On the time-consistent stochastic dominance risk averse measure for tactical supply chain planning under uncertainty (2018). Computers and Operations Research, 100, 270–286.

Laureano F. Escudero (Rey Juan Carlos University), Juan Francisco Monge (University Miguel Hernández of Elche) and Dolores Romero Morales (Copenhagen Business School).

Abstract. In this work a modeling framework and a solution approach have been presented for a multi-period stochastic mixed 0–1 problem arising in tactical supply chain planning (TSCP). A multistage scenario tree based scheme is used to represent the parameters’ uncertainty and develop the related Deterministic Equivalent Model. A cost risk reduction is performed by using a new time-consistent risk averse measure. Given the dimensions of this problem in real-life applications, a decomposition approach is proposed. It is based on stochastic dynamic programming (SDP). The computational experience is twofold, a compar- ison is performed between the plain use of a current state-of-the-art mixed integer optimization solver and the proposed SDP decomposition approach considering the risk neutral version of the model as the subject for the benchmarking. The add-value of the new risk averse strategy is confirmed by the compu- tational results that are obtained using SDP for both versions of the TSCP model, namely, risk neutral and risk averse.

Keywords. Tactical supply chain planning; Nonlinear separable objective function; Multistage stochastic integer optimization; Risk management; Time-consistency; Stochastic nested decomposition

Indexation Strategies and Calmness Constants for Uncertain Linear Inequality Systems (2018). Springer International Publishing AG 2018, 142, 831-843.

María Josefa Cánovas (University Miguel Hernandez of Elche), René Henrion (University Humboldt of Berlin), Marco Antonio López (University of Alicante) and Juan Parra (University Miguel Hernández of Elche).

Abstract. The present paper deals with uncertain linear inequality systems viewed as nonempty closed coefficient sets in the (n + 1)-dimensional Euclidean space. The perturbation size of these uncertainty sets is measured by the (extended) Hausdorff distance.We focus on calmness constants —and their associated neighborhoods— for the feasible setmapping at a given point of its graph. To this aim, the paper introduces an appropriate indexation function which allows us to provide our aimed calmness constants through their counterparts in the setting of linear inequality systems with a fixed index set, where a wide background exists in the literature.

Weak compactness and metrizability of Mackey*-bounded sets in Fréchet spaces (2018). Akadémiai Kiadó, 1-15.

Juan Carlos Ferrando (University Miguel Hernandez of Elche) and Jerzy Kąkol (University Adam Mickiewicz of Poznań).

Abstract. Motivated by the density condition in the sense of Heinrich for Fréchet spaces and by some results of Schlüchtermann and Wheeler for Banach spaces, we characterize in terms of certain weakly compact resolutions those Fréchet spaces enjoying the property that each bounded subset of its Mackey* dual is metrizable. We also characterize those Köthe echelon Fréchet spaces λp(A) as well as those Fréchet spaces Ck (X) of real-valued continuous functions equipped with the compact-open topology that enjoy this property.

Keywords. Bounded resolution; weakly compact resolution; G-base of neighborhoods; K-analytic space; SWKA space; SWCG space

Domain Mean Estimators Assisted by Nested Error Regression Models (2018). Springer International Publishing AG 2018, 142, 147-154.

María Dolores Esteban (University Miguel Hernandez of Elche), Domingo Morales (University Miguel Hernandez of Elche) and María del Mar Rueda (University of Granada).

Abstract. This paper introduces estimators of domain means assisted by nested error regression models. The new estimators are modifications of empirical best linear unbiased predictors that takes into account the sampling weights. They are obtained by summing up the model-based predicted values adjusted by a weighted sum residuals. The paper studies the sampling-design properties of the introduced estimators by means of simulation experiments. The simulation results show that the new estimators present a good balance between sampling bias and mean squared error.

Microeconomic education, strategic incentives, and gender: An oligopoly classroom experiment with social interaction (2018). International Review of Economics Education, 1-11.

José Antonio García Martínez (University Miguel Hernandez of Elche), Carlos Gutiérrez Hita (University Miguel Hernandez of Elche) and Joaquín Sánchez Soriano (University Miguel Hernández of Elche).

Abstract. In an oligopoly classroom experiment we study the extent to which microeconomic education, strategic incentives, and gender affect students’ profits. In our setting, students may interact in the classroom (indeed, everywhere) prior to submitting quantity bids to a virtual market. As students could submit a quantity bid over a week-long period, information exchange among students was expected to take place (as it did). This makes this experiment very useful as a pedagogical tool. Students were divided into markets. We first apply a treatment in which students’ incentives only depend on their own market performance. In the second treatment students’ incentives not only depend on their own market performance but also on performance in other markets. First, it is observed that gender does not affect the results. Second, significant education effects are found. Indeed, students’ profits differ as students reach a higher level of microeconomics education. Finally, cumulative profits depend on the treatment applied: under the first treatment students are more competitive, whereas under the second treatment students partially cooperate. Moreover, this result is related to the level of education in microeconomics.

Keywords. Classroom experiments; Microeconomic education; Gender; Strategic incentives; Quantity-setting oligopoly.

Formal descriptive study for the extraction and comparison of tourist spending patterns (2018). International Journal of Design & Nature and Ecodynamics, 13 (3), 272-280.

Alejandro Rabasa (University Miguel Hernandez of Elche), Nuria Mollá Campello (University Miguel Hernandez of Elche) and Agustín Pérez Torregrosa (University Miguel Hernández of Elche).

Abstract. This paper presents the design of an in-depth descriptive analysis of data collected from public surveys at tourist information points. It uses a dataset that compiles different information related to trips to the Valencian Community (Spain). The aim of this study is to describe the patterns (association rules) that a certain type of expense has, and how this could be used to improve the services offered to tourists. There are different kinds of expenses to analyze: transport, accommodation, leisure as well as total daily expenses and total daily expenses per person. Those cases where expenses are especially high or low are considered as particularly important because of their strategic interest for the public administration of tourism. The study starts with data preprocessing, followed by pattern extraction for the sub-samples with very high and very low expenses, and in some cases, zero expenses are not considered as outliers but as a particular group of individuals. After this, the study aims to extract the most important attributes (feature selection) to create a classification model and compare its efficiency with the models that compute the complete set of attributes. To conclude, this paper presents the possible future predictive models that could lead to an improvement in planning for public tourist services in the Valencian Community (Spain).

Keywords. Feature Selection; Pattern Discovery; Predictive Tourism Analysis.