The committee of the Spanish Society of Statistics and Operations Research (SEIO) – BBVA Foundation Awards 2024, meeting online on July 8th, 2024, and ratified by the SEIO Executive Board on July 9th, 2024, has decided to award the following prizes:

Best methodological contribution in Statistics

María Alonso Pena (assistant professor of Statistics and Operations Research at the Santiago de Compostela University), Irène Gijbels (professor of Statistics at the Catholic University of Leuven, Belgium) and Rosa Crujeiras (professor of Statistics and Operations Research at the Santiago de Compostela University), for their paper A general framework for circular local likelihood regression, published in the Journal of the American Statistical Association (JASA).

This paper marks a significant advancement in the field of directional statistics, a specialized area where the data typically reside in complex geometric constructs such as circles or hyperspheres, presenting unique challenges compared to those encountered in traditional Euclidean settings. This pioneering paper introduces a groundbreaking approach to analyzing the impact of circular covariates on a target variable through the application of local likelihood techniques. This is notably the first instance of utilizing these methods in the field of directional statistics. Diverse  applications are reported, using data on human motor resonance, particulate matter pollution, and neuroscience experiments, demonstrating the method’s versatility and effectiveness.

Best methodological contribution in Operations Research

Jordi Castro (professor of Statistics and Operations Research at the Polytechnic University of Catalonia), Laureano Escudero (retired professor and ad honorem research collaborator at the Rey Juan Carlos University) and Juan Monge (professor of Statistics and Operations Research at the Miguel Hernández University), for their paper On solving large-scale multistage stochastic optimization problems with a new specialized interior-point approach, published in the European Journal of Operational Research.

The article constitutes an outstanding methodological contribution to the Operations Research field, since it represents a superb combination of modelling, optimization, and implementation. The authors pay special attention to the differentiation of strategic and operational uncertainty in multistage stochastic models, recasting the resulting problem in block angular form. Then they adopt a special interior-point approach to exploit this structure, implement their algorithms and compare favorably with one of the leading professional solvers. All in all, their innovative methodology and experimental results lead the jury to award the prize in category two to these authors.

Best applied contribution in Statistics

Jesús López Fidalgo (professor of Statistics at the University of Navarre), Caterina May (associate professor of Statistics at the Eastern Piedmont University) and José Antonio Moler (associate professor of Statistics and Operations Research at the Public University of Navarre), for their paper Designing experiments for estimating an appropriate outlet size for a silo type problem, published in Annals of Applied Statistics.

This paper shows an interesting application of C-optimal design to approximate the maximum likelihood estimator of a linear combination of unknown parameters with minimum variance. The motivation is the consideration of the outlet size which guarantees a minimum expected time between two consecutive blockages. A linear approximation of the model through the Fisher  Information Matrix is considered. To solve the C-optimal design, the application of a graphical procedure based on the construction of a convex hull is achieved. The simulation study and real-data application illustrate their innovative proposal. This contribution has a clear social and economic impact in agriculture and industry, with important implications in risk assessment. The journal Annals of Applied Statistics is one of the most prestigious journals, focusing on innovative contributions to statistics for solving relevant real data problems.

Best applied contribution in Operations Research

Peter Biró (senior researcher at the en el Centre for Economic and Regional Studies and associate professor at the Corvinus University of Budapest, Hungary), Flip Klijn (scientific director of the Institute for Economic Analysis, National Research Agency, and research professor at the Barcelona School of Economics), Xenia Klimentova (senior researcher in Enterprise Systems Engineering at the Institute for Systems and Computer Engineering, Technology and Science, INESC TEC) and Ana Viana (coordinator professor of Engineering at the Polytechnic Institute of Porto and senior researcher of Industrial Engineering and Management at the Institute for Systems and Computer Engineering, Technology and Science, INESC TEC), for their paper Shapley–Scarf housing markets: respecting improvement, integer programming, and kidney exchange, published in Mathematics of Operations Research.

This paper proposes strong contributions to the optimization and design of allocation rules with a special focus on Kidney Exchange Programs (KEP). The paper is a remarkable combination of different types of interesting results and findings that can be expected to have a significant impact on the use of kidney exchange mechanisms in the field and can alter our approaches to kidney exchange in the long run because of its theoretical and practical findings.

Best contribution in Statistics and Operations Research applied to Data Science and Big Data

Emilio Carrizosa (professor of Statistics and Operations Research at the University of Seville), Jasone Ramírez-Ayerbe (predoctoral researcher in Statistics and Operations Research at the University of Seville) and Dolores Romero (professor of Operations Research at the Copenhagen Business School), for their paper Mathematical optimization modelling for group counterfactual explanations, published in the European Journal of Operational Research.

This is an original contribution to the field of Explainable Artificial Intelligence (XAI) for classification using the important new idea of Counterfactual Analysis. In the simplest case of understanding a classification method for some records into two given classes, a useful procedure is to associate to each record a so-called counterfactual explanation, that is, a small change in the record that makes it to have a high probability of being classified in the opposite class. In this article a collection of new models with combinatorial structure are presented for situations in which the same counterfactual solution can be used for several records, a problem that has not been studied. These new problems can be easily addressed with Mixed Integer (Nonlinear) Optimization solvers and the article analyses new methods using Mathematical Optimization ideas to solve them.

Committee

The international committee has a membership proposed by SEIO and the BBVA Foundation. Chairing the committee on this occasion was Daniel Peña, emeritus professor of Statistics at the Carlos III University of Madrid. Its members were: Michael Greenacre, professor of Statistics at the Pompeu Fabra University and the Barcelona School of Economics; Martine Labbé, professor of Operations Research at the Université Libre de Bruxelles (Belgium); Alfredo Marín, professor of Statistics and Operations Research at the University of Murcia; María Dolores Ruiz, professor of Statistics and Operations Research at the University of Granada; and Carla Marina Vairetti, associate professor of Industrial Civil Engineering at the Universidad de los Andes (Chile).