Jan Pablo Burgard (Trier University), María Dolores Esteban (University Miguel Hernández of Elche), Domingo Morales (University Miguel Hernández of Elche) and Agustín Pérez (University Miguel Hernández of Elche).
Abstract. The Fay–Herriot model is an area-level linear mixed model that is widely used for estimating the domain means of a given target variable. Under this model, the dependent variable is a direct estimator calculated by using the survey data and the auxiliary variables are true domain means obtained from external data sources. Administrative registers do not always give good auxiliary variables so that statisticians sometimes take them from alternative surveys and therefore they are measured with error. We introduce a variant of the Fay–Herriot model that takes into account the measurement error of the auxiliary variables and give two fitting algorithms that calculate maximum and residual maximum likelihood estimates of the model parameters. Based on the new model, empirical best predictors of domain means are introduced and an approximation of its mean squared error is derived. We finally give an application to estimate poverty proportions in the Spanish Living Condition Survey, with auxiliary information from the Spanish Labour Force Survey.
Keywords. Fay–Herriot model; Small area estimation; Measurement error; Monte Carlo simulation; Poverty proportion
Juan Aparicio (University Miguel Hernández of Elche), José Manuel Cordero (University of Extremadura) and Lidia Ortiz (University Miguel Hernández of Elche).
Abstract. Many studies devoted to efficiency performance evaluation in the education sector are based on measures of central tendency at school level as, for example, the average values of students belonging to the same school. Although this is a common and accepted way of summarizing data from the original observations (students), it is not less true that this approach neglects the existing dispersion of data, which may become a serious problem if variability across schools is high. Additionally, imprecision may arise when experts on each evaluated subject select the battery of questions, with different levels of difficulty, which will be the base for the final questionnaires completed by students. This paper uses data from US students and schools participating in PISA (Programme for International Student Assessment) 2015 to illustrate that schools’ efficiency measures based on aggregate data and imprecision may reflect an inaccurate picture of their performance if they are compared to measures estimated accounting for broader information provided by all students of the same school. In order to operationalize our approach, we resort to Fuzzy Data Envelopment Analysis. This methodology allows us to deal with the notion of fuzziness in some variables such as the socio-economic status of students or test scores. Our results indicate that the estimated measures of performance obtained with the fuzzy DEA approach are highly correlated with those calculated with traditional DEA models. However, we find some relevant divergences in the identification of efficient units when we account for data dispersion and vagueness.
Keywords. Efficiency; Data envelopment analysis; Fuzzy data; Education
José M. Ramos (University Miguel Hernández of Elche), M. Asunción Martínez-Mayoral (University Miguel Hernández of Elche), Francisco Sánchez-Ferrer (University Miguel Hernández of Elche) , Javier Morales (University Miguel Hernández of Elche), Tomás Sempere (University Miguel Hernández of Elche), Isabel Belinchón (University Miguel Hernández of Elche) and Antonio F. Company (University Miguel Hernández of Elche).
Abstract. La prueba evaluación clínica objetiva y estructurada (ECOE) es un método de evaluación de la competencia clínica con evidencia de validez, objetividad y confiabilidad. En este estudio nos propusimos analizar la prueba ECOE de los estudiantes de sexto del grado de medicina. Material y métodos: Estudio transversal de la prueba ECOE realizada en la Facultad de Medicina de la Universidad Miguel Hernández de Elche en junio de 2016. En la prueba participaron 116 alumnos. Había 7 (35%) estaciones de paciente estandarizado, 5 (25%) estaciones de informe, 4 (20%) estaciones de maniquí/procedimiento y 4 (20%) estaciones de tipo examen oral estructurado. La mediana de la puntuación de los alumnos fue de 7,14 (recorrido intercuartílico: 6,90-7,43). La mediana de la puntuación de los alumnos del primer día por la ma˜nana fue de 7,10, del primer día por tarde fue superior (7,14) y la del segundo día por la mañana también lo fue (7,24; p = 0,1). La estación con menor puntuación fue la de informe (6,41) y la estación con mayor puntuación fue la de maniquí/procedimiento (7,88) (p < 0,001). Dentro de las estaciones de paciente estandarizado (mediana = 7,12), los resultados de los alumnos fueron mejores en las que el paciente era un facultativo en formación (7,52).
Keywords. Evaluación clínica objetiva y estructurada; Grado en medicina; Competencias
Juan Aparicio (University Miguel Hernández of Elche), José Manuel Cordero (University of Extremadura) and Carlos Díaz-Caro (University of Extremadura).
Abstract. The paper presents an innovative empirical application to assess the efficiency of regional tax offices in Spain. The existing evidence about the performance of those administrative units is still limited; thus, our aim is to contribute to extend this line of research by incorporating three relevant issues into our empirical analysis. First, we consider the number of complaints against tax authority decisions as a quality measure of tax management. Since the evaluated units should aim to minimize the number of complaints, this variable represents an undesirable output; thus, we define a model that is adaptable to the special features of this unconventional output. Second, our empirical analysis covers the period 2005–2014; thus, we can analyze the productivity change across this 10-year period including different phases of the economic cycle. Finally, seeking robustness, we use enhanced versions of the Malmquist–Luenberger productivity index and the Luenberger productivity indicator that allow us to overcome some of the drawbacks suffered by the original approach. The results obtained with both indices are very similar and indicate that during the evaluated period tax offices suffered a slight worsening in terms of productivity, especially during the years previous to the economic crisis (2005–2008). This regression was mainly due to the technical regression experienced by the majority of units during those years.
Keywords. Efficiency; Tax offices; Public management; Productivity change; Administrative services; Operations research
Elisabeth Gutierrez (University Miguel Hernández of Elche), Natividad Llorca (Miguel Hernández University of Elche), Manuel Mosquera (University of Vigo) and Joaquín Sánchez-Soriano (Miguel Hernández University of Elche).
Abstract. In this paper we consider a two-echelon supply chain with one supplier that controls a limited resource and a finite set of manufacturers who need to purchase this resource. We analyze the effect of the limited resource on the horizontal cooperation of manufacturers. To this end, we use cooperative game theory and the existence of stable distributions of the total profit among the manufacturers as a measure of the possibilities of cooperation. The game theoretical model that describes the horizontal cooperation involves externalities, which arise because of the possible scarcity of the limited resource and the possible coalition structures that can be formed. Furthermore, manufacturers do not know how the supplier will allocate the limited resource, therefore, how much of this resource they will obtain is uncertain for all concerned. Nevertheless, when the limited resource is not scarce for the grand coalition, the existence of stable distributions of the total profit is guaranteed and consequently the collaboration among the manufacturers is profitable for them all. In the event that the limited resource is insufficient for the grand coalition, we introduce a new cooperative game that assesses the expectations of each coalition of manufacturers regarding the amount of the limited resource they can obtain. We analyze two extreme expectations: the optimistic and the pessimistic. In the optimistic case, we cannot reach a conclusion regarding the full cooperation of the manufacturers. In the pessimistic case, with one reasonable assumption, the existence of stable distributions of the total profit is guaranteed and as a result the collaboration among manufacturers is a win–win deal.
Keywords. Linear production processes; Limited resource; Horizontal cooperation; Externalities
Marilène Cherkesly (Université du Québec à Montréal), Mercedes Landete (Miguel Hernández University of Elche) and Gilbert Laporte (HEC Montréal).
Abstract. This paper introduces two classes of location problems with interconnected facilities. These problems dif- fer from classical location problems in the sense that the facilities to be located must be interconnected, i.e. located within a prescribed distance of a central office or of each other. Such problems arise, for example, in contexts where forest fire-fighters must be able to reach each other by short-range radios, or when locating interconnected sensors. Median and covering problems are modeled through several formulations. A metaheuristic consisting of a hybrid construction phase followed by an iterative search process developed for the median and covering problems. Extensive tests are performed in order to assess the performance of the proposed methodology.
Keywords. Facility location; Interconnectivity; Median problem; Covering; Metaheuristic