used for the development of SAG mill models. Combining good quality, test data from the RoM mills is extending and improving these models, and assisting in a practical manner in improving our understanding of SAG/AG milling. Data from high mill loads, both in absolute filling and ball loading, have been used to extend and improve the JK SAG mill model. This improved understanding has been successfully applied to increasing the throughput of a mill by 8%. Data is presented on relationships between power and load for high mill loading. Slurry pooling is common in closed-circuit RoM mills, and the detrimental effect of this has been dramatically demonstrated at ALCOA with a mill throughput increase of over 20%. Techniques for calculating the effects of slurry pooling have been developed and a new pulp lifter system designed to give optimal slurry discharge. The influence of mill speed in shifting the product size distribution has also been measured. (C) 2001 Elsevier Science Ltd. All rights reserved.

Low-density koala (Phascolarctos cinereus) populations in the mulgalands of south-west Queensland. I. Faecal pellet sampling protocol

Koala (Phascolarctos cinereus) populations in eastern Australia are threatened by land clearing for agricultural and urban development. At the same time, conservation efforts are hindered by a dearth of information about inland populations. Faecal deposits offer a source of information that is readily available and easily collected non-invasively. We detail a faecal pellet sampling protocol that was developed for use in a large rangeland biogeographic region. The method samples trees in belt transects, uses a thorough search at the tree base to quickly identify trees with koala pellets under them, then estimates the abundance of faecal pellets under those trees using 1-m(2) quadrats. There was a strong linear relationship between these estimates and a complete enumeration of pellet abundance under the same trees. We evaluated the accuracy of our method in detecting trees where pellets were present by means of a misclassification index that was weighed more heavily for missed trees that had high numbers of pellets under them. This showed acceptable accuracy in all landforms except riverine, where some trees with large numbers of pellets were missed. Here, accuracy in detecting pellet presence was improved by sampling with quadrats, rather than basal searches. Finally, we developed a method to reliably age pellets and demonstrate how this protocol could be used with the faecal-standing-crop method to derive a regional estimate of absolute koala abundance.

Low-density koala (Phascolarctos cinereus) populations in the mulgalands of south-west Queensland. III. Broad-scale patterns of habitat use

To date there have been few quantitative studies of the distribution of, and relative habitat utilisation by, koalas in the mulgalands of Queensland. To examine these parameters we applied habitat-accessibility and relative habitat-utilisation indices to estimates of faecal pellet density sampled at 149 sites across the region. Modelling the presence of pellets using logistic regression showed that the potential range of accessible habitats and relative habitat use varied greatly across the region, with rainfall being probably the most important determinant of distribution. Within that distribution, landform and rainfall were both important factors affecting habitat preference. Modelling revealed vastly different probabilities of finding a pellet under trees depending on the tree species, canopy size, and location within the region.

Low-density koala (Phascolarctos cinereus) populations in the mulgalands of south-west Queensland. II. Distribution and diet

This study used faecal pellets to investigate the broadscale distribution and diet of koalas in the mulgalands biogeographic region of south-west Queensland. Koala distribution was determined by conducting faecal pellet searches within a 30-cm radius of the base of eucalypts on 149 belt transects, located using a multi-scaled stratified sampling design. Cuticular analysis of pellets collected from 22 of these sites was conducted to identify the dietary composition of koalas within the region. Our data suggest that koala distribution is concentrated in the northern and more easterly regions of the study area, and appears to be strongly linked with annual rainfall. Over 50% of our koala records were obtained from non-riverine communities, indicating that koalas in the study area are not primarily restricted to riverine communities, as has frequently been suggested. Cuticular analysis indicates that more than 90% of koala diet within the region consists of five eucalypt species. Our data highlights the importance of residual Tertiary landforms to koala conservation in the region.