Departament d'Estadística i Investigació Operativa
http://hdl.handle.net/2117/3941
20160209T21:01:22Z

A sharedparameter joint model for prostate cancer risk and psa longitudinal profiles
http://hdl.handle.net/2117/82670
A sharedparameter joint model for prostate cancer risk and psa longitudinal profiles
Serrat Piè, Carles; Rué, Montserrat; Perpiñán Fabuel, Hèctor; Forte, Anabel; Armero, Carmen; Piulachs, Xavier; Páez, Álvaro; Gómez Melis, Guadalupe
The paper describes the use of frequentist and Bayesian sharedparameter joint models of longitudinal measurements of prostate specific antigen (PSA) and the risk of prostate cancer (PCa). The motivating dataset corresponds to the screening arm of the Spanish branch of the European Randomized Screening for Prostate Cancer (ERSPC) study. The results show that PSA is highly associated with the risk of being diagnosed with PCa and that there is an agevarying effect of PSA on PCa risk. Both the frequentist and Bayesian paradigms produced very close parameter estimates and subsequent 95% confidence and credibility intervals. Dynamic estimations of diseasefree probabilities obtained using Bayesian inference highlight the potential of joint models to guide personalized riskbased screening strategies.
20160208T12:54:41Z
Serrat Piè, Carles
Rué, Montserrat
Perpiñán Fabuel, Hèctor
Forte, Anabel
Armero, Carmen
Piulachs, Xavier
Páez, Álvaro
Gómez Melis, Guadalupe
The paper describes the use of frequentist and Bayesian sharedparameter joint models of longitudinal measurements of prostate specific antigen (PSA) and the risk of prostate cancer (PCa). The motivating dataset corresponds to the screening arm of the Spanish branch of the European Randomized Screening for Prostate Cancer (ERSPC) study. The results show that PSA is highly associated with the risk of being diagnosed with PCa and that there is an agevarying effect of PSA on PCa risk. Both the frequentist and Bayesian paradigms produced very close parameter estimates and subsequent 95% confidence and credibility intervals. Dynamic estimations of diseasefree probabilities obtained using Bayesian inference highlight the potential of joint models to guide personalized riskbased screening strategies.

Exact inference for HardyWeinberg proportions with missing genotypes: single and multiple imputation
http://hdl.handle.net/2117/82666
Exact inference for HardyWeinberg proportions with missing genotypes: single and multiple imputation
Graffelman, Jan; Nelson, S.; Gogarten, S.M.; Weir, B.S.
This paper addresses the issue of exacttest based statistical inference for HardyWeinberg equilibrium in the presence of missing genotype data. Missing genotypes often are discarded when markers are tested for HardyWeinberg equilibrium, which can lead to bias in the statistical inference about equilibrium. Single and multiple imputation can improve inference on equilibrium. We develop tests for equilibrium in the presence of missingness by using both inbreeding coefficients (or, equivalently, ¿2 statistics) and exact pvalues. The analysis of a set of markers with a high missing rate from the GENEVA project on prematurity shows that exact inference on equilibrium can be altered considerably when missingness is taken into account. For markers with a high missing rate (>5%), we found that both single and multiple imputation tend to diminish evidence for HardyWeinberg disequilibrium. Depending on the imputation method used, 613% of the test results changed qualitatively at the 5% leve
20160208T11:50:14Z
Graffelman, Jan
Nelson, S.
Gogarten, S.M.
Weir, B.S.
This paper addresses the issue of exacttest based statistical inference for HardyWeinberg equilibrium in the presence of missing genotype data. Missing genotypes often are discarded when markers are tested for HardyWeinberg equilibrium, which can lead to bias in the statistical inference about equilibrium. Single and multiple imputation can improve inference on equilibrium. We develop tests for equilibrium in the presence of missingness by using both inbreeding coefficients (or, equivalently, ¿2 statistics) and exact pvalues. The analysis of a set of markers with a high missing rate from the GENEVA project on prematurity shows that exact inference on equilibrium can be altered considerably when missingness is taken into account. For markers with a high missing rate (>5%), we found that both single and multiple imputation tend to diminish evidence for HardyWeinberg disequilibrium. Depending on the imputation method used, 613% of the test results changed qualitatively at the 5% leve

Fixedcharge facility location problems in location science
http://hdl.handle.net/2117/82657
Fixedcharge facility location problems in location science
Fernández Aréizaga, Elena; Landete, Mercedes
FixedCharge Facility Location Problems are among core problems in Location Science. There is a finite set of users with demand of service and a finite set of potential locations for the facilities that will offer service to users. Two types of decisions must be made: Location decisions determine where to establish the facilities whereas allocation decisions dictate how to satisfy the users demand from the established facilities. Potential applications of various types arise in many different contexts. We provide an overview of the main elements that may intervene in the modeling and the solution process of FixedCharge Facility Location Problems, namely, modeling hypotheses and their implications, characteristics of formulations and their relation to other formulations, properties of the domains, and appropriate solution techniques.
20160208T10:02:41Z
Fernández Aréizaga, Elena
Landete, Mercedes
FixedCharge Facility Location Problems are among core problems in Location Science. There is a finite set of users with demand of service and a finite set of potential locations for the facilities that will offer service to users. Two types of decisions must be made: Location decisions determine where to establish the facilities whereas allocation decisions dictate how to satisfy the users demand from the established facilities. Potential applications of various types arise in many different contexts. We provide an overview of the main elements that may intervene in the modeling and the solution process of FixedCharge Facility Location Problems, namely, modeling hypotheses and their implications, characteristics of formulations and their relation to other formulations, properties of the domains, and appropriate solution techniques.

Evaluation of project based learning in the area of manufacturing and statistics in the degreee of industrial technology
http://hdl.handle.net/2117/82540
Evaluation of project based learning in the area of manufacturing and statistics in the degreee of industrial technology
Buj Corral, Irene; Marco Almagro, Lluís; Riba, Alexandre; Vivancos Calvet, Joan; TortMartorell Llabrés, Xavier
In the subject Project I in the second year of the Degree in Industrial Technology Engineering taught at the School of Industrial Engineering of Barcelona (ETSEIB), groups of 34 students develop a project along a semester. Results of 2 projects are presented related to manufacturing, measurement of parts and the statistical treatment of data, placing emphasis on crosscurricular issues, recording of oral presentations and how this helped improving its quality, as well as evaluation of the subject by the students by means of questionnaires and openended questions.
20160204T12:07:10Z
Buj Corral, Irene
Marco Almagro, Lluís
Riba, Alexandre
Vivancos Calvet, Joan
TortMartorell Llabrés, Xavier
In the subject Project I in the second year of the Degree in Industrial Technology Engineering taught at the School of Industrial Engineering of Barcelona (ETSEIB), groups of 34 students develop a project along a semester. Results of 2 projects are presented related to manufacturing, measurement of parts and the statistical treatment of data, placing emphasis on crosscurricular issues, recording of oral presentations and how this helped improving its quality, as well as evaluation of the subject by the students by means of questionnaires and openended questions.

Economic analysis of battery electric storage systems operating in electricity markets
http://hdl.handle.net/2117/82524
Economic analysis of battery electric storage systems operating in electricity markets
Heredia, F.Javier (Francisco Javier); Riera, Jordi; Mata, Montserrat; Escuer, Joan; Romeu, Jordi
Battery electric storage systems (BESS) in the range of 110 MWh is a key technology allowing a more efficient operation of small electricity market producer. The aim of this work is to assess the economic viability of Liion based BESS systems for small electricity producers. The results of the expost economic analysis performed with real data from the Iberian Electricity Market shows the economic viability of a Liion based BESS thanks to the optimal operation in dayahead and ancillary electricity markets.
20160203T18:04:17Z
Heredia, F.Javier (Francisco Javier)
Riera, Jordi
Mata, Montserrat
Escuer, Joan
Romeu, Jordi
Battery electric storage systems (BESS) in the range of 110 MWh is a key technology allowing a more efficient operation of small electricity market producer. The aim of this work is to assess the economic viability of Liion based BESS systems for small electricity producers. The results of the expost economic analysis performed with real data from the Iberian Electricity Market shows the economic viability of a Liion based BESS thanks to the optimal operation in dayahead and ancillary electricity markets.

Correspondence analysis on generalised aggregated lexical tables (CAGALT) in the FactoMineR package
http://hdl.handle.net/2117/82168
Correspondence analysis on generalised aggregated lexical tables (CAGALT) in the FactoMineR package
Kostov, Belchin Adriyanov; Bécue Bertaut, Mónica María; Husson, François
Correspondence analysis on generalised aggregated lexical tables (CAGALT) is a method that generalizes classical CAALT to the case of several quantitative, categorical and mixed variables. It aims to establish a typology of the external variables and a typology of the events from their mutual relationships. In order to do so, the influence of external variables on the lexical choices is untangled cancelling the associations among them, and to avoid the instability issued from multicollinearity, they are substituted by their principal components. The CaGalt function, implemented in the FactoMineR package, provides numerous numerical and graphical outputs. Confidence ellipses are also provided to validate and improve the representation of words and variables. Although this methodology was developed mainly to give an answer to the problem of analyzing openended questions, it can be applied to any kind of frequency/contingency table with external variables.
20160127T18:55:38Z
Kostov, Belchin Adriyanov
Bécue Bertaut, Mónica María
Husson, François
Correspondence analysis on generalised aggregated lexical tables (CAGALT) is a method that generalizes classical CAALT to the case of several quantitative, categorical and mixed variables. It aims to establish a typology of the external variables and a typology of the events from their mutual relationships. In order to do so, the influence of external variables on the lexical choices is untangled cancelling the associations among them, and to avoid the instability issued from multicollinearity, they are substituted by their principal components. The CaGalt function, implemented in the FactoMineR package, provides numerous numerical and graphical outputs. Confidence ellipses are also provided to validate and improve the representation of words and variables. Although this methodology was developed mainly to give an answer to the problem of analyzing openended questions, it can be applied to any kind of frequency/contingency table with external variables.

A robust framework for the estimation of dynamic OD trip matrices for reliable traffic management
http://hdl.handle.net/2117/82164
A robust framework for the estimation of dynamic OD trip matrices for reliable traffic management
Barceló Bugeda, Jaime; Montero Mercadé, Lídia
OriginDestination (OD) trip matrices describe the patterns of traffic behavior across the network and play a key role as primary data input to many traffic models. OD matrices are a critical requirement, either in static or dynamic models for traffic assignment. However, OD matrices are not yet directly observable; thus, the current practice consists of adjusting an initial or a priori matrix from link flow counts, speeds, travel times and other aggregate demand data. This information is provided by an existing layout of traffic counting stations, as the traditional loop detectors. The availability of new traffic measurements provided by ICT applications offers the possibility to formulate and develop more efficient algorithms, especially suited for realtime applications. However, the efficiently strongly depends, among other factor, on the quality of the seed matrix. This paper proposes an integrated computational framework in which an offline procedure generates the timesliced OD matrices, which are the input to an online estimator. The paper also analyzes the sensitivity of the online estimator with respect to the available traffic measurements
20160127T18:22:37Z
Barceló Bugeda, Jaime
Montero Mercadé, Lídia
OriginDestination (OD) trip matrices describe the patterns of traffic behavior across the network and play a key role as primary data input to many traffic models. OD matrices are a critical requirement, either in static or dynamic models for traffic assignment. However, OD matrices are not yet directly observable; thus, the current practice consists of adjusting an initial or a priori matrix from link flow counts, speeds, travel times and other aggregate demand data. This information is provided by an existing layout of traffic counting stations, as the traditional loop detectors. The availability of new traffic measurements provided by ICT applications offers the possibility to formulate and develop more efficient algorithms, especially suited for realtime applications. However, the efficiently strongly depends, among other factor, on the quality of the seed matrix. This paper proposes an integrated computational framework in which an offline procedure generates the timesliced OD matrices, which are the input to an online estimator. The paper also analyzes the sensitivity of the online estimator with respect to the available traffic measurements

Distributed experiment for the calculus of optimal values for energy consumption in buildings
http://hdl.handle.net/2117/81953
Distributed experiment for the calculus of optimal values for energy consumption in buildings
Fonseca Casas, Pau; Fonseca Casas, Antoni; Garrido Soriano, Núria; Aina Ortiz, Joana; Casanovas Garcia, Josep; Salom, Jaume
20160125T12:35:58Z
Fonseca Casas, Pau
Fonseca Casas, Antoni
Garrido Soriano, Núria
Aina Ortiz, Joana
Casanovas Garcia, Josep
Salom, Jaume

UPCEO, connecting statistics and people using R
http://hdl.handle.net/2117/81952
UPCEO, connecting statistics and people using R
Fonseca Casas, Pau; Tormos, Raül; Casanovas Garcia, Josep
A methodology and a tool that implements this methodology are developed using R to construct a web site that allows a lay user to consult statistical information owned by an institution and stored in a cloud database. This methodology was developed followin g the open  data philosophy and was implemented with open source software using R as a key element. The proposed methodology was applied successfully to develop a tool to manage the data of the Centre d’Estudis d’Opinió, but it can be applied to another sta tistical center to enable open access to its data. The system is deployed on a cloud infrastructure that scales according to demand, implementing a 24/7 solution. A user (or a computer program) can access the information on the website using the R language as a communication channel or using a programming application interface. Additionally, in the R language, a common framework can be defined to structure the various processes involved in any statistical operation.
20160125T12:19:30Z
Fonseca Casas, Pau
Tormos, Raül
Casanovas Garcia, Josep
A methodology and a tool that implements this methodology are developed using R to construct a web site that allows a lay user to consult statistical information owned by an institution and stored in a cloud database. This methodology was developed followin g the open  data philosophy and was implemented with open source software using R as a key element. The proposed methodology was applied successfully to develop a tool to manage the data of the Centre d’Estudis d’Opinió, but it can be applied to another sta tistical center to enable open access to its data. The system is deployed on a cloud infrastructure that scales according to demand, implementing a 24/7 solution. A user (or a computer program) can access the information on the website using the R language as a communication channel or using a programming application interface. Additionally, in the R language, a common framework can be defined to structure the various processes involved in any statistical operation.

On the collaboration uncapacitated arc routing problem
http://hdl.handle.net/2117/81939
On the collaboration uncapacitated arc routing problem
Fernández Aréizaga, Elena; Fontana, Dario; Speranza, M. Grazia
© 2015 Elsevier Ltd. All rights reserved.
This paper introduces a new arc routing problem for the optimization of a collaboration scheme among carriers. This yields to the study of a profitable uncapacitated arc routing problem with multiple depots, where carriers collaborate to improve the profit gained. In the first model the goal is the maximization of the total profit of the coalition of carriers, independently of the individual profit of each carrier. Then, a lower bound on the individual profit of each carrier is included. This lower bound may represent the profit of the carrier in the case no collaboration is implemented. The models are formulated as integer linear programs and solved through a branchandcut algorithm. Theoretical results, concerning the computational complexity, the impact of collaboration on profit and a game theoretical perspective, are provided. The models are tested on a set of 971 instances generated from 118 benchmark instances for the Privatized Rural Postman Problem, with up to 102 vertices. All the 971 instances are solved to optimality within few seconds.
20160125T09:33:18Z
Fernández Aréizaga, Elena
Fontana, Dario
Speranza, M. Grazia
© 2015 Elsevier Ltd. All rights reserved.
This paper introduces a new arc routing problem for the optimization of a collaboration scheme among carriers. This yields to the study of a profitable uncapacitated arc routing problem with multiple depots, where carriers collaborate to improve the profit gained. In the first model the goal is the maximization of the total profit of the coalition of carriers, independently of the individual profit of each carrier. Then, a lower bound on the individual profit of each carrier is included. This lower bound may represent the profit of the carrier in the case no collaboration is implemented. The models are formulated as integer linear programs and solved through a branchandcut algorithm. Theoretical results, concerning the computational complexity, the impact of collaboration on profit and a game theoretical perspective, are provided. The models are tested on a set of 971 instances generated from 118 benchmark instances for the Privatized Rural Postman Problem, with up to 102 vertices. All the 971 instances are solved to optimality within few seconds.