On capacity expansion planning under strategic and operational uncertainties for stochastic dominance risk averse-based management

24 julio, 2018
12:00

Titulo:聽鈥淥n capacity expansion planning under strategic and operational uncertainties for stochastic dominance risk averse-based management鈥

Poenente:聽Laureano F. Escudero (Universidad Rey Juan Carlos)

Fecha: Martes聽24 de julio, 12:00 horas.

Lugar:聽Sala de Seminarios, Instituto Universitario de Investigaci贸n CIO, Edificio Torretamarit,聽Universidad Miguel Hern谩ndez聽(Campus de Elche)

Resumen:聽A new scheme for dealing with uncertainty in scenario trees is presented for dynamic mixed 0-1 optimization problems with strategic and operational stochastic parameters. Let us generically name this type of problems as Capacity Expansion Planning (CEP) in a given system, e.g., supply chain, production, rapid transit network, energy generation and transmission network, forest fire management, etc. The strategic scenario tree is usually a multistage one, and the replicas of the strategic nodes root structures in the form of either a special scenario graph or a two-stage scenario tree, depending on the type of operational activity in the system. Those 聽operational scenario structures impact in the constraints of the model and, thus, in the decomposition methodology for solving usually large-scale problems. This work presents the modeling framework for some of the risk neutral and risk averse measures to consider for CEP problem solving. Two types of risk averse measures are considered. The first one is a time-inconsistent mixture of the chance constrained and second-order stochastic dominance (SSD) functional of the value of a given set of functions up to the strategic nodes in selected stages along the time horizon.

Categories: Seminarios Doctorado Tags:
Jueves, 19 de julio de 2018 Sin comentarios

DEFENSA DE TESIS DOCTORAL: Nuevos problemas de agregaci贸n de rankings: modelos y algoritmos

23 julio, 2018
12:00

DEFENSA DE TESIS DOCTORAL

T铆tulo:聽 Nuevos problemas de agregaci贸n de rankings: modelos y algoritmos

Autor:聽Eva Mar铆a Garc铆a Nov茅

Directores: Dr.聽Javier Alcaraz Soria (Universidad Miguel Hern谩ndez de Elche) y Dra.聽Mercedes Landete Ruiz (Universidad Miguel Hern谩ndez de Elche)

Fecha: Lunes 23 de聽juilo de 2018 a las 12:00 horas

Lugar:聽Sala de Seminarios IBMC, Edificio Torregait谩n. Campus de Elche de la Universidad Miguel Hern谩ndez de Elche

Viernes, 13 de julio de 2018 Sin comentarios

Minimax Inequalities and Nonlinear In nite Programming

28 junio, 2018
13:00

T铆tulo:聽Minimax Inequalities and Nonlinear In nite Programming

Ponente:聽Miguel Ruiz Gal谩n (Universidad de Granada)

Fecha:聽Jueves聽28 de junio de 2018 a las 13:00 horas

Lugar:聽Sala de Seminarios, Instituto Universitario de Investigaci贸n CIO, Edificio Torretamarit,聽Universidad Miguel Hern谩ndez聽(Campus de Elche)

Resumen: A minimax inequality guarantees the validity of the interchange of the operations聽“sup” and “inf” for certain two-variable functions. We fi rst show some recent advances on minimax theory and then illustrate their versatility with some applications to nonlinear in nite programming.

Categories: Seminarios Doctorado Tags:
Jueves, 21 de junio de 2018 Sin comentarios

Nuevos procedimientos estad铆sticos para los modelos de regresi贸n log铆stica multinomial

18 junio, 2018
12:30

T铆tulo:聽Nuevos procedimientos estad铆sticos para los modelos de regresi贸n log铆stica multinomial

Ponente:聽Nirian Mart铆n (Universidad Complutense de Madrid)

Fecha: Lunes 18 de junio de 2018 a las 12:30 horas

Lugar:聽Sala de Seminarios, Instituto Universitario de Investigaci贸n CIO, Edificio Torretamarit,聽Universidad Miguel Hern谩ndez聽(Campus de Elche)

Resumen: Este trabajo desarrolla una nueva familia de estimadores, los conocidos estimadores de m铆nima “density power divergence” para el modelo de regresi贸n log铆stica multinomial. Se presentan as铆 mismo, una familia de estad铆sticos de contraste de Wald, 煤tiles para hip贸tesis lineales respecto a los par谩metros del modelo, basados en estos estimadores. Se estudia te贸ricamente la robustez de de los estimadores y estad铆sticos de contraste propuestos, mediante un an谩lisis de la funci贸n de influencia. Se muestran varios ejemplos reales para ilustrar la necesidad de contar con procedimientos estad铆sticos robustos en lugar de utilizar inferencia estad铆stica basada en la funci贸n de verosimilitud. Se realiza tambi茅n un estudio de simulaci贸n con el fin de validar emp铆ricamente los resultados te贸ricos del trabajo. Finalmente, se propone un procedimiento basado en realizaciones muestrales para seleccionar el par谩metro de robustez adecuado con su correspondiente justificaci贸n emp铆rica.

Categories: Seminarios Doctorado Tags:
Jueves, 7 de junio de 2018 Sin comentarios

El enfoque sist茅mico en la eficiencia de la educaci贸n superior: una revisi贸n integrativa de la literatura

13 junio, 2018
13:00

CANCELADO POR MOTIVOS PERSONALES DE LA PONENTE

T铆tulo:聽El enfoque sist茅mico en la eficiencia de la educaci贸n superior: una revisi贸n integrativa de la literatura

Ponente:聽Dorys Yaneth Rodriguez Castro (Universidad de聽Deusto)

Fecha:聽Mi茅rcoles 13聽de junio de 2018 a las 13:00 horas

Lugar:聽Sala de Seminarios, Instituto Universitario de Investigaci贸n CIO, Edificio Torretamarit,聽Universidad Miguel Hern谩ndez聽(Campus de Elche)

El enfoque sist茅mico es una aproximaci贸n metodol贸gica para la evaluaci贸n de sistemas que se centra en examinar la interacci贸n entre los actores clave que lo conforman. En los sistemas de educaci贸n superior los procesos se originan en la interacci贸n entre elementos institucionales y organizacionales, que en su conjunto se comportan como un sistema, y que en su esencia requiere de insumos, mecanismos de conversi贸n a nivel procesal, con salidas y flujos de retroalimentaci贸n. Adicionalmente, estos sistemas enfrentan presiones internas (cobertura y calidad) y externas (ser competitivos en un mercado global) que los obligan a optimizar sus recursos y a mejorar su desempe帽o, logrando que las universidades que los conforman sean eficientes y efectivas en su producci贸n. Consecuentemente, a las universidades se les generan, cada vez m谩s, mayores responsabilidades reforzando su car谩cter de organizaciones multiproducto, multidimensional y multiprop贸sito. Este art铆culo propone examinar qu茅 y c贸mo se mide el desempe帽o de sistemas de educaci贸n superior en entornos institucionales a escala nacional. De esta forma, esta investigaci贸n ofrece una base conceptual s贸lida e integral para la definici贸n de modelos de medici贸n del desempe帽o de sistemas de educaci贸n superior, brindando alternativas para la gesti贸n de las pol铆ticas p煤blicas desde un enfoque sist茅mico. Para la validaci贸n emp铆rica se examinaron los estudios previos sobre medici贸n de eficiencia y productividad del sector de educaci贸n superior aplicando la metodolog铆a de revisi贸n integrativa de literatura. Los resultados muestran el creciente inter茅s de la comunidad cient铆fica en la evaluaci贸n emp铆rica de sistemas de educaci贸n superior y en el desarrollo de t茅cnicas matem谩ticas ajustadas a la estructura funcional de este sector. Se evidencia la evaluaci贸n del desempe帽o de sistemas nacionales en funci贸n a cinco orientaciones de producci贸n del orden organizacional. Esta investigaci贸n culmina con una discusi贸n acerca del desarrollo de esta tem谩tica de investigaci贸n e identifica las limitaciones, 谩reas y temas futuros a explorar, para su consolidaci贸n como herramienta de evaluaci贸n sist茅mica.

 

Categories: Seminarios Doctorado Tags:
Mi茅rcoles, 30 de mayo de 2018 Sin comentarios

Ranking and Benchmarking Innovation Performance in the EU: Policy Guidelines Based on DEA-TOPSIS Methods

12 junio, 2018
13:00

T铆tulo:聽Ranking and Benchmarking Innovation Performance in the EU: Policy Guidelines Based on DEA-TOPSIS Methods

Ponente:聽Jon Mikel Zabala (Universidad de聽Deusto)

Fecha:聽Martes 12聽de junio de 2018 a las 13:00 horas

Lugar:聽Sala de Seminarios, Instituto Universitario de Investigaci贸n CIO, Edificio Torretamarit,聽Universidad Miguel Hern谩ndez聽(Campus de Elche)

“The Innovation Union Scoreboard (IUS) is a tool to monitor the implementation of and to examine and illustrate the innovation performance of European Member States as well as to evaluate (and rank) their research and innovation systems. A Summary Innovation Index (SII) is provided by the IUS to assess the innovation performance of the member states.聽The SII is constituted by an average of 25 indicators.聽聽The IUS thus measures the innovation performance for each country by summarizing all 25 indicators into a single SII, irrespective of whether the indicators are presenting innovation outputs or innovation inputs. In addition in the SII all indicators are equally weighted.聽聽This means that the higher the average value of the 25 indicators, the better the innovation performance is said to be.

The IUS follows a rationale in which 鈥渢he more is the better鈥, namely, the higher the values of the 25 indicators that constitute the IUS, the better the innovation performance. The goal of this paper is to examine the IUS, and through the application of a complementary methodology based on efficiency, find out whether the ranking of European countries obtained with each approach are positively related (i.e. complementary) to each other.聽By doing so, the paper offers a critical review of the SII, and proposes to put more emphasis on the identification of and relation between input and output innovation indicators.聽We find that the results differ substantially between the SII and the ranking based on our method, with significant consequences for the design of innovation policies”.

Categories: Seminarios Doctorado Tags:
Martes, 29 de mayo de 2018 Sin comentarios

The problem of dividing a budget among several districts

4 junio, 2018
12:30

T铆tulo:聽The 聽problem of dividing a budget among several districts

Ponente:聽Ricardo Mart铆nez (Universidad de Granada)

Fecha:聽Lunes 4 de junio de 2018 a las 12:30 horas

Lugar:聽Sala de Seminarios, Instituto Universitario de Investigaci贸n CIO, Edificio Torretamarit,聽Universidad Miguel Hern谩ndez聽(Campus de Elche)

Resumen:

We study the problem of dividing a budget among the districts of a city taking into account their population and wealth. We focus on order preservation properties that ensure higher transfers to those districts with larger populations and, at the same time, introduce a policy redistribution so that districts with lower wealth per capita obtain higher transfers per capita. We determine the allocation methods that fulfills both requirements. We also study requirements on the stability and manipulability of the allocation. We find out that the proportional rule is the unique allocation method that meets the previous requirements. This proportional rule obviates the wealth component of the problem; however is reduces the inequality in the wealth per capita.

Categories: Seminarios Doctorado Tags:
Jueves, 17 de mayo de 2018 Sin comentarios

Uniform inference for Small Area Parameter

24 mayo, 2018
12:00

T铆tulo: Uniform inference for Small Area Parameter

聽Ponente: Stefan Sperlich (Universidad de Ginebra, Instituto de Econom铆a y Econometr铆a, Suiza)

Fecha:聽Jueves聽24 de mayo de 2018 a las 12:00 horas

Lugar:聽Sala de Seminarios, Instituto Universitario de Investigaci贸n CIO, Edificio Torretamarit,聽Universidad Miguel Hern谩ndez聽(Campus de Elche)

Resumen:

Today, SAE is a common tool used world-wide by Statistical offices for addressing the need of disaggregated information. Interval estimates can either be extremely wide if not model-based, or only refer to marginal (ie unconditional) distributions. That is, when speaking of a 95% confidence interval, for 5% of the considered areas, the intervals do not contain the true parameter. This is a delicate default if political decisions based on them, and prohibits the comparing areas based on those estimates.聽 In this work, construction of uniform prediction intervals (or simultaneous confidence sets) for small area parameter in linear mixed models is introduced. We consider three frameworks to develop simultaneous intervals: analytical, numerical and bootstrap approximation. Proofs of the consistency as well as the asymptotic coverage probability of the bootstrap intervals are provided. Our proposal is accompanied by simulation experiments and data examples.

Categories: Seminarios Doctorado Tags:
Jueves, 17 de mayo de 2018 Sin comentarios

Mathematical Programs with Complementarity constraints: Critical Point Theory

23 mayo, 2018
12:30

T铆tulo:聽Mathematical Programs with Complementarity constraints: Critical Point Theory

Ponente:聽Jan J. R眉ckmann (Universidad de Bergen, Noruega)

Fecha:聽Mi茅rcoles聽23 de聽mayo de 2018 a las 12:30 horas

Lugar:聽Sala de Seminarios, 聽Instituto Universitario de Investigaci贸n CIO, Edificio Torretamarit,聽Universidad Miguel Hern谩ndez聽(Campus de Elche)

Resumen:

We study mathematical programs with complementarity constraints from a topological point of view. We derive a Morse Lemma at nondegenerate C-stationary points and present two basic theorems from Morse theory (deformation theorem and cell-attachment theorem). Outside the C-stationary point set,continuous deformation of lower level sets can be performed and, as a consequence, the topological data (such as the number of connected components) remain invariant. However, when passing a level containing a C-stationary point, the topology of the lower level set changes via the attachment of a q-dimensional cell where its dimension equals the stationary C-index of the corresponding C-stationary point. The stationary C-index depends on both the restricted Hessian of the Lagrangian and the Lagrange multipliers related to bi-active complementarity constraints. Finally, some relations with other stationarity concepts are discussed.

Categories: Seminarios Doctorado Tags:
Jueves, 17 de mayo de 2018 Sin comentarios

Incentives and Emission Responsibility Allocation in Supply Chains

22 mayo, 2018
12:30

SEMINARIO DEL DOCTORADO DE ESTAD脥STICA, OPTIMIZACI脫N Y MATEM脕TICAAPLICADA. CURSO 2017-2018

Titulo:聽Incentives and Emission Responsibility Allocation in Supply Chains

Ponente:聽Greys Sosic (USC Marshall School of聽Business, USA)

Fecha: Martes 22 de Mayo de 2018聽a las聽12:30 horas

Lugar:聽Sala de Seminarios, Instituto Universitario de Investigaci贸n CIO, Edificio Torretamarit,聽Universidad Miguel Hern谩ndez聽(Campus de Elche)

聽Resumen:

In view of the urgency and challenges of mitigating climate change, it should be noted that Greenhouse Gas (GHG) emitted from the supply chains of the 2,500 largest global corporations accounts for about 18% of global GHG emissions. Therefore, rationalizing emissions in supply chains could make a significant contribution to achieving the CO2 emission reduction targets recently agreed upon in Paris (Paris Agreement, 2015).

In this paper we consider supply chains with 聽motivated dominant leaders, such as Walmart, who strive to reduce emissions in their supply chains. These supply chain leaders are assumed to be knowledgeable about causes of pollution in their supply chains, to the extent that they are able to assign their suppliers responsibilities for both direct and indirect GHG emissions in the supply chain. Given these pollution responsibility assignments, we use cooperative game theory methodology to derive a scheme for allocating the responsibilities of the total GHG emissions to the firms in the supply chain.

The allocation scheme that we derive, which is the Shapley value of an associated cooperative game, is shown to have several desirable properties. In particular, (i) it is footprint-balanced, (ii) it is transparent and easy to compute, (iii) it lends itself to several intuitive and insightful axiomatic characterizations, and (iv) when the abatement cost functions of the firms are private information, it is shown to incentivize suppliers to exert pollution abatement efforts that, among all footprint-balanced allocation schemes, minimize the maximum deviation from the socially optimal pollution level.

Categories: Seminarios Doctorado Tags:
Martes, 24 de abril de 2018 Sin comentarios