Using approximate Bayesian computation to estimate transmission rates of nosocomial pathogens

In this paper, we apply a simulation based approach for estimating transmission rates of nosocomial pathogens. In particular, the objective is to infer the transmission rate between colonised health-care practitioners and uncolonised patients (and vice versa) solely from routinely collected incidence data. The method, using approximate Bayesian computation, is substantially less computer intensive and easier to implement than likelihood-based approaches we refer to here. We find through replacing the likelihood with a comparison of an efficient summary statistic between observed and simulated data that little is lost in the precision of estimated transmission rates. Furthermore, we investigate the impact of incorporating uncertainty in previously fixed parameters on the precision of the estimated transmission rates.

The relationship between chronic disease self-efficacy and nutritional status, functional ability and quality of life in older adults at risk of hospital readmission

Background and significance: Older adults with chronic diseases are at increasing risk of hospital admission and readmission. Approximately 75% of adults have at least one chronic condition, and the odds of developing a chronic condition increases with age. Chronic diseases consume about 70% of the total Australian health expenditure, and about 59% of hospital events for chronic conditions are potentially preventable. These figures have brought to light the importance of the management of chronic disease among the growing older population. Many studies have endeavoured to develop effective chronic disease management programs by applying social cognitive theory. However, limited studies have focused on chronic disease self-management in older adults at high risk of hospital readmission. Moreover, although the majority of studies have covered wide and valuable outcome measures, there is scant evidence on examining the fundamental health outcomes such as nutritional status, functional status and health-related quality of life. Aim: The aim of this research was to test social cognitive theory in relation to self-efficacy in managing chronic disease and three health outcomes, namely nutritional status, functional status, and health-related quality of life, in older adults at high risk of hospital readmission. Methods: A cross-sectional study design was employed for this research. Three studies were undertaken. Study One examined the nutritional status and validation of a nutritional screening tool; Study Two explored the relationships between participants. characteristics, self-efficacy beliefs, and health outcomes based on the study.s hypothesized model; Study Three tested a theoretical model based on social cognitive theory, which examines potential mechanisms of the mediation effects of social support and self-efficacy beliefs. One hundred and fifty-seven patients aged 65 years and older with a medical admission and at least one risk factor for readmission were recruited. Data were collected from medical records on demographics, medical history, and from self-report questionnaires. The nutrition data were collected by two registered nurses. For Study One, a contingency table and the kappa statistic was used to determine the validity of the Malnutrition Screening Tool. In Study Two, standard multiple regression, hierarchical multiple regression and logistic regression were undertaken to determine the significant influential predictors for the three health outcome measures. For Study Three, a structural equation modelling approach was taken to test the hypothesized self-efficacy model. Results: The findings of Study One suggested that a high prevalence of malnutrition continues to be a concern in older adults as the prevalence of malnutrition was 20.6% according to the Subjective Global Assessment. Additionally, the findings confirmed that the Malnutrition Screening Tool is a valid nutritional screening tool for hospitalized older adults at risk of readmission when compared to the Subjective Global Assessment with high sensitivity (94%), and specificity (89%) and substantial agreement between these two methods (k = .74, p < .001; 95% CI .62-.86). Analysis data for Study Two found that depressive symptoms and perceived social support were the two strongest influential factors for self-efficacy in managing chronic disease in a hierarchical multiple regression. Results of multivariable regression models suggested advancing age, depressive symptoms and less tangible support were three important predictors for malnutrition. In terms of functional status, a standard regression model found that social support was the strongest predictor for the Instrumental Activities of Daily Living, followed by self-efficacy in managing chronic disease. The results of standard multiple regression revealed that the number of hospital readmission risk factors adversely affected the physical component score, while depressive symptoms and self-efficacy beliefs were two significant predictors for the mental component score. In Study Three, the results of the structural equation modelling found that self-efficacy partially mediated the effect of health characteristics and depression on health-related quality of life. The health characteristics had strong direct effects on functional status and body mass index. The results also indicated that social support partially mediated the relationship between health characteristics and functional status. With regard to the joint effects of social support and self-efficacy, social support fully mediated the effect of health characteristics on self-efficacy, and self-efficacy partially mediated the effect of social support on functional status and health-related quality of life. The results also demonstrated that the models fitted the data well with relative high variance explained by the models, implying the hypothesized constructs under discussion were highly relevant, and hence the application for social cognitive theory in this context was supported. Conclusion: This thesis highlights the applicability of social cognitive theory on chronic disease self-management in older adults at risk of hospital readmission. Further studies are recommended to validate and continue to extend the development of social cognitive theory on chronic disease self-management in older adults to improve their nutritional and functional status, and health-related quality of life.

Spatial and temporal clusters of Barmah Forest virus disease in Queensland, Australia

Objective To identify the spatial and temporal clusters of Barmah Forest virus (BFV) disease in Queensland in Australia, using geographical information systems (GIS) and spatial scan statistic (SaTScan). Methods We obtained BFV disease cases, population and statistical local areas boundary data from Queensland Health and Australian Bureau of Statistics respectively during 1992-2008 for Queensland. A retrospective Poisson-based analysis using SaTScan software and method was conducted in order to identify both purely spatial and space-time BFV disease high-rate clusters. A spatial cluster size of a proportion of the population and a 200km circle radius and varying time windows from 1 month to 12 months were chosen (for the space-time analysis). Results The spatial scan statistic detected a most likely significant purely spatial cluster (including 23 SLAs) and a most likely significant space-time cluster (including 24 SLAs) in approximately the same location. Significant secondary clusters were also identified from both the analyses in several locations. Conclusions This study provides evidence of the existence of statistically significant BFV disease clusters in Queensland, Australia. The study also demonstrated the relevance and applicability of SaTScan in analysing on-going surveillance data to identify clusters to facilitate the development of effective BFV disease prevention and control strategies in Queensland, Australia.

Spatio-temporal patterns of Barmah Forest virus disease in Queensland, Australia

Background Barmah Forest virus (BFV) disease is a common and wide-spread mosquito-borne disease in Australia. This study investigated the spatio-temporal patterns of BFV disease in Queensland, Australia using geographical information system (GIS) tools and geostatistical analysis. Methods/Principal Findings We calculated the incidence rates and standardised incidence rates of BFV disease. Moran's I statistic was used to assess the spatial autocorrelation of BFV incidences. Spatial dynamics of BFV disease was examined using semi-variogram analysis. Interpolation techniques were applied to visualise and display the spatial distribution of BFV disease in statistical local areas (SLAs) throughout Queensland. Mapping of BFV disease by SLAs reveals the presence of substantial spatio-temporal variation over time. Statistically significant differences in BFV incidence rates were identified among age groups (χ2 = 7587, df = 7327,p<0.01). There was a significant positive spatial autocorrelation of BFV incidence for all four periods, with the Moran's I statistic ranging from 0.1506 to 0.2901 (p<0.01). Semi-variogram analysis and smoothed maps created from interpolation techniques indicate that the pattern of spatial autocorrelation was not homogeneous across the state. Conclusions/Significance This is the first study to examine spatial and temporal variation in the incidence rates of BFV disease across Queensland using GIS and geostatistics. The BFV transmission varied with age and gender, which may be due to exposure rates or behavioural risk factors. There are differences in the spatio-temporal patterns of BFV disease which may be related to local socio-ecological and environmental factors. These research findings may have implications in the BFV disease control and prevention programs in Queensland.

Spectrum sensing, detection and optimisation in cognitive radio for non-stationary primary user signals

Cognitive radio is an emerging technology proposing the concept of dynamic spec- trum access as a solution to the looming problem of spectrum scarcity caused by the growth in wireless communication systems. Under the proposed concept, non- licensed, secondary users (SU) can access spectrum owned by licensed, primary users (PU) so long as interference to PU are kept minimal. Spectrum sensing is a crucial task in cognitive radio whereby the SU senses the spectrum to detect the presence or absence of any PU signal. Conventional spectrum sensing assumes the PU signal as ‘stationary’ and remains in the same activity state during the sensing cycle, while an emerging trend models PU as ‘non-stationary’ and undergoes state changes. Existing studies have focused on non-stationary PU during the transmission period, however very little research considered the impact on spectrum sensing when the PU is non-stationary during the sensing period. The concept of PU duty cycle is developed as a tool to analyse the performance of spectrum sensing detectors when detecting non-stationary PU signals. New detectors are also proposed to optimise detection with respect to duty cycle ex- hibited by the PU. This research consists of two major investigations. The first stage investigates the impact of duty cycle on the performance of existing detec- tors and the extent of the problem in existing studies. The second stage develops new detection models and frameworks to ensure the integrity of spectrum sensing when detecting non-stationary PU signals. The first investigation demonstrates that conventional signal model formulated for stationary PU does not accurately reflect the behaviour of a non-stationary PU. Therefore the performance calculated and assumed to be achievable by the conventional detector does not reflect actual performance achieved. Through analysing the statistical properties of duty cycle, performance degradation is proved to be a problem that cannot be easily neglected in existing sensing studies when PU is modelled as non-stationary. The second investigation presents detectors that are aware of the duty cycle ex- hibited by a non-stationary PU. A two stage detection model is proposed to improve the detection performance and robustness to changes in duty cycle. This detector is most suitable for applications that require long sensing periods. A second detector, the duty cycle based energy detector is formulated by integrat- ing the distribution of duty cycle into the test statistic of the energy detector and suitable for short sensing periods. The decision threshold is optimised with respect to the traffic model of the PU, hence the proposed detector can calculate average detection performance that reflect realistic results. A detection framework for the application of spectrum sensing optimisation is proposed to provide clear guidance on the constraints on sensing and detection model. Following this framework will ensure the signal model accurately reflects practical behaviour while the detection model implemented is also suitable for the desired detection assumption. Based on this framework, a spectrum sensing optimisation algorithm is further developed to maximise the sensing efficiency for non-stationary PU. New optimisation constraints are derived to account for any PU state changes within the sensing cycle while implementing the proposed duty cycle based detector.

Statistical and scientometric analysis of international research in geographical and environmental education

Certain statistic and scientometric features of articles published in the journal “International Research in Geographical and Environmental Education” are examined in this paper, for the period 1992-2009, by applying nonparametric statistics and Shannon’s entropy (diversity) formula. The main findings of this analysis are: a) after 2004 the research priorities of researchers in geographical and environmental education seem to have changed, b) “teacher education” has been the most recurrent theme throughout these 18 years, followed by “values & attitudes” and “inquiry & problem solving” c) the themes “GIS” and “Sustainability” were the most “stable” throughout the 18 years, meaning that they maintained their ranks as publication priorities more than other themes, d) citations of IRGEE increase annually, e) the average thematic diversity of articles published during the period 1992-2009 is 82.7% of the maximum thematic diversity (very high), meaning that the Journal has the capacity to attract a wide readership for the 10 themes it has successfully covered throughout the 18 years of its publication.

A known-groups evaluation of the Response Bias Scale in a neuropsychological setting

We evaluated the Minnesota Multiphasic Personality Inventory-Second Edition (MMPI-2) Response Bias Scale (RBS). Archival data from 83 individuals who were referred for neuropsychological assessment with no formal diagnosis (n = 10), following a known or suspected traumatic brain injury (n = 36), with a psychiatric diagnosis (n = 20), or with a history of both trauma and a psychiatric condition (n = 17) were retrieved. The criteria for malingered neurocognitive dysfunction (MNCD) were applied, and two groups of participants were formed: poor effort (n = 15) and genuine responders (n = 68). Consistent with previous studies, the difference in scores between groups was greatest for the RBS (d = 2.44), followed by two established MMPI-2 validity scales, F (d = 0.25) and K (d = 0.23), and strong significant correlations were found between RBS and F (rs = .48) and RBS and K (r = −.41). When MNCD group membership was predicted using logistic regression, the RBS failed to add incrementally to F. In a separate regression to predict group membership, K added significantly to the RBS. Receiver-operating curve analysis revealed a nonsignificant area under the curve statistic, and at the ideal cutoff in this sample of >12, specificity was moderate (.79), sensitivity was low (.47), and positive and negative predictive power values at a 13% base rate were .25 and .91, respectively. Although the results of this study require replication because of a number of limitations, this study has made an important first attempt to report RBS classification accuracy statistics for predicting poor effort at a range of base rates.

Bayesian algorithms with applications

Advances in algorithms for approximate sampling from a multivariable target function have led to solutions to challenging statistical inference problems that would otherwise not be considered by the applied scientist. Such sampling algorithms are particularly relevant to Bayesian statistics, since the target function is the posterior distribution of the unobservables given the observables. In this thesis we develop, adapt and apply Bayesian algorithms, whilst addressing substantive applied problems in biology and medicine as well as other applications. For an increasing number of high-impact research problems, the primary models of interest are often sufficiently complex that the likelihood function is computationally intractable. Rather than discard these models in favour of inferior alternatives, a class of Bayesian "likelihoodfree" techniques (often termed approximate Bayesian computation (ABC)) has emerged in the last few years, which avoids direct likelihood computation through repeated sampling of data from the model and comparing observed and simulated summary statistics. In Part I of this thesis we utilise sequential Monte Carlo (SMC) methodology to develop new algorithms for ABC that are more efficient in terms of the number of model simulations required and are almost black-box since very little algorithmic tuning is required. In addition, we address the issue of deriving appropriate summary statistics to use within ABC via a goodness-of-fit statistic and indirect inference. Another important problem in statistics is the design of experiments. That is, how one should select the values of the controllable variables in order to achieve some design goal. The presences of parameter and/or model uncertainty are computational obstacles when designing experiments but can lead to inefficient designs if not accounted for correctly. The Bayesian framework accommodates such uncertainties in a coherent way. If the amount of uncertainty is substantial, it can be of interest to perform adaptive designs in order to accrue information to make better decisions about future design points. This is of particular interest if the data can be collected sequentially. In a sense, the current posterior distribution becomes the new prior distribution for the next design decision. Part II of this thesis creates new algorithms for Bayesian sequential design to accommodate parameter and model uncertainty using SMC. The algorithms are substantially faster than previous approaches allowing the simulation properties of various design utilities to be investigated in a more timely manner. Furthermore the approach offers convenient estimation of Bayesian utilities and other quantities that are particularly relevant in the presence of model uncertainty. Finally, Part III of this thesis tackles a substantive medical problem. A neurological disorder known as motor neuron disease (MND) progressively causes motor neurons to no longer have the ability to innervate the muscle fibres, causing the muscles to eventually waste away. When this occurs the motor unit effectively ‘dies’. There is no cure for MND, and fatality often results from a lack of muscle strength to breathe. The prognosis for many forms of MND (particularly amyotrophic lateral sclerosis (ALS)) is particularly poor, with patients usually only surviving a small number of years after the initial onset of disease. Measuring the progress of diseases of the motor units, such as ALS, is a challenge for clinical neurologists. Motor unit number estimation (MUNE) is an attempt to directly assess underlying motor unit loss rather than indirect techniques such as muscle strength assessment, which generally is unable to detect progressions due to the body’s natural attempts at compensation. Part III of this thesis builds upon a previous Bayesian technique, which develops a sophisticated statistical model that takes into account physiological information about motor unit activation and various sources of uncertainties. More specifically, we develop a more reliable MUNE method by applying marginalisation over latent variables in order to improve the performance of a previously developed reversible jump Markov chain Monte Carlo sampler. We make other subtle changes to the model and algorithm to improve the robustness of the approach.

Regression and hypothesis tests for multivariate GNSS state time series

A satellite based observation system can continuously or repeatedly generate a user state vector time series that may contain useful information. One typical example is the collection of International GNSS Services (IGS) station daily and weekly combined solutions. Another example is the epoch-by-epoch kinematic position time series of a receiver derived by a GPS real time kinematic (RTK) technique. Although some multivariate analysis techniques have been adopted to assess the noise characteristics of multivariate state time series, statistic testings are limited to univariate time series. After review of frequently used hypotheses test statistics in univariate analysis of GNSS state time series, the paper presents a number of T-squared multivariate analysis statistics for use in the analysis of multivariate GNSS state time series. These T-squared test statistics have taken the correlation between coordinate components into account, which is neglected in univariate analysis. Numerical analysis was conducted with the multi-year time series of an IGS station to schematically demonstrate the results from the multivariate hypothesis testing in comparison with the univariate hypothesis testing results. The results have demonstrated that, in general, the testing for multivariate mean shifts and outliers tends to reject less data samples than the testing for univariate mean shifts and outliers under the same confidence level. It is noted that neither univariate nor multivariate data analysis methods are intended to replace physical analysis. Instead, these should be treated as complementary statistical methods for a prior or posteriori investigations. Physical analysis is necessary subsequently to refine and interpret the results.

Oceanografia UFBA : Desenvolvimento de Marca, Imagem e Identidade

A well-developed brand helps to establish a solid identity and creates support to an image that is coherent to the actual motivations in an institution. Educational institutions have inherent characteristics that are diverse from the other sort of institutions, mainly when the focus is set on its internal and external publics. Consequently, these institutions should deal with the development of their brand and identity system also in a different approach. This research aims to investigate the traditional methodology for brand and identity systems development and proposes some modifications in order to allow a broader inclusion of the stakeholders in the process. The implementation of the new Oceanography Course in the Federal University of Bahia (UFBA) offered a unique opportunity to investigate and test these new strategies. In order to investigate and relate the image, identity, interaction and experience concepts through a participative methodology, this research project applies the new suggested strategies in the development of a brand and an identity system for the Oceanography Course in UFBA. Open surveys have been carried out between the alumni, lecturers and coordination body, in order to discover and establish a symbol for the course. The statistic analysis of the surveys’ results showed clear aesthetic preferences to some icons and colours to represent the course. The participative methodology celebrated, in this project, a democratization of the generally expert-centred brand development process.

Exact and approximate Bayesian inference for low count time series models with intractable likelihoods

In this paper we present a new simulation methodology in order to obtain exact or approximate Bayesian inference for models for low-valued count time series data that have computationally demanding likelihood functions. The algorithm fits within the framework of particle Markov chain Monte Carlo (PMCMC) methods. The particle filter requires only model simulations and, in this regard, our approach has connections with approximate Bayesian computation (ABC). However, an advantage of using the PMCMC approach in this setting is that simulated data can be matched with data observed one-at-a-time, rather than attempting to match on the full dataset simultaneously or on a low-dimensional non-sufficient summary statistic, which is common practice in ABC. For low-valued count time series data we find that it is often computationally feasible to match simulated data with observed data exactly. Our particle filter maintains $N$ particles by repeating the simulation until $N+1$ exact matches are obtained. Our algorithm creates an unbiased estimate of the likelihood, resulting in exact posterior inferences when included in an MCMC algorithm. In cases where exact matching is computationally prohibitive, a tolerance is introduced as per ABC. A novel aspect of our approach is that we introduce auxiliary variables into our particle filter so that partially observed and/or non-Markovian models can be accommodated. We demonstrate that Bayesian model choice problems can be easily handled in this framework.

Quantifying spatial structure in experimental observations and agent-based simulations using pair-correlation functions

We define a pair-correlation function that can be used to characterize spatiotemporal patterning in experimental images and snapshots from discrete simulations. Unlike previous pair-correlation functions, the pair-correlation functions developed here depend on the location and size of objects. The pair-correlation function can be used to indicate complete spatial randomness, aggregation or segregation over a range of length scales, and quantifies spatial structures such as the shape, size and distribution of clusters. Comparing pair-correlation data for various experimental and simulation images illustrates their potential use as a summary statistic for calibrating discrete models of various physical processes.

No role for estrogen receptor 1 gene intron 1 Pvu II and exon 4 C325G polymorphisms in migraine susceptibility

Background We have previously reported an association between the estrogen receptor 1 (ESR1) gene exon 8 G594A polymorphism and migraine susceptibility in two independent Australian cohorts. In this paper we report results of analysis of two further single nucleotide polymorphisms (SNPs) in the ESR1 gene in the same study group, the T/C Pvu II SNP in intron 1 and the C325G SNP in exon 4, as well as results of linkage disequilibrium (LD) analysis on these markers. Methods We investigated these variants by case-control association analysis in a cohort of 240 migraineurs and 240 matched controls. The SNPs were genotyped using specific restriction enzyme assays. Results were analysed using contingency table methods incorporating the chi-squared statistic. LD results are presented as D' statistics with associated P values. Results We found no evidence for association of the Pvu II T/C polymorphism and the C325G polymorphism and migraine susceptibility and no evidence for LD between these two SNPs and the previously implicated exon 8 G594A marker. Conclusion We have found no role for the polymorphisms in intron 1 and exon 4 with migraine susceptibility. To further investigate our previously implicated exon 8 marker, we suggest the need for studies with a high density of polymorphisms be undertaken, with particular focus on markers in LD with the exon 8 marker.

Bayesian indirect inference using a parametric auxiliary model

Indirect inference (II) is a methodology for estimating the parameters of an intractable (generative) model on the basis of an alternative parametric (auxiliary) model that is both analytically and computationally easier to deal with. Such an approach has been well explored in the classical literature but has received substantially less attention in the Bayesian paradigm. The purpose of this paper is to compare and contrast a collection of what we call parametric Bayesian indirect inference (pBII) methods. One class of pBII methods uses approximate Bayesian computation (referred to here as ABC II) where the summary statistic is formed on the basis of the auxiliary model, using ideas from II. Another approach proposed in the literature, referred to here as parametric Bayesian indirect likelihood (pBIL), we show to be a fundamentally different approach to ABC II. We devise new theoretical results for pBIL to give extra insights into its behaviour and also its differences with ABC II. Furthermore, we examine in more detail the assumptions required to use each pBII method. The results, insights and comparisons developed in this paper are illustrated on simple examples and two other substantive applications. The first of the substantive examples involves performing inference for complex quantile distributions based on simulated data while the second is for estimating the parameters of a trivariate stochastic process describing the evolution of macroparasites within a host based on real data. We create a novel framework called Bayesian indirect likelihood (BIL) which encompasses pBII as well as general ABC methods so that the connections between the methods can be established.