Evaluating multivariate volatility forecasts : how effective are statistical and economic loss functions?

Multivariate volatility forecasts are an important input in many financial applications, in particular portfolio optimisation problems. Given the number of models available and the range of loss functions to discriminate between them, it is obvious that selecting the optimal forecasting model is challenging. The aim of this thesis is to thoroughly investigate how effective many commonly used statistical (MSE and QLIKE) and economic (portfolio variance and portfolio utility) loss functions are at discriminating between competing multivariate volatility forecasts. An analytical investigation of the loss functions is performed to determine whether they identify the correct forecast as the best forecast. This is followed by an extensive simulation study examines the ability of the loss functions to consistently rank forecasts, and their statistical power within tests of predictive ability. For the tests of predictive ability, the model confidence set (MCS) approach of Hansen, Lunde and Nason (2003, 2011) is employed. As well, an empirical study investigates whether simulation findings hold in a realistic setting. In light of these earlier studies, a major empirical study seeks to identify the set of superior multivariate volatility forecasting models from 43 models that use either daily squared returns or realised volatility to generate forecasts. This study also assesses how the choice of volatility proxy affects the ability of the statistical loss functions to discriminate between forecasts. Analysis of the loss functions shows that QLIKE, MSE and portfolio variance can discriminate between multivariate volatility forecasts, while portfolio utility cannot. An examination of the effective loss functions shows that they all can identify the correct forecast at a point in time, however, their ability to discriminate between competing forecasts does vary. That is, QLIKE is identified as the most effective loss function, followed by portfolio variance which is then followed by MSE. The major empirical analysis reports that the optimal set of multivariate volatility forecasting models includes forecasts generated from daily squared returns and realised volatility. Furthermore, it finds that the volatility proxy affects the statistical loss functions’ ability to discriminate between forecasts in tests of predictive ability. These findings deepen our understanding of how to choose between competing multivariate volatility forecasts.

Cross likelihood ratio based speaker clustering using eigenvoice models

This paper proposes the use of eigenvoice modeling techniques with the Cross Likelihood Ratio (CLR) as a criterion for speaker clustering within a speaker diarization system. The CLR has previously been shown to be a robust decision criterion for speaker clustering using Gaussian Mixture Models. Recently, eigenvoice modeling techniques have become increasingly popular, due to its ability to adequately represent a speaker based on sparse training data, as well as an improved capture of differences in speaker characteristics. This paper hence proposes that it would be beneficial to capitalize on the advantages of eigenvoice modeling in a CLR framework. Results obtained on the 2002 Rich Transcription (RT-02) Evaluation dataset show an improved clustering performance, resulting in a 35.1% relative improvement in the overall Diarization Error Rate (DER) compared to the baseline system.

Letter to the editor : likelihood of tetraplegia after CT clearance of the cervical spine in obtunded blunt trauma patients

...the probabilistic computer simulation study by Dunham and colleagues evaluating the impact of different cervical spine management (CSM) strategies on tetraplegia and brain injury outcomes.1 Based on literature findings, expert opinion and with use of advances programming techniques the authors conclude that early collar removal without cervical spine magnetic resonance imaging (MRI) is a preferable CSM strategy for comatose, blunt trauma patients with extremity movement and a negative cervical spine computed tomography(CT) scan. Although we do not have the required expertise to comment on the applied statistical approach, we would like to comment on one of the medical assumptions raised by the authors, namely the likelihood of tetraplegia in this specific population....

Event-related brain potentials dissociate the developmental time-course of automatic numerical magnitude analysis and cognitive control functions during the first three years of primary school

In this study we set out to dissociate the developmental time course of automatic symbolic number processing and cognitive control functions in grade 1-3 British primary school children. Event-related potential (ERP) and behavioral data were collected in a physical size discrimination numerical Stroop task. Task-irrelevant numerical information was processed automatically already in grade 1. Weakening interference and strengthening facilitation indicated the parallel development of general cognitive control and automatic number processing. Relationships among ERP and behavioral effects suggest that control functions play a larger role in younger children and that automaticity of number processing increases from grade 1 to 3.

Structural damage detection using frequency response functions and neural networks

This paper illustrates the damage identification and condition assessment of a three story bookshelf structure using a new frequency response functions (FRFs) based damage index and Artificial Neural Networks (ANNs). A major obstacle of using measured frequency response function data is a large size input variables to ANNs. This problem is overcome by applying a data reduction technique called principal component analysis (PCA). In the proposed procedure, ANNs with their powerful pattern recognition and classification ability were used to extract damage information such as damage locations and severities from measured FRFs. Therefore, simple neural network models are developed, trained by Back Propagation (BP), to associate the FRFs with the damage or undamaged locations and severity of the damage of the structure. Finally, the effectiveness of the proposed method is illustrated and validated by using the real data provided by the Los Alamos National Laboratory, USA. The illustrated results show that the PCA based artificial Neural Network method is suitable and effective for damage identification and condition assessment of building structures. In addition, it is clearly demonstrated that the accuracy of proposed damage detection method can also be improved by increasing number of baseline datasets and number of principal components of the baseline dataset.

Structural damage identification with noise polluted Frequency Response Functions (FRFs)

Damage detection in structures has become increasingly important in recent years. While a number of damage detection and localization methods have been proposed, very few attempts have been made to explore the structure damage with noise polluted data which is unavoidable effect in real world. The measurement data are contaminated by noise because of test environment as well as electronic devices and this noise tend to give error results with structural damage identification methods. Therefore it is important to investigate a method which can perform better with noise polluted data. This paper introduces a new damage index using principal component analysis (PCA) for damage detection of building structures being able to accept noise polluted frequency response functions (FRFs) as input. The FRF data are obtained from the function datagen of MATLAB program which is available on the web site of the IASC-ASCE (International Association for Structural Control– American Society of Civil Engineers) Structural Health Monitoring (SHM) Task Group. The proposed method involves a five-stage process: calculation of FRFs, calculation of damage index values using proposed algorithm, development of the artificial neural networks and introducing damage indices as input parameters and damage detection of the structure. This paper briefly describes the methodology and the results obtained in detecting damage in all six cases of the benchmark study with different noise levels. The proposed method is applied to a benchmark problem sponsored by the IASC-ASCE Task Group on Structural Health Monitoring, which was developed in order to facilitate the comparison of various damage identification methods. The illustrated results show that the PCA-based algorithm is effective for structural health monitoring with noise polluted FRFs which is of common occurrence when dealing with industrial structures.

The perceived importance of mall retail categories and its effect on likelihood of purchase during a recession

Recessions impact the retail sector and as such research into consumer decision making during such times is imperative. In response to this, our study takes an innovative approach to examining how the perceived importance of retail store categories in a shopping mall influences the relationship between consumers' shopping attitudes and likelihood of purchasing in those categories during a recession. The overall findings show the importance of a product category to a consumer, which is often overlooked, has a strong explanatory influence on consumer purchase intentions for that specific retail store categories in a shopping mall under recession conditions. Findings also show that for consumers’ who have altered their shopping behaviour the perceived importance of a retail store category fully mediates the relationship for: Majors, Leisure, Food Catered and Mini Majors categories, and partial mediation for Apparel. Importance has no mediating effect for: Food Retail, General Retail, Mobile Phone Services, Home wares, and Retail Services. Our study makes a key contribution to the retail management literature with the findings suggesting that redefining and articulating the importance of the value offering for specific retail store categories can help reduce the impact of changes in consumers' recessionary shopping intentions across the mall tenant mix. Such actions can then help preserve the image of the shopping mall in the minds of the consumers when the economic recovery begins.

Novel methods and the maximum likelihood estimation technique for estimating traffic critical gap

Most unsignalised intersection capacity calculation procedures are based on gap acceptance models. Accuracy of critical gap estimation affects accuracy of capacity and delay estimation. Several methods have been published to estimate drivers’ sample mean critical gap, the Maximum Likelihood Estimation (MLE) technique regarded as the most accurate. This study assesses three novel methods; Average Central Gap (ACG) method, Strength Weighted Central Gap method (SWCG), and Mode Central Gap method (MCG), against MLE for their fidelity in rendering true sample mean critical gaps. A Monte Carlo event based simulation model was used to draw the maximum rejected gap and accepted gap for each of a sample of 300 drivers across 32 simulation runs. Simulation mean critical gap is varied between 3s and 8s, while offered gap rate is varied between 0.05veh/s and 0.55veh/s. This study affirms that MLE provides a close to perfect fit to simulation mean critical gaps across a broad range of conditions. The MCG method also provides an almost perfect fit and has superior computational simplicity and efficiency to the MLE. The SWCG method performs robustly under high flows; however, poorly under low to moderate flows. Further research is recommended using field traffic data, under a variety of minor stream and major stream flow conditions for a variety of minor stream movement types, to compare critical gap estimates using MLE against MCG. Should the MCG method prove as robust as MLE, serious consideration should be given to its adoption to estimate critical gap parameters in guidelines.

A sequential Monte Carlo approach to the sequential design for discriminating between rival continuous data models

Here we present a sequential Monte Carlo approach to Bayesian sequential design for the incorporation of model uncertainty. The methodology is demonstrated through the development and implementation of two model discrimination utilities; mutual information and total separation, but it can also be applied more generally if one has different experimental aims. A sequential Monte Carlo algorithm is run for each rival model (in parallel), and provides a convenient estimate of the marginal likelihood (of each model) given the data, which can be used for model comparison and in the evaluation of utility functions. A major benefit of this approach is that it requires very little problem specific tuning and is also computationally efficient when compared to full Markov chain Monte Carlo approaches. This research is motivated by applications in drug development and chemical engineering.

Indigeneity and the likelihood of imprisonment in Queensland’s adult and children’s courts

Australian research on Indigenous sentencing disparities of the standard of international work is somewhat recent. Contrary to expectations based on international research, Australian studies generally have not found Indigenous offenders to be treated substantively more harshly than non-Indigenous offenders in similar circumstances. However, this research has primarily focused on adult higher courts, with little attention to lower courts and children’s courts. In this article, we examine whether Indigeneity has a direct impact on the judicial decision to incarcerate for three courts (adult higher, adult lower, children’s higher court) in Queensland. We found no significant differences in the likelihood of a sentence of incarceration in the higher courts (adult and children’s). In contrast, in the lower courts, Indigenous defendants were more likely to be imprisoned than non-Indigenous defendants when sentenced under statistically similar circumstances.

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.

A comparison of safety climate and safety outcomes between construction and resource functions in a large case study organisation

The research described in this paper forms part of an in-depth investigation of safety culture in one of Australia’s largest construction companies. The research builds on a previous qualitative study with organisational safety leaders and further investigates how safety culture is perceived and experienced by organisational members, as well as how this relates to their safety behaviour and related outcomes at work. Participants were 2273 employees of the case study organisation, with 689 from the Construction function and 1584 from the Resources function. The results of several analyses revealed some interesting organisational variance on key measures. Specifically, the Construction function scored significantly higher on all key measures: safety climate, safety motivation, safety compliance, and safety participation. The results are discussed in terms of relevance in an applied research context.

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