Intractable differences : artistic research and the problem of practice

The purpose of this paper is to analyse the complex nature of practice within Artistic research. This will be done by considering practice through the lens of Bourdieu’s conceptualisation of practice. The focus of the paper is on developing an understanding of practice-led approaches to research and how these are framed by what Coessens et al. (2009) call the artistic turn in research. The paper begins with a brief introduction to the nature of practice and then continues on to discuss the broader field of artistic research, describing the environment which has shaped its evolution and foregrounding several of its key dispositions. The paper aims to not simply describe existing methodology but to rethink what is meant by artistic research and practice-led strategies.

Automatic Audio Segmentation Using the Generalized Likelihood Ratio

This paper presents a novel technique for segmenting an audio stream into homogeneous regions according to speaker identities, background noise, music, environmental and channel conditions. Audio segmentation is useful in audio diarization systems, which aim to annotate an input audio stream with information that attributes temporal regions of the audio into their specific sources. The segmentation method introduced in this paper is performed using the Generalized Likelihood Ratio (GLR), computed between two adjacent sliding windows over preprocessed speech. This approach is inspired by the popular segmentation method proposed by the pioneering work of Chen and Gopalakrishnan, using the Bayesian Information Criterion (BIC) with an expanding search window. This paper will aim to identify and address the shortcomings associated with such an approach. The result obtained by the proposed segmentation strategy is evaluated on the 2002 Rich Transcription (RT-02) Evaluation dataset, and a miss rate of 19.47% and a false alarm rate of 16.94% is achieved at the optimal threshold.

Eigenvoice modeling for cross likelihood ratio based speaker clustering : a Bayesian approach

This paper proposes the use of Bayesian approaches with the cross likelihood ratio (CLR) as a criterion for speaker clustering within a speaker diarization system, using eigenvoice modeling techniques. The CLR has previously been shown to be an effective decision criterion for speaker clustering using Gaussian mixture models. Recently, eigenvoice modeling has become an increasingly popular technique, due to its ability to adequately represent a speaker based on sparse training data, as well as to provide an improved capture of differences in speaker characteristics. The integration of eigenvoice modeling into the CLR framework to capitalize on the advantage of both techniques has also been shown to be beneficial for the speaker clustering task. Building on that success, this paper proposes the use of Bayesian methods to compute the conditional probabilities in computing the CLR, thus effectively combining the eigenvoice-CLR framework with the advantages of a Bayesian approach to the diarization problem. Results obtained on the 2002 Rich Transcription (RT-02) Evaluation dataset show an improved clustering performance, resulting in a 33.5% relative improvement in the overall Diarization Error Rate (DER) compared to the baseline system.

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.

Likelihood‐free inference for transmission rates of nosocomial pathogens

This chapter contains sections titled: Introduction Case study: Estimating transmission rates of nosocomial pathogens Models and methods Data analysis and results Discussion References

Bayesian computation via empirical likelihood

Approximate Bayesian computation has become an essential tool for the analysis of complex stochastic models when the likelihood function is numerically unavailable. However, the well-established statistical method of empirical likelihood provides another route to such settings that bypasses simulations from the model and the choices of the approximate Bayesian computation parameters (summary statistics, distance, tolerance), while being convergent in the number of observations. Furthermore, bypassing model simulations may lead to significant time savings in complex models, for instance those found in population genetics. The Bayesian computation with empirical likelihood algorithm we develop in this paper also provides an evaluation of its own performance through an associated effective sample size. The method is illustrated using several examples, including estimation of standard distributions, time series, and population genetics models.

A quasi-maximum likelihood method for estimating the parameters of multivariate diffusions

A quasi-maximum likelihood procedure for estimating the parameters of multi-dimensional diffusions is developed in which the transitional density is a multivariate Gaussian density with first and second moments approximating the true moments of the unknown density. For affine drift and diffusion functions, the moments are exactly those of the true transitional density and for nonlinear drift and diffusion functions the approximation is extremely good and is as effective as alternative methods based on likelihood approximations. The estimation procedure generalises to models with latent factors. A conditioning procedure is developed that allows parameter estimation in the absence of proxies.

Self-reported likelihood of speeding : the effects of attitudes, personality, and perceived legitimacy of enforcement

The positive relationship between speed and crash risk and severity is robust and well-established. While excessive speeding is typically regarded by the public as a common contributing factor in road crashes, speeding remains a common traffic infringement and an arguably socially acceptable behaviour, particularly at low levels over the speed limit. This suggests that other factors potentially contribute to this disparity between crash perceptions and actual behaviours. Previous work has described associations between perceptions of the legitimacy of speed enforcement, attitudes, and how they relate to the likelihood of speeding. This study sought to more closely examine the nature of the relationships between these variables. In total, 293 Queensland drivers participated in a study that examined how demographics, personality variables, attitudes, and perceptions of the legitimacy of enforcement contributed to drivers’ self-reported likelihood of speeding. Results suggested that positive attitudes towards speeding had the greatest impact on likelihood of speeding behaviours. Being younger and higher levels of the personality trait of extraversion were also associated with greater levels of self-reported likelihood of speeding. Attitudes were found to mediate the relationship between perceived legitimacy of speed enforcement and self-reported likelihood of speeding. A subgroup analysis of participants with positive and negative attitudes towards speeding revealed that a differential set of variables were predictive of self-reported likelihood of speeding for the two subgroups. This highlights the potential importance of attitudes in understanding the influence of perceptions of legitimacy of speed enforcement on speeding behaviour, and the need for targeted rather than a ‘one size fits all’ approach to changing attitudes and ultimately behaviour. The findings of the current study help to further understand why some drivers continue to speed.

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.

Shrinkage empirical likelihood estimator in longitudinal analysis with time-dependent covariates-application to modeling the health of Filipino children

The method of generalized estimating equations (GEE) is a popular tool for analysing longitudinal (panel) data. Often, the covariates collected are time-dependent in nature, for example, age, relapse status, monthly income. When using GEE to analyse longitudinal data with time-dependent covariates, crucial assumptions about the covariates are necessary for valid inferences to be drawn. When those assumptions do not hold or cannot be verified, Pepe and Anderson (1994, Communications in Statistics, Simulations and Computation 23, 939–951) advocated using an independence working correlation assumption in the GEE model as a robust approach. However, using GEE with the independence correlation assumption may lead to significant efficiency loss (Fitzmaurice, 1995, Biometrics 51, 309–317). In this article, we propose a method that extracts additional information from the estimating equations that are excluded by the independence assumption. The method always includes the estimating equations under the independence assumption and the contribution from the remaining estimating equations is weighted according to the likelihood of each equation being a consistent estimating equation and the information it carries. We apply the method to a longitudinal study of the health of a group of Filipino children.

'Too high in human terms' : the costs of high security imprisonment. Review of Imprisoning Resistance by Bree Carlton and Intractable by Bernie Matthews.

The article discusses the issues of resistance; that is resistance by prisoners to the various manifestations of power operating in high security prisons, as well as that of attempted shifts in the regime from physical to psychological control. Other topics highlighted include legitimacy and 'official discourse', mourning and the construction of 'ungrievable lives' and the importance of finding a way out of the cycle of violence, which high security regimes perpetuate.

Predicting the likelihood of QA failure using treatment plan accuracy metrics

This study used automated data processing techniques to calculate a set of novel treatment plan accuracy metrics, and investigate their usefulness as predictors of quality assurance (QA) success and failure. 151 beams from 23 prostate and cranial IMRT treatment plans were used in this study. These plans had been evaluated before treatment using measurements with a diode array system. The TADA software suite was adapted to allow automatic batch calculation of several proposed plan accuracy metrics, including mean field area, small-aperture, off-axis and closed-leaf factors. All of these results were compared the gamma pass rates from the QA measurements and correlations were investigated. The mean field area factor provided a threshold field size (5 cm2, equivalent to a 2.2 x 2.2 cm2 square field), below which all beams failed the QA tests. The small aperture score provided a useful predictor of plan failure, when averaged over all beams, despite being weakly correlated with gamma pass rates for individual beams. By contrast, the closed leaf and off-axis factors provided information about the geometric arrangement of the beam segments but were not useful for distinguishing between plans that passed and failed QA. This study has provided some simple tests for plan accuracy, which may help minimise time spent on QA assessments of treatments that are unlikely to pass.

Recursive pathways to marginal likelihood estimation with prior-sensitivity analysis

We investigate the utility to computational Bayesian analyses of a particular family of recursive marginal likelihood estimators characterized by the (equivalent) algorithms known as "biased sampling" or "reverse logistic regression" in the statistics literature and "the density of states" in physics. Through a pair of numerical examples (including mixture modeling of the well-known galaxy dataset) we highlight the remarkable diversity of sampling schemes amenable to such recursive normalization, as well as the notable efficiency of the resulting pseudo-mixture distributions for gauging prior-sensitivity in the Bayesian model selection context. Our key theoretical contributions are to introduce a novel heuristic ("thermodynamic integration via importance sampling") for qualifying the role of the bridging sequence in this procedure, and to reveal various connections between these recursive estimators and the nested sampling technique.

What aspects of demographic, personality, attitudes, and perceptions of law enforcement influence self-reported likelihood of drink driving?

The aim of the current study was to examine the associations between a number of individual factors (demographic factors (age and gender), personality factors, risk-taking propensity, attitudes towards drink driving, and perceived legitimacy of drink driving enforcement) and how they influence the self-reported likelihood of drink driving. The second aim of this study was to examine the potential of attitudes mediating the relationship between risk-taking and self-reported likelihood of drink driving. In total, 293 Queensland drivers volunteered to participate in an online survey that assessed their self-reported likelihood to drink drive in the next month, demographics, traffic-related demographics, personality factors, risk-taking propensity, attitudes towards drink driving, and perceived legitimacy of drink driving enforcement. An ordered logistic regression analysis was utilised to evaluate the first aim of the study; at the first step the demographic variables were entered; at step two the personality and risk-taking were entered; at the third step, the attitudes and perceptions of legitimacy variables were entered. Being a younger driver and having a high risk-taking propensity were related to self-reported likelihood of drink driving. However, when the attitudes variable was entered, these individual factors were no longer significant; with attitudes being the most important predictor of self-reported drink driving likelihood. A significant mediation model was found with the second aim of the study, such that attitudes mediated the relationship between risk-taking and self-reported likelihood of drink driving. Considerable effort and resources are utilised by traffic authorities to reducing drink driving on the Australian road network. Notwithstanding these efforts, some participants still had some positive attitudes towards drink driving and reported that they were likely to drink drive in the future. These findings suggest that more work is needed to address attitudes regarding the dangerousness of drink driving.

Novel use of faecal sterols to assess human faecal contamination in Antarctica : a likelihood assessment matrix for environmental monitoring

Wastewater containing human sewage is often discharged with little or no treatment into the Antarctic marine environment. Faecal sterols (primarily coprostanol) in sediments have been used for assessment of human sewage contamination in this environment, but in situ production and indigenous faunal inputs can confound such determinations. Using gas chromatography with mass spectral detection profiles of both C27 and C29 sterols, potential sources of faecal sterols were examined in nearshore marine sediments, encompassing sites proximal and distal to the wastewater outfall at Davis Station. Faeces from indigenous seals and penguins were also examined. Faeces from several indigenous species contained significant quantities of coprostanol but not 24-ethylcoprostanol, which is present in human faeces. In situ coprostanol and 24-ethylcoprostanol production was identified by co-production of their respective epi isomers at sites remote from the wastewat er source and in high total organic matter sediments. A C 29 sterols-based polyphasic likelihood assessment matrix for human sewage contamination is presented, which distinguishes human from local fauna faecal inputs and in situ production in the Antarctic environment. Sewage contamination was detected up to 1.5 km from Davis Station.