An Analysis of Applicability using Quality Metrics for Ontologies on Ontology Design Patterns

Ontology design patterns (ODPs) provide best-practice solutions for common or recurring ontology design problems. This work focuses on content ODPs, which form small ontologies themselves and thus can be subject to ontology quality metrics in general. We investigate the use of such metrics for content ODP evaluation in terms of metrics applicability and validity. The quality metrics used for this investigation are taken from existing work in the area of ontology quality evaluation. We discuss the general applicability to content ODP of each metric considering its definition, ODP characteristics, and the defined goals of ODPs. The research process presented in this paper has two phases. In the first phase, we conducted a literature research in the area of metrics for assessing ontology quality. The second phase consisted of a two-step evaluation of the ontology metrics identified in the literature analysis. During the first step, we investigated whether the metrics are appropriate to differentiate between content ODPs of different quality. Metrics that proved to be applicable were calculated for a random set of 14 content ODPs. In the second step, a controlled experiment, the quality indicated by the metric value was contrasted with the perception of ontology engineers; that is, do ‘measured quality’ and ‘perceived quality’ match?. Copyright © 2015 John Wiley & Sons, Ltd.     

Influence of perceptual metrics on customer profitability: The mediating effect of behavioural metrics

Accountability of marketing actions is a topic of ongoing interest. In accordance with the growing importance of the subject, a multitude of customer metrics has been developed intended to measure and value marketing investments and link their returns to financial results and performance. Managers widely acknowledge the need for quantitative measures of marketing performance but now face the challenge of deciding which metrics to measure and how to interpret them. One of the main difficulties lies in the interdependencies of metrics. Those interdependencies may lead to serious misinterpretation and have been widely neglected in the existing literature. Therefore, this study empirically tests if the influence of customer perceptual metrics (for example, customer satisfaction) on customer profitability persists when customer behavioural metrics are considered. We use data from a large European financial service provider. Our findings support the relevance of mediating effects of customer behavioural metrics (for example, cross-selling ratio) on the relationship between customer perceptual metrics and customer profitability. The article contributes significantly to the body of knowledge about interdependencies between different customer metric combinations by considering direct and indirect links, testing for mediator effects, and evaluating their impact on customer profitability.     

An inductive reasoning approach for building system safety risk models of aviation accidents

An inductive reasoning approach is employed to develop a prototype hybrid decision support tool whose main objective is to build probabilistic causal models representing the safety risk involved in aviation accidents. In this context, 15 aircraft accidents representative of five major accident types are selected to build an initial seed for the case‐base of the prototype tool. Consequently, within each individual accident model, main clusters of causal factors are identified for inclusion in the initial seed, thereby improving, both quantitatively and qualitatively, the case‐base of the prototype tool. A new methodology developed specifically for indexing aviation accidents into databases is used for indexing the initial seed into the case‐base of the tool. The resulting product is a highly customized conversational decision support tool that provides solution possibilities in the form of probabilistic causal models of accident scenarios retrieved and ranked according to their similarity to the current accident that the intended user investigates.     

An analytical approach for systematic risk sensitivity of structured finance products

The global financial crisis has shown that many financial institutions dealing with credit derivatives were exposed to severe unexpected losses. This indicates that systematic influences are decisively underestimated particularly with regard to structured products like securitized tranches of collateralized debt obligations. Our analytical study addresses these systematic effects: We provide a simple model which allows a closed-form comparison of both bonds and tranches with respect to their systematic risk. We demonstrate that the exposure to systematic risk of tranches may be many times higher than the exposure of bonds, even if both products share the same rating grade, e.g., an ‘AAA’ rating, measured by either default probability or expected loss. Particularly in economic downturns, default rates of tranches may be multiples of those of bonds. Our results help understand high default rates of tranches during the financial crisis and show that classical ratings are insufficient metrics for measuring risks of structured products.     

Validation of default probability models: A stress testing approach

This study aims to evaluate the techniques used for the validation of default probability (DP) models. By generating simulated stress data, we build ideal conditions to assess the adequacy of the metrics in different stress scenarios. In addition, we empirically analyze the evaluation metrics using the information on 30,686 delisted US public companies as a proxy of default. Using simulated data, we find that entropy based metrics such as measure M are more sensitive to changes in the characteristics of distributions of credit scores. The empirical sub-samples stress test data show that AUROC is the metric most sensitive to changes in market conditions, being followed by measure M. Our results can help risk managers to make rapid decisions regarding the validation of risk models in different scenarios.     

Assessing the information content of short-selling metrics using daily disclosures

As a consequence of the 2008 financial crisis, the Australian regulator mandated daily reporting and disclosure of both short flow and short interest at an individual stock level. This provides a unique opportunity to study the nature and source of information embedded in each metric. Our empirical findings are consistent with short sellers being heterogeneous with respect to their information. Short flow is strongly related to recent returns and buy-order imbalance, and both anticipates and reacts to price-relevant announcements. In contrast, short interest is related to the mispricing of firm fundamentals. The distinct differences in the nature of information embedded in the two metrics provide an economic rationale for both the unique ability of each metric to predict returns and the future horizons over which the information is relevant.     

Forecasting foreign exchange volatility: Why is implied volatility biased and inefficient? And does it matter?

Research has consistently found that implied volatility is a conditionally biased predictor of realized volatility across asset markets. This paper evaluates explanations for this bias in the market for options on foreign exchange futures. Several recently proposed solutions – including a model of priced volatility risk – fail to explain a significant portion of the conditional bias found in implied volatility. Further, while implied volatility fails to subsume econometric forecasts in encompassing regressions, these forecasts do not significantly improve delta-hedging performance. Thus this paper argues that statistical metrics are inappropriate measures of the information content of implied volatility. Implied volatility appears much more useful when measured by a more relevant, economic metric.     

Assessing Systemic Importance With a Fuzzy Logic Inference System

Three metrics are designed to assess Colombian financial institutions' size, connectedness and non-substitutability as the main drivers of systemic importance: (i) centrality as net borrower in the money market network; (ii) centrality as payments originator in the large-value payment system network; and (iii) asset value of core financial services. An aggregated systemic importance index is calculated based on expert knowledge by using a fuzzy logic inference system. We use principal component analysis to calculate a benchmark index for comparison purposes. Overall similarities between both indexes put forward that expert knowledge aggregation is consistent with that based on a purely quantitative standard approach. Specific non-negligible differences concur with the nonlinear features of an approach whose intention is to replicate human reasoning. Both indexes are complementary and provide a comprehensive relative assessment of each financial institution's systemic importance in the Colombian case, in which the choice of metrics pursues the macroprudential perspective of financial stability. Copyright © 2015 John Wiley & Sons, Ltd.     

Risk models-at-risk

The experience from the global financial crisis has raised serious concerns about the accuracy of standard risk measures as tools for the quantification of extreme downward risks. A key reason for this is that risk measures are subject to a model risk due, e.g. to specification and estimation uncertainty. While regulators have proposed that financial institutions assess the model risk, there is no accepted approach for computing such a risk. We propose a remedy for this by a general framework for the computation of risk measures robust to model risk by empirically adjusting the imperfect risk forecasts by outcomes from backtesting frameworks, considering the desirable quality of VaR models such as the frequency, independence and magnitude of violations. We also provide a fair comparison between the main risk models using the same metric that corresponds to model risk required corrections.     

The use of domestic and world market indexes in the estimation of time-varying betas

This paper generates time-varying estimates of Australian industry betas relative to an Australian market index and a world market index using the Kalman filter approach. As a means of comparison, these conditional estimated betas are used to forecast each industry’s return in-sample. The forecast error metrics suggest that the estimates of conditional risk relative to the domestic market index are preferred to estimates generated using the world market index, irrespective of the industry concerned. While not to suggest time-varying betas estimated relative to a domestic index are universally superior, these results suggest that they are preferable in certain circumstances.     

A multivariate Markov chain stock model

ABSTRACT

We propose a dividend stock valuation model where multiple dividend growth series and their dependencies are modelled using a multivariate Markov chain. Our model advances existing Markov chain stock models. First, we determine assumptions that guarantee the finiteness of the price and risk as well as the fulfilment of transversality conditions. Then, we compute the first- and second-order price-dividend ratios by solving corresponding linear systems of equations and show that a different price-dividend ratio is attached to each combination of states of the dividend growth process of each stock. Subsequently, we provide a formula for the computation of the variances and covariances between stocks in a portfolio. Finally, we apply the theoretical model to the dividend series of three US stocks and perform comparisons with existing models. The results could also be applied for actuarial purposes as a general stochastic investment model and for calculating the initial endowment to fund a portfolio of dependent perpetuities.     

Australian retail fund performance persistence

The present study extends the Australian fund performance persistence literature through the use of five performance metrics: raw returns, the Sharpe ratio, the single‐factor model and two multifactor models, the Carhart (1997) model and the Gruber (1996) model, in analysis of Australian retail fund performance over the period 1991–2000. Analysis suggests that performance persistence is sensitive to fund objective and appears to be driven by inadequate adjustment for risk.     

Combining LCA and RA for the integrated risk management of emerging technologies

Emerging risks of innovative technologies, like for instance nanotechnology, require proactive assessments in order to guarantee that their future materials and products will not result in adverse effects on health, safety and the environment. The combination of Life Cycle Assessment (LCA) and Risk Assessment (RA) offers a systematic approach to identify and assess potential impacts. LCA is a well-known analytical tool, standardised in ISO 14040-14044, to assess the environmental impact of the entire life-cycle of a product or service. Its strengths are the systematic approach to analyse all life-cycle stages of complex systems. Integrated risk management can benefit in various ways from LCA. Firstly, LCA offers a new dimension to the safety paradigm, exploring the principles and synergies between LCA and RA. Secondly, LCA offers a systematic approach to analyse the risks of innovative technologies along their entire life-cycle (from design, building, maintenance, operation to decommissioning). Thirdly, LCA offers an analytical tool to quantify the environmental impact of emerging technologies. In combination with RA, LCA can provide scientifically sound information for the early assessment of potential impacts on health, safety and the environment.     

A new method for ranking academic journals in accounting and finance

Given the many and varied uses to which journal rankings are put. interest in ranking journal ‘quality’ is likely to persist. Unfortunately, existing methods of constructing such rankings all have inherent limitations. This paper proposes a new (complementary) approach, based on submissions to RAE 2001. which is not restricted to a pre-defined journal set and, importantly, is based on quality choice decisions driven by economic incentives. For three metrics, submissions to RAE 2001 are compared with the available set of publications to provide evidence on the perception of journal quality, a fourth metric is based on the overall RAE grades, and an overall ranking is produced.     

A COMPARISON OF INTERVENTION AND RESIDUAL ANALYSIS

By comparing intervention and residual analysis abnormal return metrics, this study illustrates the impact that cross-sectional return dependencies can have on empirical tests of the semi-strong form of the efficient market hypothesis. The source of the dependencies encountered in this study appears to be the result of nine value altering information releases (e.g., events) that occurred in a seven-month period in 1982. For one sample of bank equity returns, the abnormal return metrics obtained with residual analysis are generally smaller than those obtained with intervention analysis. In addition, the intervention analysis results suggest that two of the nine events led to significant shifts in the banks' systematic risk. These findings suggest that tests of the semi-strong form of the efficient market hypothesis conducted with a less-than randomly constructed sample need to examine the restrictions that accompany the specification of an expected return metric.     

Linear beta pricing with inefficient benchmarks in a given factor structure*

ABSTRACT

We show the equivalence between the zero-beta version of a multi-factor arbitrage pricing model and a linear pricing model utilizing undiversified inefficient benchmarks in a given factor structure. The resulting linear model is a two-beta model, with one beta related to the inefficient benchmark and another adjusting for its inefficiency. This linear model shows that there are only two distinctive and computable sources of risk, affecting security expected returns, despite the existence of several risk factors. In a short empirical example we demonstrate that the model can be employed to provide guidance and allow researchers to test for the validity of their selection of the underlying risk factors driving variations in security returns.     

Comprehensive scenario analysis for mitigation of risks of the maritime traffic in the Strait of Istanbul

In this paper, the results of a scenario analysis are presented using the models developed by the authors in their prior work. Therein an aggregate risk-simulation model of the maritime traffic in the Strait of Istanbul was developed giving consideration to traffic rules, vessel profiles, pilotage services, meteorological, geographical conditions, and vessel scheduling. A risk assessment was carried out by incorporating a probabilistic accident risk model into the simulation model to establish a baseline level of risk. Herein, 16 scenarios are described as modifications of the baseline scenario for the purpose of studying maritime risk mitigation in this geographic context. We have evaluated the impact of several factors such as vessel arrival rates, vessel pursuit distances, number of pilots, local traffic density, and vessel scheduling practices such as the single-lane traffic regime start time on safety risks. We also present a discussion on the impact of each factor on vessel passages and waiting times at both entrances of the Strait. We conclude with risk mitigation recommendations that reduce both risk and waiting times, and thus can be considered ‘win-win’ from both an operational and risk reduction perspective.     

基于主成份分析的上市公司治理水平体系构建

全球金融危机的爆发与蔓延突显出公司治理对风险防范的重要性,政府监管层、上市公司以及投资者自身都产生了对公司治理进行评价的客观要求。本文将公司治理体系分为股权结构、董事会治理、经理层治理、信息披露及透明度、伦理维度五个层面,运用主成份分析方法来寻求上述五个层面各代理变量的线性组合,构建了上市公司治理水平体系。     

Societal risks as seen by Chinese students living in Macao

The present study reports on mean risk magnitude judgements expressed by Chinese students living in Macao on 87 hazardous activities, substances and technologies. These judgements were compared with findings on African, American and European samples. Despite high similarity in mean results, standard deviations, and linear correlation with the other countries, Macao appears to be the country in which the level of risk perception was clearly the highest, and this seems largely due to five items connected with violence and crime. These results are explained by the exceptionally high level of crime in Macao and its crude display by the local media.