Shortfall Risk Models When Information on Loss Function Is Incomplete

Utility-based shortfall risk measures effectively captures a decision maker's risk attitude on tail losses. In this paper, we consider a situation where the decision maker's risk attitude toward tail losses is ambiguous and introduce a robust version of shortfall risk, which mitigates the risk arising from such ambiguity. Specifically, we use some available partial information or subjective judgement to construct a set of plausible utility-based shortfall risk measures and define a so-called preference robust shortfall risk as through the worst risk that can be measured in this (ambiguity) set. We then apply the robust shortfall risk paradigm to optimal decision-making problems and demonstrate how the latter can be reformulated as tractable convex programs when the underlying exogenous uncertainty is discretely distributed.

Distributionally Robust Mean-Variance Portfolio Selection with Wasserstein Distances

We revisit Markowitz’s mean-variance portfolio selection model by considering a distributionally robust version, in which the region of distributional uncertainty is around the empirical measure and the discrepancy between probability measures is dictated by the Wasserstein distance. We reduce this problem into an empirical variance minimization problem with an additional regularization term. Moreover, we extend the recently developed inference methodology to our setting in order to select the size of the distributional uncertainty as well as the associated robust target return rate in a data-driven way. Finally, we report extensive back-testing results on S&P 500 that compare the performance of our model with those of several well-known models including the Fama–French and Black–Litterman models. This paper was accepted by David Simchi-Levi, finance.

Self-regulated learning, academic achievement and socioeconomic context at the end of primary school

The increase of inequalities and the learning crisis due to COVID-19 pandemic has forced to review the role of education in the attainment of skills to learn throughout life. The purpose of this study is to investigate the incidence of the academic achievement on selfregulation strategies (forethought, inhibition and volitional inhibition), considering the socioeconomical context at the end of elementary school. The SRL strategies are assessed, from the perspective of students and teachers, triangulating measurement in different tasks. 67 students in their last year of primary education participated. The SRL measures were compared using robust tests considering high and low academic achievement and low and medium socioeconomic context (robust version of Welch’s test for two groups, Yuen’s test, and two-way ANOVA based on trimmed means and Winsorized variances). The academic achievement affects and significantly predicts the forethought strategy. In the low socioeconomical context, the students with a high academic achievement maximize their SRL. The modulating role of the school experience in self-regulation is discussed.

Human-like Computer Vision

Statistical machine learning is widely used in image classification and typically 1) requires many images to achieve high accuracy and 2) does not provide support for reasoning below the level of classification. By contrast this paper describes an approach called machine learning approach called Logical Vision (LV) which uses a) background knowledge such as light reflection that can itself be learned and used for resolving visual ambiguities, which cannot be easily modeled using statistical approaches, b) a wider class of background models representing classical 2D shapes such as circles and ellipses, c) primitive-level statistical estimators to handle noise in real images, Our results indicate that in real images the new noise-robust version of LV using a single example (ie one-shot LV) converges to an accuracy at least comparable to thirty-shot statistical machine learner on the prediction of hidden light sources.

A Robust Version of the Empirical Likelihood Estimator

In this paper, we introduce a robust version of the empirical likelihood estimator for semiparametric moment condition models. This estimator is obtained by minimizing the modified Kullback–Leibler divergence, in its dual form, using truncated orthogonality functions. We prove the robustness and the consistency of the new estimator. The performance of the robust empirical likelihood estimator is illustrated through examples based on Monte Carlo simulations.

Testing for slope heterogeneity in Stata

In this article, we introduce a new community-contributed command, xthst, to test for slope heterogeneity in panels with many observations over cross-sectional units and time periods. The command implements such a test, the delta test (Pesaran and Yamagata, 2008, Journal of Econometrics 142: 50–93). Under its null, slope coefficients are homogeneous across cross-sectional units. Under the alternative, slope coefficients are heterogeneous in the cross-sectional dimension. xthst also includes two extensions. The first is a heteroskedasticity- and autocorrelation-consistent robust test along the lines of Blomquist and Westerlund (2013, Economics Letters 121: 374–378). The second extension is a cross-sectional-dependence robust version. We discuss all tests and present examples using an economic growth model. A Monte Carlo simulation shows that the size and the power behave as expected.

Fallibilism and Consequence

Alex Worsnip argues in favor of what he describes as a particularly robust version of fallibilism: subjects can sometimes know things that are, for them, possibly false (in the epistemic sense of ‘possible’). My aim in this paper is to show that Worsnip’s argument is inconclusive for a surprising reason: the existence of possibly false knowledge turns on how we ought to model entailment or consequence relations among sentences in natural language. Since it is an open question how we ought to think about consequence in natural language, it is an open question whether there is possibly false knowledge. I close with some reflections on the relation between possibly false knowledge and fallibilism. I argue that there is no straightforward way to use linguistic data about natural language epistemic modals to either verify or refute the fallibilist thesis.

Orthonormal Canonical Correlation Analysis

Complex managerial problems are usually described by datasets with multiple variables, and in lack of a theoretical model, the data structures can be found by special multivariate statistical techniques. For two datasets, the canonical correlation analysis and its robust version are known as good working research tools. This paper presents their further development via the orthonormal approximation of data matrices which corresponds to using singular value decomposition in the canonical correlations. The features of the new method are described and applications considered. This type of multivariate analysis is useful for solving various practical problems of applied statistics requiring operating with two data sets, and can be helpful in managerial estimations and decision making.

Foundations of relativism by J. Margolis in the polemic of R. Rorty and H. Putnam

The polemic about the realism of H. Putnam and R. Rorty is a remarkable event of the 20th century for a number of reasons. Forming within the analytical philosophy, and using the most relevant concepts and ideas of this direction as arguments, this polemic for almost three decades of its existence balanced on the border with relativism, the least popular and admited direction of philosophy of the 20th century. Putnam's arguments against metaphysical realism reject any "point of view of God", entail "internalism", accept the concept of incommensurability of conceptual schemes and the relativization the reality described by the epistemic agent to his experience. Rorty's arguments reject not only relativism, but also realism, but his concepts of ethnocentrism and solidarity also take the view that the standards of truth correlate with the conceptual schemes, are "sociologized" and meet the interests of the majority. J. Margolis find in this polemic not only a retreat into relativism, but also recognized its pragmatistic potential, which gave him the opportunity to defend relativism, proposing its reliable (robust) version and building a neo-pragmatist philosophy on the development of the arguments of both sides.

Productivity in the Hotel Industry: An Order-α Malmquist Productivity Indicator

In the literature, it is highlighted that the deterministic nature of the data envelopment analysis–based productivity measures makes them sensitive to sample characteristics. However, the majority of the related empirical studies ignore the potential bias in their data envelopment analysis–based productivity estimations. This article illustrates how the order-α quantile-type estimators can be applied to construct a robust version of the Malmquist productivity indices. Using the order-α estimators, we construct a Malmquist productivity index alongside with two well-known decompositions. The proposed productivity indicator is less sensitive to potential outliers and extreme values. Then, as an illustrative example, we apply the quantile-type productivity index on a sample of 270 hotels operating in the Balearic Islands over the period 2004-2013. The productivity levels alongside with their components are analyzed during the global financial crisis period.