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.

International market selection: Developing a model from Australian case studies

This paper develops a theory that firms seek out new country markets on the basis of expected commercial returns. These expectations depend on judgements about the attractiveness of the market and the firm's competitive position in it, which in turn are influenced by informants. It is the number and strengths of these informants that will underlie the probability of a country being identified and assessed as a new market by any firm.

Comparison between Eysenck's and Gray's models of personality in the prediction of motivational work criteria

Impulsivity based on Gray's [Gray, J. A. (1982) The neuropsychology of anxiety: an enquiry into the function of the septo-hippocampal system. New York: Oxford University Press: (1991). The neurophysiology of temperament. In J. Strelau & A. Angleitner. Explorations in temperament: international perspectives on theory and measurement. London. Plenum Press]. physiological model of personality was hypothesised to be more predictive of goal oriented criteria within the workplace than scales derived From Eysenck's [Eysenck. H.J. (1967). The biological basis of personality. Springfield, IL: Charles C. Thompson.] physiological model of personality. Results confirmed the hypothesis and also showed that Gray's scale of Impulsivity was generally a better predictor than attributional style and interest in money. Results were interpreted as providing support for Gray's Behavioural Activation System which moderates response to reward. (C) 2001 Elsevier Science Ltd. All rights reserved.

Exact quantum phase model for mesoscopic Josephson junctions

Starting from the two-mode Bose-Hubbard model, we derive an exact version of the standard Mathieu equation governing the wave function of a Josephson junction. For a finite number of particles N, we find an additional cos 2 phi term in the potential. We also find that the inner product in this representation is nonlocal in phi. Our model exhibits phenomena, such as pi oscillations, which are not found in the standard phase model, but have been predicted from Gross-Pitaevskii mean-field theory.

Fitting a mixture model to three-mode three-way data with missing information

When the data consist of certain attributes measured on the same set of items in different situations, they would be described as a three-mode three-way array. A mixture likelihood approach can be implemented to cluster the items (i.e., one of the modes) on the basis of both of the other modes simultaneously (i.e,, the attributes measured in different situations). In this paper, it is shown that this approach can be extended to handle three-mode three-way arrays where some of the data values are missing at random in the sense of Little and Rubin (1987). The methodology is illustrated by clustering the genotypes in a three-way soybean data set where various attributes were measured on genotypes grown in several environments.

MRI based diffusion and perfusion predictive model to estimate stroke evolution

In this study we present a novel automated strategy for predicting infarct evolution, based on MR diffusion and perfusion images acquired in the acute stage of stroke. The validity of this methodology was tested on novel patient data including data acquired from an independent stroke clinic. Regions-of-interest (ROIs) defining the initial diffusion lesion and tissue with abnormal hemodynamic function as defined by the mean transit time (MTT) abnormality were automatically extracted from DWI/PI maps. Quantitative measures of cerebral blood flow (CBF) and volume (CBV) along with ratio measures defined relative to the contralateral hemisphere (r(a)CBF and r(a)CBV) were calculated for the MTT ROIs. A parametric normal classifier algorithm incorporating these measures was used to predict infarct growth. The mean r(a)CBF and r(a)CBV values for eventually infarcted MTT tissue were 0.70 +/-0.19 and 1.20 +/-0.36. For recovered tissue the mean values were 0.99 +/-0.25 and 1.87 +/-0.71, respectively. There was a significant difference between these two regions for both measures (P

Predicting coal ash slag flow characteristics (viscosity model for the Al2O3-CaO-'FeO'-SiO2 system)

A model has been developed which enables the viscosities of coal ash slags to be predicted as a function of composition and temperature under reducing conditions. The model describes both completely liquid and heterogeneous, i.e. partly crystallised, slags in the Al2O3-CaO-'FeO'-SiO2 system in equilibrium with metallic iron. The Urbain formalism has been modified to describe the viscosities of the liquid slag phase over the complete range of compositions and a wide range of temperatures. The computer package F * A * C * T was used to predict the proportions of solids and the compositions of the remaining liquid phases. The Roscoe equation has been used to describe the effect of presence of solid suspension (slurry effect) on the viscosity of partly crystallised slag systems. The model provides a good description of the experimental data of fully liquid, and liquid + solids mixtures, over the complete range of compositions and a wide range of temperatures. This model can now be used for viscosity predictions in industrial slag systems. Examples of the application of the new model to coal ash fluxing and blending are given in the paper. (C) 2001 Elsevier Science Ltd. All rights reserved.

Mass balance characterisation of Al-7Si-Mg alloy microstructures as a function of solution treatment time

Mass balance calculations were performed to model the effect of solution treatment time on A356 and A357 alloy microstructures. Image analysis and electron probe microanalysis were used to characterise microstructures and confirm model predictions. In as-cast microstructures, up to 8 times more Mg is tied up in the pi-phase than in Mg2Si. The dissolution of pi is accompanied by a corresponding increase in the amount of beta-phase. This causes the rate of pi dissolution to be limited by the rate of beta formation. It is predicted that solution treatments of the order of tens of minutes at 540degreesC produce near-maximum T6 yield strengths, and that Mg contents in excess of 0.52 wt% have no advantage.

An improved survival model of hypoxia/ischaemia in the piglet suitable for neuroprotection studies

The purpose of this study, was to develop a newborn piglet model of hypoxia/ischaemia which would better emulate the clinical situation in the asphyxiated human neonate and produce a consistent degree of histopathological injury following the insult. One-day-old piglets (n = 18) were anaesthetised with a mixture of propofol (10 mg/kg/h) and alfentinal (5,5.5 mug/kg/h) i.v. The piglets were intubated and ventilated. Physiological variables were monitored continuously. Hypoxia was induced by decreasing the inspired oxygen (FiO(2)) to 3-4% and adjusting FiO(2) to maintain the cerebral function monitor peak amplitude at less than or equal to5 muV. The duration of the mild insult was 20, min while the severe insult was 30 min which included 10 min where the blood pressure was allowed to fall below 70% of baseline. Control piglets (n=4 of 18) were subjected to the same protocol except for the hypoxic/ischaemic insult. The piglets were allowed to recover from anaesthesia then euthanased 72 It after the insult. The brains were perfusion-fixed, removed and embedded in paraffin. Coronal sections were stained by haematoxylin/eosin. A blinded observer examined the frontal and parietal cortex, hippocampus, basal ganglia, thalamus and cerebellum for the degree of damage. The total mean histology score for the five areas of the brain for the severe insult was 15.6 +/-4.4 (mean +/-S.D., n=7), whereas no damage was seen in either the mild insult (n=4) or control groups. This 'severe damage' model produces a consistent level of damage and will prove useful for examining potential neuroprotective therapies in the neonatal brain. (C) 2001 Elsevier Science BY. All rights reserved.

Effect of the toxic milk mutation (tx) on the function and intracellular localization of Wnd, the murine homologue of the Wilson copperATPase

Wilson disease is an autosomal recessive copper transport disorder resulting from defective biliary excretion of copper and subsequent hepatic copper accumulation and liver failure if not treated. The disease is caused by mutations in the ATP7B (WND) gene, which is expressed predominantly in the liver and encodes a copper-transporting P-type ATPase that is structurally and functionally similar to the Menkes protein (MNK), which is defective in the X-linked copper transport disorder Menkes disease. The toxic milk (tx) mouse has a clinical phenotype similar to Wilson disease patients and, recently, the tx mutation within the murine WND homologue (Wnd) of this mouse was identified, establishing it as an animal model for Wilson disease. In this study, cDNA constructs encoding the wild-type (Wnd-wt) and mutant (Wnd-tx) Wilson proteins (Wnd) were generated and expressed in Chinese hamster ovary (CHO) cells. The fx mutation disrupted the copper-induced relocalization of Wnd in CHO cells and abrogated Wnd-mediated copper resistance of transfected CHO cells. In addition, co-localization experiments demonstrated that while Wnd and MNK are located in the trans-Golgi network in basal copper conditions, with elevated copper, these proteins are sorted to different destinations within the same cell, Ultrastructural studies showed that with elevated copper levels, Wnd accumulated in large multivesicular structures resembling late endosomes that may represent a novel compartment for copper transport. The data presented provide further support for a relationship between copper transport activity and the copper-induced relocalization response of mammalian copper ATPases, and an explanation at a molecular level for the observed phenotype of fx mice.

A zero-augmented gamma mixed model for longitudinal data with many zeros

In many occupational safety interventions, the objective is to reduce the injury incidence as well as the mean claims cost once injury has occurred. The claims cost data within a period typically contain a large proportion of zero observations (no claim). The distribution thus comprises a point mass at 0 mixed with a non-degenerate parametric component. Essentially, the likelihood function can be factorized into two orthogonal components. These two components relate respectively to the effect of covariates on the incidence of claims and the magnitude of claims, given that claims are made. Furthermore, the longitudinal nature of the intervention inherently imposes some correlation among the observations. This paper introduces a zero-augmented gamma random effects model for analysing longitudinal data with many zeros. Adopting the generalized linear mixed model (GLMM) approach reduces the original problem to the fitting of two independent GLMMs. The method is applied to evaluate the effectiveness of a workplace risk assessment teams program, trialled within the cleaning services of a Western Australian public hospital.

Analysis of the microbial community structure and function of a laboratory scale enhanced biological phosphorus removal reactor

A laboratory scale sequencing batch reactor (SBR) operating for enhanced biological phosphorus removal (EBPR) and fed with a mixture of volatile fatty acids (VFAs) showed stable and efficient EBPR capacity over a four-year-period. Phosphorus (P), poly-beta-hydroxyalkanoate (PHA) and glycogen cycling consistent with classical anaerobic/aerobic EBPR were demonstrated with the order of anaerobic VFA uptake being propionate, acetate then butyrate. The SBR was operated without pH control and 63.67+/-13.86 mg P l(-1) was released anaerobically. The P% of the sludge fluctuated between 6% and 10% over the operating period (average of 8.04+/-1.31%). Four main morphological types of floc-forming bacteria were observed in the sludge during one year of in-tensive microscopic observation. Two of them were mainly responsible for anaerobic/aerobic P and PHA transformations. Fluorescence in situ hybridization (FISH) and post-FISH chemical staining for intracellular polyphosphate and PHA were used to determine that 'Candidatus Accumulibacter phosphatis' was the most abundant polyphosphate accumulating organism (PAO), forming large clusters of coccobacilli (1.0-1.5 mum) and comprising 53% of the sludge bacteria. Also by these methods, large coccobacillus-shaped gammaproteobacteria (2.5-3.5 mum) from a recently described novel cluster were glycogen-accumulating organisms (GAOs) comprising 13% of the bacteria. Tetrad-forming organisms (TFOs) consistent with the 'G bacterium' morphotype were alphaproteobacteria , but not Amaricoccus spp., and comprised 25% of all bacteria. According to chemical staining, TFOs were occasionally able to store PHA anaerobically and utilize it aerobically.

Reconciling value estimates from the discounted cash flow model and the residual income model

This paper examines why practitioners and researchers get different estimates of equity value when they use a discounted cash flow (CF) model versus a residual income (RI) model. Both models are derived from the same underlying assumption -- that price is the present value of expected future net dividends discounted at the cost of equity capital -- but in practice and in research they frequently yield different estimates. We argue that the research literature devoted to comparing the accuracy of these two models is misguided; properly implemented, both models yield identical valuations for all firms in all years. We identify how prior research has applied inconsistent assumptions to the two models and show how these seemingly small errors cause surprisingly large differences in the value estimates. [ABSTRACT FROM AUTHOR]

Developing a meta model for the Bunge-Wand-Weber ontological constructs

At the core of the analysis task in the development process is information systems requirements modelling, Modelling of requirements has been occurring for many years and the techniques used have progressed from flowcharting through data flow diagrams and entity-relationship diagrams to object-oriented schemas today. Unfortunately, researchers have been able to give little theoretical guidance only to practitioners on which techniques to use and when. In an attempt to address this situation, Wand and Weber have developed a series of models based on the ontological theory of Mario Bunge-the Bunge-Wand-Weber (BWW) models. Two particular criticisms of the models have persisted however-the understandability of the constructs in the BWW models and the difficulty in applying the models to a modelling technique. This paper addresses these issues by presenting a meta model of the BWW constructs using a meta language that is familiar to many IS professionals, more specific than plain English text, but easier to understand than the set-theoretic language of the original BWW models. Such a meta model also facilitates the application of the BWW theory to other modelling techniques that have similar meta models defined. Moreover, this approach supports the identification of patterns of constructs that might be common across meta models for modelling techniques. Such findings are useful in extending and refining the BWW theory. (C) 2002 Elsevier Science Ltd. All rights reserved.