Outperformance in exchange-traded fund pricing deviations: Generalized control of data snooping bias

An investigation into exchange-traded fund (ETF) outperforrnance during the period 2008-2012 is undertaken utilizing a data set of 288 U.S. traded securities. ETFs are tested for net asset value (NAV) premium, underlying index and market benchmark outperformance, with Sharpe, Treynor, and Sortino ratios employed as risk-adjusted performance measures. A key contribution is the application of an innovative generalized stepdown procedure in controlling for data snooping bias. We find that a large proportion of optimized replication and debt asset class ETFs display risk-adjusted premiums with energy and precious metals focused funds outperforming the S&P 500 market benchmark. 

Hui and Walter's latent-class model extended to estimate diagnostic test properties from surveillance data: a latent model for latent data

Diagnostic test sensitivity and specificity are probabilistic estimates with far reaching implications for disease control, management and genetic studies. In the absence of 'gold standard' tests, traditional Bayesian latent class models may be used to assess diagnostic test accuracies through the comparison of two or more tests performed on the same groups of individuals. The aim of this study was to extend such models to estimate diagnostic test parameters and true cohort-specific prevalence, using disease surveillance data. The traditional Hui-Walter latent class methodology was extended to allow for features seen in such data, including (i) unrecorded data (i.e. data for a second test available only on a subset of the sampled population) and (ii) cohort-specific sensitivities and specificities. The model was applied with and without the modelling of conditional dependence between tests. The utility of the extended model was demonstrated through application to bovine tuberculosis surveillance data from Northern and the Republic of Ireland. Simulation coupled with re-sampling techniques, demonstrated that the extended model has good predictive power to estimate the diagnostic parameters and true herd-level prevalence from surveillance data. Our methodology can aid in the interpretation of disease surveillance data, and the results can potentially refine disease control strategies.

Modeling energy consumption in error-prone IEEE 802.11-based wireless ad-hoc networks

In the IEEE 802.11 MAC layer protocol, there are different trade-off points between the number of nodes competing for the medium and the network capacity provided to them. There is also a trade-off between the wireless channel condition during the transmission period and the energy consumption of the nodes. Current approaches at modeling energy consumption in 802.11 based networks do not consider the influence of the channel condition on all types of frames (control and data) in the WLAN. Nor do they consider the effect on the different MAC and PHY schemes that can occur in 802.11 networks. In this paper, we investigate energy consumption corresponding to the number of competing nodes in IEEE 802.11's MAC and PHY layers in error-prone wireless channel conditions, and present a new energy consumption model. Analysis of the power consumed by each type of MAC and PHY over different bit error rates shows that the parameters in these layers play a critical role in determining the overall energy consumption of the ad-hoc network. The goal of this research is not only to compare the energy consumption using exact formulae in saturated IEEE 802.11-based DCF networks under varying numbers of competing nodes, but also, as the results show, to demonstrate that channel errors have a significant impact on the energy consumption.

Impact of the number of users on error probabilities in multiuser diversity systems

Multiuser diversity gain has been investigated well in terms of a system capacity formulation in the literature. In practice, however, designs on multiuser systems with nonzero error rates require a relationship between the error rates and the number of users within a cell. Considering a best-user scheduling, where the user with the best channel condition is scheduled to transmit per scheduling interval, our focus is on the uplink. We assume that each user communicates with the base station through a single-input multiple-output channel. We derive a closed-form expression for the average BER, and analyze how the average BER goes to zero asymptotically as the number of users increases for a given SNR. Note that the analysis of average BER even in SI SO multiuser diversity systems has not been done with respect to the number of users for a given SNR. Our analysis can be applied to multiuser diversity systems with any number of antennas.

Reducible Diffusions with Time-Varying Transformations with Application to Short-Term Interest Rates

Reducible diffusions (RDs) are nonlinear transformations of analytically solvable Basic Diffusions (BDs). Hence, by construction RDs are analytically tractable and flexible diffusion processes. Existing literature on RDs has mostly focused on time-homogeneous transformations, which to a significant extent fail to explore the full potential of RDs from both theoretical and practical points of view. In this paper, we propose flexible and economically justifiable time variations to the transformations of RDs. Concentrating on the Constant Elasticity Variance (CEV) RDs, we consider nonlinear dynamics for our time-varying transformations with both deterministic and stochastic designs. Such time variations can greatly enhance the flexibility of RDs while maintaining sufficient tractability of the resulting models. In the meantime, our modeling approach enjoys the benefits of classical inferential techniques such as the Maximum Likelihood (ML). Our application to the UK and the US short-term interest rates suggests that from an empirical point of view time-varying transformations are highly relevant and statistically significant. We expect that the proposed models can describe more truthfully the dynamic time-varying behavior of economic and financial variables and potentially improve out-of-sample forecasts significantly.

ALEA: Fine-Grain Energy Profiling with Basic Block Sampling

Energy efficiency is an essential requirement for all contemporary computing systems. We thus need tools to measure the energy consumption of computing systems and to understand how workloads affect it. Significant recent research effort has targeted direct power measurements on production computing systems using on-board sensors or external instruments. These direct methods have in turn guided studies of software techniques to reduce energy consumption via workload allocation and scaling. Unfortunately, direct energy measurements are hampered by the low power sampling frequency of power sensors. The coarse granularity of power sensing limits our understanding of how power is allocated in systems and our ability to optimize energy efficiency via workload allocation.
We present ALEA, a tool to measure power and energy consumption at the granularity of basic blocks, using a probabilistic approach. ALEA provides fine-grained energy profiling via sta- tistical sampling, which overcomes the limitations of power sens- ing instruments. Compared to state-of-the-art energy measurement tools, ALEA provides finer granularity without sacrificing accuracy. ALEA achieves low overhead energy measurements with mean error rates between 1.4% and 3.5% in 14 sequential and paral- lel benchmarks tested on both Intel and ARM platforms. The sampling method caps execution time overhead at approximately 1%. ALEA is thus suitable for online energy monitoring and optimization. Finally, ALEA is a user-space tool with a portable, machine-independent sampling method. We demonstrate two use cases of ALEA, where we reduce the energy consumption of a k-means computational kernel by 37% and an ocean modelling code by 33%, compared to high-performance execution baselines, by varying the power optimization strategy between basic blocks.

Effects of amisulpride, risperidone and chlorpromazine on auditory and visual latent inhibition, prepulse inhibition, executive function and eye movements in healthy volunteers.

In view of the evidence that cognitive deficits in schizophrenia are critically important for long-term outcome, it is essential to establish the effects that the various antipsychotic compounds have on cognition, particularly second-generation drugs. This parallel group, placebo-controlled study aimed to compare the effects in healthy volunteers (n = 128) of acute doses of the atypical antipsychotics amisulpride (300 mg) and risperidone (3 mg) to those of chlorpromazine (100 mg) on tests thought relevant to the schizophrenic process: auditory and visual latent inhibition, prepulse inhibition of the acoustic startle response, executive function and eye movements. The drugs tested were not found to affect auditory latent inhibition, prepulse inhibition or executive functioning as measured by the Cambridge Neuropsychological Test Battery and the FAS test of verbal fluency. However, risperidone disrupted and amisulpride showed a trend to disrupt visual latent inhibition. Although amisulpride did not affect eye movements, both risperidone and chlorpromazine decreased peak saccadic velocity and increased antisaccade error rates, which, in the risperidone group, correlated with drug-induced akathisia. It was concluded that single doses of these drugs appear to have little effect on cognition, but may affect eye movement parameters in accordance with the amount of sedation and akathisia they produce. The effect risperidone had on latent inhibition is likely to relate to its serotonergic properties. Furthermore, as the trend for disrupted visual latent inhibition following amisulpride was similar in nature to that which would be expected with amphetamine, it was concluded that its behaviour in this model is consistent with its preferential presynaptic dopamine antagonistic activity in low dose and its efficacy in the negative symptoms of schizophrenia.

E-Commerce Innovations in the Personal Tax System of the United Kingdom

This study finds evidence that attempts to reduce costs and error rates in the Inland Revenue through the use of e-commerce technology are flawed. While it is technically possible to write software that will record tax data, and then transmit it to the Inland Revenue, there is little demand for this service. The key finding is that the tax system is so complex that many people are unable to complete their own tax returns. This complexity cannot be overcome by well-designed software. The recommendation is to encourage the use of agents to assist taxpayers or simplify the tax system. The Inland Revenue is interested in saving administrative costs and errors by encouraging electronic submission of tax returns. To achieve these objectives, given the raw data it would seem clear that the focus should be on facilitating the work of agents.

Robust Speaker Recognition in Noisy Conditions

This paper investigates the problem of speaker identi-fication and verification in noisy conditions, assuming that speechsignals are corrupted by environmental noise, but knowledgeabout the noise characteristics is not available. This research ismotivated in part by the potential application of speaker recog-nition technologies on handheld devices or the Internet. Whilethe technologies promise an additional biometric layer of securityto protect the user, the practical implementation of such systemsfaces many challenges. One of these is environmental noise. Due tothe mobile nature of such systems, the noise sources can be highlytime-varying and potentially unknown. This raises the require-ment for noise robustness in the absence of information about thenoise. This paper describes a method that combines multicondi-tion model training and missing-feature theory to model noisewith unknown temporal-spectral characteristics. Multiconditiontraining is conducted using simulated noisy data with limitednoise variation, providing a “coarse” compensation for the noise,and missing-feature theory is applied to refine the compensationby ignoring noise variation outside the given training conditions,thereby reducing the training and testing mismatch. This paperis focused on several issues relating to the implementation of thenew model for real-world applications. These include the gener-ation of multicondition training data to model noisy speech, thecombination of different training data to optimize the recognitionperformance, and the reduction of the model’s complexity. Thenew algorithm was tested using two databases with simulated andrealistic noisy speech data. The first database is a redevelopmentof the TIMIT database by rerecording the data in the presence ofvarious noise types, used to test the model for speaker identifica-tion with a focus on the varieties of noise. The second database isa handheld-device database collected in realistic noisy conditions,used to further validate the model for real-world speaker verifica-tion. The new model is compared to baseline systems and is foundto achieve lower error rates.

Response variability in Attention Deficit Hyperactivity Disorder: Evidence for neuropsychological heterogeneity

Response time (RT) variability is a common finding in ADHD research. RT variability may reflect frontal cortex function and may be related to deficits in sustained attention. The existence of a sustained attention deficit in ADHD has been debated, largely because of inconsistent evidence of time-on-task effects. A fixed-sequence Sustained Attention to Response Task (SART) was given to 29 control, 39 unimpaired and 24 impaired-ADHD children (impairment defined by the number of commission errors). The response time data were analysed using the Fast Fourier Transform, to define the fast-frequency and slow-frequency contributions to overall response variability. The impaired-ADHD group progressively slowed in RT over the course of the 5.5 min task, as reflected in this group's greater slow-frequency variability. The fast-frequency trial-to-trial variability was also significantly greater, but did not differentially worsen over the course of the task. The higher error rates of the impaired-ADHD group did not become differentially greater over the length of the task. The progressive slowing in mean RT over the course of the task may relate to a deficit in arousal in the impaired-ADHD group. The consistently poor performance in fast-frequency variability and error rates may be due to difficulties in sustained attention that fluctuate on a trial-to-trial basis. (c) 2006 Elsevier Ltd. All rights reserved.

Phonological oddballs in the focus of attention elicit a normal P3b in dyslexic adults

Difficulties in phonological processing have been proposed to be the core symptom of developmental dyslexia. Phoneme awareness tasks have been shown to both index and predict individual reading ability. In a previous experiment, we observed that dyslexic adults fail to display a P3a modulation for phonological deviants within an alliterated word stream when concentrating primarily on a lexical decision task [Fosker and Thierry, 2004, Neurosci. Lett. 357, 171-174]. Here we recorded the P3b oddball response elicited by initial phonemes within streams of alliterated words and pseudo-words when participants focussed directly on detecting the oddball phonemes. Despite significant verbal screening test differences between dyslexic adults and controls, the error rates, reactions times, and main components (P2, N2, P3a, and P3b) were indistinguishable across groups. The only difference between groups was found in the NI range, where dyslexic participants failed to show the modulations induced by phonological pairings (/b/-/p/ versus /r/ /g/) in controls. In light of previous P3a differences, these results suggest an important role for attention allocation in the manifestation of phonological deficits in developmental dyslexia. (c) 2005 Elsevier B.V. All rights reserved.

Regression analysis of spatial data

Many of the most interesting questions ecologists ask lead to analyses of spatial data. Yet, perhaps confused by the large number of statistical models and fitting methods available, many ecologists seem to believe this is best left to specialists. Here, we describe the issues that need consideration when analysing spatial data and illustrate these using simulation studies. Our comparative analysis involves using methods including generalized least squares, spatial filters, wavelet revised models, conditional autoregressive models and generalized additive mixed models to estimate regression coefficients from synthetic but realistic data sets, including some which violate standard regression assumptions. We assess the performance of each method using two measures and using statistical error rates for model selection. Methods that performed well included generalized least squares family of models and a Bayesian implementation of the conditional auto-regressive model. Ordinary least squares also performed adequately in the absence of model selection, but had poorly controlled Type I error rates and so did not show the improvements in performance under model selection when using the above methods. Removing large-scale spatial trends in the response led to poor performance. These are empirical results; hence extrapolation of these findings to other situations should be performed cautiously. Nevertheless, our simulation-based approach provides much stronger evidence for comparative analysis than assessments based on single or small numbers of data sets, and should be considered a necessary foundation for statements of this type in future.

Who makes prescribing decisions in hospital inpatients?:An observational study

Errors involving drug prescriptions are a key target for patient safety initiatives. Recent studies have focused on error rates across different grades of doctors in order to target interventions. However, many prescriptions are not instigated by the doctor who writes them. It is important to clarify how often this occurs in order to interpret these studies and create interventions. This study aimed to provisionally quantify and describe prescriptions where the identity of the decision maker and prescription writer differed.

Prevalence and Causes of Prescribing ErrorsL The PRescribing Outcomes for Trainee Doctors Engaged in Clinical Training (PROTECT) Study

Objectives: Study objectives were to investigate the prevalence and causes of prescribing errors amongst foundation doctors (i.e. junior doctors in their first (F1) or second (F2) year of post-graduate training), describe their knowledge and experience of prescribing errors, and explore their self-efficacy (i.e. confidence) in prescribing.

Method: A three-part mixed-methods design was used, comprising: prospective observational study; semi-structured interviews and cross-sectional survey. All doctors prescribing in eight purposively selected hospitals in Scotland participated. All foundation doctors throughout Scotland participated in the survey. The number of prescribing errors per patient, doctor, ward and hospital, perceived causes of errors and a measure of doctors’ self-efficacy were established.

Results: 4710 patient charts and 44,726 prescribed medicines were reviewed. There were 3364 errors, affecting 1700 (36.1%) charts (overall error rate: 7.5%; F1:7.4%; F2:8.6%; consultants:6.3%). Higher error rates were associated with : teaching hospitals (p,0.001), surgical (p = ,0.001) or mixed wards (0.008) rather thanmedical ward, higher patient turnover wards (p,0.001), a greater number of prescribed medicines (p,0.001) and the months December and June (p,0.001). One hundred errors were discussed in 40 interviews. Error causation was multi-factorial; work environment and team factors were particularly noted. Of 548 completed questionnaires (national response rate of 35.4%), 508 (92.7% of respondents) reported errors, most of which (328 (64.6%) did not reach the patient. Pressure from other staff, workload and interruptions were cited as the main causes of errors. Foundation year 2 doctors reported greater confidence than year 1 doctors in deciding the most appropriate medication regimen.

Conclusions: Prescribing errors are frequent and of complex causation. Foundation doctors made more errors than other doctors, but undertook the majority of prescribing, making them a key target for intervention. Contributing causes included work environment, team, task, individual and patient factors. Further work is needed to develop and assess interventions that address these.