Bad news and Dow Jones make the Spanish stocks go round

This paper is a data-based attempt to analyse what kind of information basically affects close-to-open returns, open-to-close returns, volatility and volume in actively traded individual securities on the Spanish stock market. Specifically, we are interested in detecting how these variables react to specific pieces of news considered as exogenous information. However, as volume itself could be interpreted as a proxy of the information flow, we first apply the linear and nonlinear Granger causality tests from volume to return and to volatility. We do not find evidence supporting this latter hypothesis. Furthermore, we only find significant evidence of linear causality from volume to volatility. The other major finding is that both bad news and the Dow Jones play a significant informational role in explaining price changes and volatility. As a consequence of these findings, we also test the residual role of volume as a proxy for noise/liquidity trading after filtering for news, although we do not find evidence in favour of this argument.     

Portfolio optimization based on downside risk: a mean-semivariance efficient frontier from Dow Jones blue chips

To create efficient funds appealing to a sector of bank clients, the objective of minimizing downside risk is relevant to managers of funds offered by the banks. In this paper, a case focusing on this objective is developed. More precisely, the scope and purpose of the paper is to apply the mean-semivariance efficient frontier model, which is a recent approach to portfolio selection of stocks when the investor is especially interested in the constrained minimization of downside risk measured by the portfolio semivariance. Concerning the opportunity set and observation period, the mean-semivariance efficient frontier model is applied to an actual case of portfolio choice from Dow Jones stocks with daily prices observed over the period 2005–2009. From these daily prices, time series of returns (capital gains weekly computed) are obtained as a piece of basic information. Diversification constraints are established so that each portfolio weight cannot exceed 5 per cent. The results show significant differences between the portfolios obtained by mean-semivariance efficient frontier model and those portfolios of equal expected returns obtained by classical Markowitz mean-variance efficient frontier model. Precise comparisons between them are made, leading to the conclusion that the results are consistent with the objective of reflecting downside risk.     

Predicting DAX trends from Dow Jones data by methods of the mathematical theory of democracy

The mathematical theory of democracy operates on the indices of popularity and universality which are used to find socially optimal representatives and representative bodies. Regarded mathematically, neither the ‘society’, nor its ‘representatives’ are necessarily human, so that some objects can represent the behavior of other objects. This idea is applied to predicting the DAX-trends (German stock index) from the actual Dow-Jones data; the current fluctuations of stock prices in New York are regarded as representative indicators of future stock price fluctuations in Frankfurt. In particular, it is found that American Express anticipates on the average the price ±fluctuations of 2/3 of the DAX stocks. The statistical significance of the null hypothesis that such a bias from the uncertainty 50% can occur by chance is only 3.5%.     

Bandwidth selection for the local polynomial estimator under dependence: A simulation study

Summary  Seven of the most popular methods for bandwidth selection in regression estimation are compared by means of a thorough simulation study, when the local polynomial estimator is used and the observations are dependent. The study is completed with two plug-in bandwidths for the generalized local polynomial estimator proposed by Vilar-Fernandez & Francisco-Fernández (2002).     

On the crossing number of positive knots and braids and braid index criteria of Jones and Morton-Williams-Franks

We give examples of knots with some unusual properties of the crossing number of positive diagrams or strand number of positive braid representations. In particular, we show that positive braid knots may not have positive minimal (strand number) braid representations, giving a counterpart to results of Franks-Williams and Murasugi. Other examples answer questions of Cromwell on homogeneous and (partially) of Adams on almost alternating knots.

We give a counterexample to, and a corrected version of, a theorem of Jones on the Alexander polynomial of 4-braid knots. We also give an example of a knot on which all previously applied braid index criteria fail to estimate sharply (from below) the braid index. A relation between (generalizations of) such examples and a conjecture of Jones that a minimal braid representation has unique writhe is discussed.

Finally, we give a counterexample to Morton's conjecture relating the genus and degree of the skein polynomial.

     

Pairs selection and outranking: An application to the S&P 100 index

Pairs trading is a popular quantitative speculation strategy. This article proposes a general and flexible framework for pairs selection. The method uses multiple return forecasts based on bivariate information sets and multi-criteria decision techniques. Our approach can be seen as a sort of forecast combination but the output of the method is a ranking. It helps to detect potentially under- and overvalued stocks. A first application with S&P 100 index stocks provides promising results in terms of excess return and directional forecasting.     

Value-at-Risk with quantile regression neural network: New evidence from internet finance firms

Traditional risk measurements have proven inadequate in capturing tail risk and nonlinear correlation. This study proposes a novel approach to measure financial risk in the Internet finance industry: a new Value-at-Risk (VaR) measurement based on quantile regression neural network (QRNN). Sparrow Search Algorithm (SSA) is utilized to optimize the QRNN model, which improves the model's performance in predicting internet finance risk. By comparing the TGARCH-VaR and QR-VaR approaches, our study demonstrates the effectiveness of the QRNN-VaR approach and its potential to improve the accuracy of risk prediction in the Internet finance industry. This study further examines and compares the risks between the traditional and internet finance industries. It also considers the unique impact of COVID-19 on industry risk based on statistical testing for differences and machine learning models. Our results indicate that the level of risk in the Internet finance industry is higher than in the traditional finance industry. Moreover, COVID-19 has contributed to increased risk within the Internet finance industry. These findings have significant implications for investors and policymakers seeking to better understand and manage risks within the Internet finance industry, particularly in the ongoing COVID-19 pandemic.     

Modelling dependence structure with Archimedean copulas and applications to the iTraxx CDS index

In this paper we model the dependence structure between credit default swap (CDS) and jump risk using Archimedean copulas. The paper models and estimates the different relationships that can exist in different ranges of behaviour. It studies the bivariate distributions of CDS index spreads and the kurtosis of equity return distribution. To take into account nonlinear relationships and different structures of dependency, we employ three Archimedean copula functions: Gumbel, Clayton, and Frank. We adopt nonparametric estimation of copula parameters and we find an extreme co-movement of CDS and stock market conditions. In addition, tail dependence indicates the extreme co-movements and the potential for a simultaneous large loss in stock markets and a significant default risk. Ignoring the tail dependence would lead to underestimation of the default risk premium.     

Privatization and performance: evidence from telecommunications sector

There is a continuing debate on whether or not ownership changes accompanying privatization of state-owned enterprises (SOEs) lead to performance improvements of such firms. Since profitability measures alone are possibly inappropriate for SOEs, we address this very significant current question using a novel approach. We test the performance of a large sample of telecommunication firms around the world, 4 years before and 4 years after privatization, using two parallel measures namely financial performance measures and production performance measures. Our purpose is to identify if both approaches could corroborate stronger evidence for or against maintained hypothesis of performance improvements after privatization. The overall finding for this industry indicates significant improvements in both financial and production performance after privatization. Further research is warranted to extend this parallel-methods approach to firms in other industries.     

Oscillation theorems for linear Hamiltonian systems with nonlinear dependence on the spectral parameter and the comparative index

We consider linear Hamiltonian differential systems which depend in general nonlinearly on the spectral parameter and with Dirichlet boundary conditions. In our consideration we do not impose any controllability and strict normality assumptions and omit the Legendre condition for the Hamiltonian. We adapt the theory developed by A.A. Abramov for the Hamiltonian spectral problems based on piecewise constant transformations of their conjoined bases using the notion of the comparative index. We introduce the concept of oscillation numbers which generalize the notion of proper focal points and prove the oscillation theorem relating the number of finite eigenvalues in the given interval with the values of the oscillation numbers at the end points of this interval.     

Supplier default dependencies: Empirical evidence from the automotive industry

Common ways to mitigate the detrimental consequences of supplier bankruptcies are to install redundancy and to pursue a multiple-sourcing strategy. This is based on the assumption that the adverse event of one supplier going out of business is largely independent from the default of other suppliers. However, this implicit assumption does not hold in all cases. This study – based on empirical data from automotive suppliers – reveals that default dependencies among suppliers do often exist and can have significant consequences. We use copula functions, a method of representing joint distribution functions with particular marginals, to capture the default dependence between automotive suppliers and to simulate various default dependence scenarios. We also conduct a comparative static analysis illustrating the significant impact of default correlation in a supplier portfolio. Our findings should spur managers to analyze their supplier portfolios with respect to default dependencies, and to take this phenomenon into consideration when making sourcing decisions.     

On a Characterization of the Gamma Distribution: The Independence of the Sample Mean and the Sample Coefficient of Variation

Let n 3 and let X ₁,...,X _n be positive i.i.d. random variables whose common distribution function f has a continuous p.d.f. Using earlier work of the present authors and a method due to Anosov for solving certain integro-functional equations, it is shown that the independence of the sample mean and the sample coefficient of variation is equivalent to that f is a gamma function. While the proof is of methodological interest, this conclusion can also be arrived at without any assumptions by appealing to the Laplace-Stieltjes transform, as in the Concluding Romark (Section 3).     

A natural selection from the core of a TU game: the core-center

We present a new allocation rule for the class of games with a nonempty core: the core-center. This allocation rule selects a centrally located point within the core of any such game. We provide a deep discussion of its main properties.     

Continuous selection from the sets of best and near-best approximation

The paper studies approximation and structural geometric-topological properties of sets in normed and more general (asymmetric) spaces for which there exists a continuous selection for the best and near-best approximation operators. Sufficient conditions on the metric projection of sets which ensure the existence of a continuous selection for this projection are obtained, and the structural properties of such sets are determined. The existence of a continuous selection for the near-best approximation operator on a finite-dimensional space more general than a normed space is investigated. It is shown that the lower semicontinuity of the metric projection is sufficient for the existence of a continuous selection for the near-best approximation operator in the general case.     

Representational disfluency in algebra: evidence from student gestures and speech

In this investigation, we analyzed US middle school students’ (grades 6–8) gestures and speech during interviews to understand students’ reasoning while interpreting quantitative patterns represented by Cartesian graphs. We studied students’ representational fluency, defined as their abilities to work within and translate among representations. While students translated across representations to address task demands, they also translated to a different representation when reaching an impasse, where the initial representation could not be used to answer a task. During these impasse events, which we call representational disfluencies, three categories of behavior were observed. Some students perceived the graph to be bounded by its physical and numerical limits, and these students were categorized as physically grounded. A second, related, disfluency was categorized as spatially grounded. Students who were classified as spatially grounded exhibited a bounded view of the graph that limited their ability to make far predictions until they physically altered the spatial configuration of the graph by rescaling or extending the axes. Finally, students who recovered from one or more of these disfluencies by translating the quantitative information to alternative but equivalent representations (i.e., exhibiting representational fluency), while retaining the connection back to the linear pattern as graphed, were categorized as interpretatively grounded. Understanding the causes and varieties of representational fluency and disfluency contributes directly to our understanding of mathematics knowledge, learning and adaptive forms of reasoning. These findings also provide implications for mathematics instruction and assessment.     

Measuring efficiency and productivity in professional football teams: evidence from the English Premier League

Professional football clubs are unusual businesses, their performance judged on and off the field of play. This study is concerned with measuring the efficiency of clubs in the English Premier League. Information from clubs’ financial statements is used as a measure of corporate performance. To measure changes in efficiency and productivity the Malmquist non-parametric technique has been used. This is derived from the Data Envelopment Analysis (DEA) linear programming approach, with Canonical Correlation Analysis (CCA) being used to ensure the cohesion of the input–output variables. The study concludes that while clubs operate close to efficient levels for the assessed models, there is limited technological advance in their performance in terms of the displacement of the technological frontier. The research was supported by the Investigation Program of the Technical University of Cartagena (Spain) and by the Department of Sports Studies at the University of Stirling (Scotland, UK).     

Beyond the number of classes: separating substantive from non-substantive dependence in latent class analysis

Latent class analysis (LCA) for categorical data is a model-based clustering and classification technique applied in a wide range of fields including the social sciences, machine learning, psychiatry, public health, and epidemiology. Its central assumption is conditional independence of the indicators given the latent class, i.e. “local independence”; violations can appear as model misfit, often leading LCA practitioners to increase the number of classes. However, when not all of the local dependence is of substantive scientific interest this leads to two options, that are both problematic: modeling uninterpretable classes, or retaining a lower number of substantive classes but incurring bias in the final results and classifications of interest due to remaining assumption violations. This paper suggests an alternative procedure, applicable in cases when the number of substantive classes is known in advance, or when substantive interest is otherwise well-defined. I suggest, in such cases, to model substantive local dependencies as additional discrete latent variables, while absorbing nuisance dependencies in additional parameters. An example application to the estimation of misclassification and turnover rates of the decision to vote in elections of 9510 Dutch residents demonstrates the advantages of this procedure relative to increasing the number of classes.