Skip to main content

DATOS DE CONTEO: METODOS BAYESIANOS Y COMPOSICIONALES

PID2021-125380OB-I00

•
Funding agency name Agencia Estatal de Investigación
Funding agency acronym AEI
Program Programa Estatal para Impulsar la Investigación Científico-Técnica y su Transferencia
Subprogram Subprograma Estatal de Generación de Conocimiento
Call Proyectos de I+D+i (Generación de Conocimiento y Retos Investigación)
Call year 2021
State Plan 2021-2023 Plan Estatal de Investigación Científica y Técnica y de Innovación
Beneficiary centre UNIVERSITAT POLITECNICA DE CATALUNYA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 28
Encontrada(s) 1 página(s)

DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Contribución de congreso (ConferenceOutput)

Sea-land interaction along the Catalan coast (NW Mediterranean): Assessment of Submarine Groundwater Discharge (SGD) based on seawater nutrient concentrations

  • Sanchis, Martí
  • Garcés, Esther
  • Ortego, María Isabel
  • Folch, Albert
European Geosciences Union General Assembly (EGU24), 14-19 April 2024, Vienna, Austria, Submarine Groundwater Discharge (SGD) has garnered attention in the assessment of sea-land interactions within coastal regions. SGD plays a crucial yet uncertain role in coastal ecosystems, involving the release of nutrient-enriched groundwater and recirculation seawater in the geological matrix into the sea. Its significance is particularly relevant in the oligotrophic Mediterranean Sea, characterized by low nutrient concentrations, making SGD a pivotal process in sustaining life within the sea-land transition zone. This study explores the impact of SGD along the 580 km of the Catalan coast (Western Mediterranean) an area densely populated where land-sea interactions and the effects of SGD on marine ecosystems may be substantial. Leveraging a 23-year dataset, the study seeks to establish connections between SGD and the quality of the coastal area. The primary focus lies in investigate SGD locations through the analysis of salinity and inorganic nutrient composition (NO3, NO2, NH4, PO4, and SiO4) at 70 coastal stations. A novel perspective, Compositional Data Analysis (CoDa), is employed for this purpose. The study also integrates land-based hydrogeological factors, such as the geological nature of the aquifer. Furthermore, it explores the correlations between nutrient composition and biological indicators, specifically chlorophyll in the coastal area, utilizing CoDa techniques. Chlorophyll, as an indicator of photosynthetic activity, serves as a marker for biological responses to nutrient changes induced by SGD. This innovative approach, centered on the compositional nature of the data, streamlines the identification SGD locations and enables a comprehensive assessment of its ecological impact. The outcomes of this study have the potential to provide valuable insights for the improvement of coastal ecosystem management, This work was funded by the Spanish Government grant no. PID2022-140862OB-C21/C22 and PID2021-125380OB-I00 funded by MCIN/AEI/10.13039/501100011033 and by ERDF A way of making Europe, Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Otros (Other)

Detrital zircon age distributions in Bayes-Hilbert spaces

  • Fernández-Suárez, J.
  • Pawlowsky-Glahn, Vera
  • Egozcue, J. J.
A growing number of researchers in the Earth Science community use the information provided by the U[sbnd]Pb ages of detrital zircon in sedimentary environments, be these modern (sediments) or ancient (sedimentary or metasedimentary rocks). This information is key to understanding detritus's past and present flow on Earth and its attendant geological implications. An essential component of the investigation concerning detrital zircon age distributions (DZD) and their bearing on several sedimentological, tectonic, geodynamic, paleogeographic, or climatic issues is to compare DZD from different samples. Much theoretical and empirical research has been devoted to ascertaining how to best compare and measure the dissimilarity/distance between DZDs. This ongoing endeavour has generated a variety of metrics and statistical procedures to perform such tasks. In this contribution, a metric based on the Aitchison distance to measure the dissimilarity of any given set of DZD (samples represented by density functions) is presented. The Aitchison distance is used in the reference framework of the Bayes-Hilbert spaces, whose properties help to avoid some of the limitations of previously used metrics. The mathematical and methodological foundations are presented and illustrated with three geological examples taken from the recent literature, using both sedimentary rocks and recent sediments in different geological and geographical settings. The proposed approach results in a consistent statistical tool to determine whether a set of samples is likely to be derived from a common source or, at least, from indistinguishable sources based on DZD data alone., Gabriel Gutiérrez-Alonso is most kindly acknowledged for countless (and endless) discussions over many a year on nearly every aspect of detrital zircon geochronology. JJE and VPG were supported by the grants PID2021-123833OB-I00 and PID2021-125380OB-I00, funded by the Spanish Ministry of Science, Innovation and Universities (MICIU/AEI/10.13039/501100011033/) and ERDF A way of making Europe. JFS acknowledges financial support from project PID2020-112489GB-C21 funded by the Spanish Ministry of Science, Innovation and Universities. We thankfully acknowledge the two anonymous reviewers whose comments, suggestions and encouragement have contributed to improve the MS., Peer reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

Insights in hierarchical clustering of variables for compositional data

  • Martín Fernández, Josep Antoni
  • Di Donato, Valentino
  • Pawlowsky Glahn, Vera
  • Egozcue Rubí, Juan José|||0000-0002-5144-4483
R-mode hierarchical clustering is a method for forming hierarchical groups of mutually exclusive subsets of variables. This R-mode cluster method identifies interrelationships between variables which are useful for variable selection and dimension reduction. Importantly, the method is based on metric elements defined on the sample space of variables. Consequently, hierarchical clustering of compositional parts should respect the particular geometry of the simplex. In this work, the connections between concepts such as distance, cluster representative, compositional biplot, and log-ratio basis are explored within the framework of the most popular R-mode agglomerative hierarchical clustering methods. The approach is illustrated in a paleoecological study to identify groups of species sharing similar behavior., This research was supported by the Ministerio de Ciencia e Innovación under the projects CODA-GENERA (Ref. PID2021-123833OB-I00) and CONBACO (Ref. PID2021-125380OBI00); and by the Agència de Gestió d’Ajuts Universitaris i de Recerca of the Generalitat de Catalunya under the project COSDA (Ref. 2021SGR01197)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

Estimation of Jacquard’s genetic identity coefficients with bi-allelic variants by constrained least-squares

  • Graffelman, Jan|||0000-0003-3900-0780
  • Weir, Bruce S.
  • Goudet, Jérôme
The Jacquard genetic identity coefficients are of fundamental importance in relatedness research. We address the estimation of these coefficients as well as other relationship parameters that derive from them such as kinship and inbreeding coefficients using a concise matrix framework. Estimation of the Jacquard coefficients via likelihood methods and the expectation–maximization algorithm is computationally very demanding for large numbers of polymorphisms. We propose a constrained least squares approach to estimate the Jacquard coefficients. A simulation study shows constrained least squares achieves root-mean-squared errors that are comparable with those of the maximum likelihood approach, in particular when founder allele frequencies are unknown, while obtaining enormous computational savings., This work was supported by the Spanish Ministry of Science and Innovation and the European Regional Development Fund under grant PID2021-125380OB-I00 (MCIN/ AEI/FEDER); by the Swiss National Science Foundation under grants 31003A_179358 and 310030_215709; and by the National Institutes of Health under Grant GM075091. Wethank the Editor and three anonymous reviewers for their comments, which have helped us to improve the manuscript., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

Assessing the impact on sales of competing nearby supermarkets

  • González Ibáñez, Daniel
  • Puig Oriol, Xavier|||0000-0001-6525-0498
The supermarket industry faces fierce competition in many geographic areas, with various brands competing for a market share that represents a significant portion of a country's GDP. For these businesses, understanding the factors that influence their sales and how they do so is crucial: location, pricing, quality, customer loyalty, and more. While much has been written about how these elements can affect revenue, there is a lack of existing models quantifying the monetary impact of having competitor stores within an own establishment area of influence. This article introduces a hierarchical Bayesian model that quantifies this impact for each product category within the brand's catalog. The model requires careful parameterization to adapt to the specific context, and therefore both its application and design represent a methodological novelty in this area. The main result is a matrix of coefficients that indicate the monetary effect of the presence of every competitor for each product category. The findings revealed by the model show that the influence of the proximity of each competitor does indeed vary depending on these categories. This information is valuable for the company when making decisions, such as choosing new store locations or determining the product assortment to offer in each establishment. The use of the results derived from this model provides a competitive advantage over others and helps to better understand the market by identifying which supermarket brands are the perceived leaders in each product category., This work was supported by the grant PID2021-125380OB-I00 funded by ERDF A way of making Europe, MCIN/AEI/ 10.13039/501100011033, and Agencia Estatal de Investigación., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

Rainfall and wave storms interdependence in the western Spanish Mediterranean coast

  • Aguilera Vidal, Maria|||0000-0001-7669-5273
  • Sanuy Vázquez, Marc|||0000-0003-2711-5409
  • Ortego Martínez, María Isabel|||0000-0001-9437-9354
  • Jiménez Quintana, José Antonio|||0000-0003-0900-4684
We characterise the dominant main terrestrial and marine drivers of compound floodevents in the study region. Due to the prevalence of ephemeral rivers, rainfall represents theterrestrial driver, while waves, more influential than storm surges, represent the marinecomponent. We analyse the frequency, intensity, and interdependence of compound events toidentify spatial patterns across the study area. Conditional exceedance analysis estimates prob-abilities and determines likely driver combinations during multivariate events.New hydrological insights for the region: Significant regional variability exists in compound floodevent drivers. Key hotspots in northern Catalonia and central Valencia are driven by overlappingrainfall and wave patterns. Compound extreme events are around 8–10 % more intense thansingle-driver events. Seasonal patterns revealed that compound extreme events are rare in sum-mer but more frequent in autumn, winter, and spring, with the strongest wave–rainfall correlationoccurring at zero lag time. Areas with stronger statistical dependencies between drivers experi-enced a higher frequency of compound extreme events. We identified the most likely combina-tions of event types associated with various joint return periods. The analysis reveals notableregional variations, with some areas predominantly affected by a single extreme driver, typicallywave storms, and others equally influenced by both wave and rainfall storms. These findingsemphasize the need to incorporate multivariate dependencies and spatial heterogeneity intoregional flood risk assessments., This study was accomplished within the framework of the C3RiskMed research project (PID2020-113638RB-C21, AEI/10.13039/ 501100011033) funded by the Spanish Ministry of Science and Innovation. The first author benefited from a PhD grant from the Spanish Ministry of Science and Innovation (PRE2021-100813). The work of MIO was done in the framework of the projects PID2021-125380OB-I00 (MICIU/AEI/10.13039/501100011033/FEDER, UE), and 2021SGR01197 (Departament de Recerca i Universitats de la Generalitat de Catalunya)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

How compound flood drivers have changed over time in the Catalan coast (NW Mediterranean)

  • Aguilera Vidal, Maria|||0000-0001-7669-5273
  • Sanuy Vázquez, Marc|||0000-0003-2711-5409
  • Ortego Martínez, María Isabel|||0000-0001-9437-9354
  • Jiménez Quintana, José Antonio|||0000-0003-0900-4684
This study examines multi-decadal changes in rainfall and wave interactions driving compound flooding along the Catalan coast (NW Mediterranean) from 1950 to 2022. While growing attention has been given to the increasing impacts of coastal storms in the Mediterranean, this work examines whether such changes are linked to variations in the intensity, frequency, or dependence of the underlying hazard drivers. Results show marked temporal and spatial shifts in the dependence structure between rainfall and waves. Initially near-independent, several basins exhibit a progressive strengthening of dependence and upper-tail coupling, indicating growing synchronization between heavy rainfall and energetic wave events, together with an increased probability of extreme rainfall in northern Catalonia. The frequency of extreme compound events has increased in accordance with the strength of dependence. Northern basins exhibit the highest joint probabilities and annual occurrences, while southern basins remain less affected. Synoptic-scale analyses link these trends to a decline in Atlantic Lows and a concurrent rise in Mediterranean Lows and Cut-Off systems, atmospheric configurations conducive to concurrent heavy rainfall and high waves. The observed north-south gradient in compound hazard can be partly explained by the preferential storm tracks affecting the NW Mediterranean. Cyclonic systems typically develop or intensify in the Gulf of Lion and propagate southeastward, generating strong northeasterly winds and intense precipitation along the northern Catalan coast. The results suggest a potential intensification of compound coastal hazards in northern Catalonia and the need to incorporate evolving driver dependence into coastal risk assessment and climate adaptation strategies., The authors sincerely thank AEMET for the rainfall data and Tim Toomey and Marta Marcos (Universitat de les Illes Balears, Spain) for the wave data. This work has been done within the framework of the C3RiskMed (PID 2020-113638RB-C21, AEI/10.13039/501100011033) research project funded by the Spanish Ministry of Science and Innovation. The first author benefited from a PhD grant from the Spanish Ministry of Science and Innovation. JAJ acknowledges the support of the Departament de Recerca i Universitats of the Generalitat de Catalunya (Academia d’Excel⋅l`encia award). We also acknowledge the contribution of the project PID 2021-125380OB-I00 (MCIN/AEI/10.13039/501100011033, ERDF “A way of making Europe”), in which the third co-author is involved., Peer Reviewed, 13 - Acció per al Clima
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

Analysis of psychological well-being from a compositional data analysis perspective: a new approach

  • Cortés Rodriguez, María
  • Galindo Villardón, Purificación
  • Sánchez Barba, Mercedes
  • Jarauta Bragulat, Eusebio|||0000-0003-3452-3435
  • Urchaga Litago, José David
Well-being is a widely studied construct in psychology. In 1989, Carol Ryff proposed the “Scale of Psychological Well-Being (SPWB)”, which has been validated in multiple languages. The instrument assesses six dimensions of psychological well-being: Self-acceptance, Positive Relationships with Others, Autonomy, Environmental Mastery, Purpose in Life, and Personal Growth. In this article, we propose to enrich the traditional approach of directly interpreting the raw scores in each dimension by incorporating Compositional Data Analysis. This new approach aims to identify “what proportion” of each dimension constitutes well-being, which will allow us to analyze the interactions between the different dimensions of well-being and balance among them. To achieve this, we introduce two position ratios (PR1 and PR2) and a general adjustment indicator called the General Indicator of Subjective Psychological Well-Being (GISPW), which characterizes individuals in a compositional manner, providing a fresh perspective in the interpretation of psychological test results, specifically those related to PWB. The proposal is illustrated with three cases taken from a study involving 628 university students who completed the psychological well-being scale questionnaire. The results show that the GISPW, PR1, and PR2 obtained offer relevant information about the overall balance of each case in the different dimensions., This publication is part of the project PID2021-125380OB-I00, funded by MCIN/AEI/ 10.13039/501100011033 and by “ERDF A way of making Europe”., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

Disease mapping with individual level information, a case study of acute myocardial infarction mortality

  • Puig Oriol, Xavier|||0000-0001-6525-0498
  • Ginebra Molins, Josep|||0000-0001-9521-9635
© 2025 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY-NC license, When mapping relative mortality risk under specific causes of death in time, one can use small areas and single year mortality data to explore the space time variation in detail. To reduce the variability of the initial mortality risk estimates and help explain their differences, hierarchical Poisson models are typically used. Here we deal with the situation where besides aggregated small-area level data necessary for that, one also has complete individual level data about the presence of certain risk factors in the population, which is now rare but it should become routine in places with universal health coverage using a medical record sharing system. In particular, we consider the convenience of including individual level covariates in the models, and mapping relative mortality risk adjusted for them. That is illustrated by exploring how mortality due to acute myocardial infarction varies in space and in time in Catalonia between 2014 and 2019 using individual data on obesity, diabetes, dyslipidemia and smoking habits., APC - EIO (Josep Ginebra), Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

Monitoring count data without a Phase I study: a poisson case on industrial printers

  • González Ibáñez, Daniel
  • Puig Oriol, Xavier|||0000-0001-6525-0498
  • Tort-Martorell Llabrés, Xavier|||0000-0003-1167-6703
Statistical Process Control (SPC) is traditionally based on a two-phase framework: a reference sample is required to estimate in-control parameters (Phase I) before active monitoring (Phase II) begins. However, in many contemporary industrial and service settings, such a sample is either unavailable or heavily contaminated by heterogeneity, structural changes, or sporadic anomalies. Under these conditions, classical Phase I and Phase II schemes are difficult to justify. This challenge arose while attempting to remotely monitor industrial printers, prompting a search for alternatives that led to the Bayesian outlier framework proposed by Box and Tiao. This article revisits that framework and argues that its core principles provide a coherent basis for SPC when reliable Phase I data are absent. In the Box and Tiao formulation, observations arise from a mixture of two components sharing a common mean but differing in dispersion; this allows for simultaneous parameter estimation and outlier identification through posterior probabilities. Using the industrial printer case as a primary example, this article demonstrates how this logic can be extended from the original Normal distribution to Poisson data – such as error counts – which are frequently encountered in SPC applications., This work was supported by the grant Ministerio de Ciencia e Innovación, PID2021-125380OB-I00 funded by ERDF A way of making Europe and by MCIN/AEI/10.13039/501100011033., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

Biplots for the correlation matrix

  • Graffelman, Jan|||0000-0003-3900-0780
The visualization of the correlation matrix by means of biplots is considered. The classical centering operations, either by the overallmean, the column means, or rowand column means are shown to be problematic for the visualization of the correlation matrix, and sub-optimal in terms of goodness-of-fit. More flexible adjustments are possible by using a single scalar adjustment, a set of column scalars or both row–and–column scalars using a weighted alternating least squares algorithm. Recently, correlation biplots with a single scalar adjustment have been advocated and outperform the usual correlation biplots made by principal component analysis. This article presents an iterative algorithm for a column adjustment of the correlation matrix with the goal of improving the goodness-of-fit over the use of a single scalar adjustment and studies its usefulness in practical data analysis. The resulting biplots are harder to read but can be made more interpretable by using correlation tally sticks. Correlation tally sticks are advocated for improving the visualization of correlation structure. The weighted root mean squared error is used to compare lowdimensional approximations to the correlation matrix across methods., This work was supported by the Spanish Ministry of Science and Innovationand the European Regional Development Fund under grant PID2021-125380OB-I00 (MCIN/AEI/FEDER); and the National Institutes of Healthunder Grant GM075091., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

40 years after Aitchison’s article “The statistical analysis of compositional data”. Where we are and where we are heading

  • Coenders, Germà
  • Egozcue Rubí, Juan José|||0000-0002-5144-4483
  • Facevicova, Kamila
  • Navarro López, Carolina
  • Palarea Albadalejo, Javier
  • Pawlowsky Glahn, Vera
  • Tolosana Delgado, Raimon
The year 2022 marked 40 years since Aitchison published the article “The statistical analysis of compositional data”. It is considered to be the foundation of contemporary compositional data analysis. It is time to review what has been accomplished in the feld and what needs to be addressed. Astonishingly enough, many aspects seen as challenging in 1982 continue to lead to fruitful scholarly work. We commence with a bibliometric study and continue with some hot topics such as multi-way compositions, compositional regression models, dealing with zero values, non-logratio transformations, new application felds, and a number of current loose ends. Finally, a tentative future research agenda is outlined., This article was supported by the Spanish Ministry of Science and Innovation/AEI/10.13039/501100011033 and by ERDF – A way of making Europe [grant numbers PID2021-123833OB-I00; PID2021-125380OB-I00], the Department of Research and Universities of the Generalitat de Catalunya [grant number 2021SGR01197], and the Czech Science Foundation [grant number 22-15684L]., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

Subcompositional coherence and a novel proportionality index of parts

  • Egozcue Rubí, Juan José|||0000-0002-5144-4483
  • Pawlowsky Glahn, Vera
Research in compositional data analysis was motivated by spurious (Pearson) correlation. Spurious results are due to semantic incoherence, but the question of ways to relate parts in a statistically consistent way remains open. To solve this problem we frst defne a coherent system of functions with respect to a subcomposition and analyze the space of parts. This leads to understanding why measures like covariance and correlation depend on the subcomposition considered, while measures like the distance between parts are independent of the same. It allows the defnition of a novel index of proportionality between parts., Grants PID2021-125380OB-I00 and PID2021-123833OB-I00 funded by MCIN/AEI/ 10.13039/501100011033 and by ERDF A way of making Europe. The authors also thank the two anonymous reviewers for their detailed and constructive review of the manuscript., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

Mapping life expectancy loss in Barcelona in 2020

  • Puig Oriol, Xavier|||0000-0001-6525-0498
  • Ginebra Molins, Josep|||0000-0001-9521-9635
© 2023 The Author(s). Published with license by Taylor & Francis Group, LLC., We use a Bayesian spatio-temporal model, first to smooth small-area initial life expectancy estimates inBarcelona for 2020, and second to predict what small-area life expectancy would have been in 2020 inabsence of covid-19 using mortality data from 2007 to 2019. This allows us to estimate and map the small-area life expectancy loss, which can be used to assess how the impact of covid-19 varies spatially, and toexplore whether that loss relates to underlying factors, such as population density, educational level, orproportion of older individuals living alone. We find that the small-area life expectancy loss for men and forwomen have similar distributions, and are spatially uncorrelated but positively correlated with populationdensity and among themselves. On average, we estimate that the life expectancy loss in Barcelona in 2020 was of 2.01 years for men, falling back to 2011 levels, and of 2.11 years for women, falling back to 2006 levels., This work was supported by the grant PID2021-125380OB-I00 funded by MCIN/AEI/10.13039/501100011033 and by ERDF A way of making Europe., Peer Reviewed
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Monitoring count data without a Phase I study: a poisson case on industrial printers

  • González Ibáñez, Daniel
  • Puig Oriol, Xavier
  • Tort-Martorell Llabrés, Xavier
Statistical Process Control (SPC) is traditionally based on a two-phase framework: a reference sample is required to estimate in-control parameters (Phase I) before active monitoring (Phase II) begins. However, in many contemporary industrial and service settings, such a sample is either unavailable or heavily contaminated by heterogeneity, structural changes, or sporadic anomalies. Under these conditions, classical Phase I and Phase II schemes are difficult to justify. This challenge arose while attempting to remotely monitor industrial printers, prompting a search for alternatives that led to the Bayesian outlier framework proposed by Box and Tiao. This article revisits that framework and argues that its core principles provide a coherent basis for SPC when reliable Phase I data are absent. In the Box and Tiao formulation, observations arise from a mixture of two components sharing a common mean but differing in dispersion; this allows for simultaneous parameter estimation and outlier identification through posterior probabilities. Using the industrial printer case as a primary example, this article demonstrates how this logic can be extended from the original Normal distribution to Poisson data – such as error counts – which are frequently encountered in SPC applications., This work was supported by the grant Ministerio de Ciencia e Innovación, PID2021-125380OB-I00 funded by ERDF A way of making Europe and by MCIN/AEI/10.13039/501100011033., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

40 years after Aitchison’s article “The statistical analysis of compositional data”. Where we are and where we are heading

  • Coenders, Germà
  • Egozcue Rubí, Juan José
  • Facevicova, Kamila
  • Navarro López, Carolina
  • Palarea Albadalejo, Javier
  • Pawlowsky Glahn, Vera
  • Tolosana Delgado, Raimon
The year 2022 marked 40 years since Aitchison published the article “The statistical analysis of compositional data”. It is considered to be the foundation of contemporary compositional data analysis. It is time to review what has been accomplished in the feld and what needs to be addressed. Astonishingly enough, many aspects seen as challenging in 1982 continue to lead to fruitful scholarly work. We commence with a bibliometric study and continue with some hot topics such as multi-way compositions, compositional regression models, dealing with zero values, non-logratio transformations, new application felds, and a number of current loose ends. Finally, a tentative future research agenda is outlined., This article was supported by the Spanish Ministry of Science and Innovation/AEI/10.13039/501100011033 and by ERDF – A way of making Europe [grant numbers PID2021-123833OB-I00; PID2021-125380OB-I00], the Department of Research and Universities of the Generalitat de Catalunya [grant number 2021SGR01197], and the Czech Science Foundation [grant number 22-15684L]., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

How compound flood drivers have changed over time in the Catalan coast (NW Mediterranean)

  • Aguilera Vidal, Maria
  • Sanuy Vázquez, Marc
  • Ortego Martínez, María Isabel
  • Jiménez Quintana, José Antonio
This study examines multi-decadal changes in rainfall and wave interactions driving compound flooding along the Catalan coast (NW Mediterranean) from 1950 to 2022. While growing attention has been given to the increasing impacts of coastal storms in the Mediterranean, this work examines whether such changes are linked to variations in the intensity, frequency, or dependence of the underlying hazard drivers. Results show marked temporal and spatial shifts in the dependence structure between rainfall and waves. Initially near-independent, several basins exhibit a progressive strengthening of dependence and upper-tail coupling, indicating growing synchronization between heavy rainfall and energetic wave events, together with an increased probability of extreme rainfall in northern Catalonia. The frequency of extreme compound events has increased in accordance with the strength of dependence. Northern basins exhibit the highest joint probabilities and annual occurrences, while southern basins remain less affected. Synoptic-scale analyses link these trends to a decline in Atlantic Lows and a concurrent rise in Mediterranean Lows and Cut-Off systems, atmospheric configurations conducive to concurrent heavy rainfall and high waves. The observed north-south gradient in compound hazard can be partly explained by the preferential storm tracks affecting the NW Mediterranean. Cyclonic systems typically develop or intensify in the Gulf of Lion and propagate southeastward, generating strong northeasterly winds and intense precipitation along the northern Catalan coast. The results suggest a potential intensification of compound coastal hazards in northern Catalonia and the need to incorporate evolving driver dependence into coastal risk assessment and climate adaptation strategies., The authors sincerely thank AEMET for the rainfall data and Tim Toomey and Marta Marcos (Universitat de les Illes Balears, Spain) for the wave data. This work has been done within the framework of the C3RiskMed (PID 2020-113638RB-C21, AEI/10.13039/501100011033) research project funded by the Spanish Ministry of Science and Innovation. The first author benefited from a PhD grant from the Spanish Ministry of Science and Innovation. JAJ acknowledges the support of the Departament de Recerca i Universitats of the Generalitat de Catalunya (Academia d’Excel⋅l`encia award). We also acknowledge the contribution of the project PID 2021-125380OB-I00 (MCIN/AEI/10.13039/501100011033, ERDF “A way of making Europe”), in which the third co-author is involved., Peer Reviewed, 13 - Acció per al Clima, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Analysis of psychological well-being from a compositional data analysis perspective: a new approach

  • Cortés Rodriguez, María
  • Galindo Villardón, Purificación
  • Sánchez Barba, Mercedes
  • Jarauta Bragulat, Eusebio
  • Urchaga Litago, José David
Well-being is a widely studied construct in psychology. In 1989, Carol Ryff proposed the “Scale of Psychological Well-Being (SPWB)”, which has been validated in multiple languages. The instrument assesses six dimensions of psychological well-being: Self-acceptance, Positive Relationships with Others, Autonomy, Environmental Mastery, Purpose in Life, and Personal Growth. In this article, we propose to enrich the traditional approach of directly interpreting the raw scores in each dimension by incorporating Compositional Data Analysis. This new approach aims to identify “what proportion” of each dimension constitutes well-being, which will allow us to analyze the interactions between the different dimensions of well-being and balance among them. To achieve this, we introduce two position ratios (PR1 and PR2) and a general adjustment indicator called the General Indicator of Subjective Psychological Well-Being (GISPW), which characterizes individuals in a compositional manner, providing a fresh perspective in the interpretation of psychological test results, specifically those related to PWB. The proposal is illustrated with three cases taken from a study involving 628 university students who completed the psychological well-being scale questionnaire. The results show that the GISPW, PR1, and PR2 obtained offer relevant information about the overall balance of each case in the different dimensions., This publication is part of the project PID2021-125380OB-I00, funded by MCIN/AEI/ 10.13039/501100011033 and by “ERDF A way of making Europe”., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Improved approximation and visualization of the correlation matrix

  • Graffelman, Jan
  • De Leeuw, Jan
This is an Accepted Manuscript of an article published by Taylor & Francis Group in American statistician on 11/04/2023, available online at: http://www.tandfonline.com/10.1080/00031305.2023.2186952, The graphical representation of the correlation matrix by means of different multivariate statistical methods is reviewed, a comparison of the different procedures is presentedwith the use of an example dataset, and an improved representation with better fit is proposed. Principal component analysis is widely used for making pictures of correlation structure, though as shown a weighted alternating least squares approach that avoids the fitting of the diagonal of the correlation matrix outperforms both principal component analysis and principal factor analysis in approximating a correlation matrix. Weighted alternating least squares is a very strong competitor for principal component analysis, in particular if the correlation matrix is the focus of the study, because it improves the representation of the correlation matrix, often at the expense of only aminor percentage of explained variance for the original data matrix, if the latter is mapped onto the correlation biplot by regression. In this article, we propose to combine weighted alternating least squares with an additive adjustment of the correlation matrix, and this is seen to lead to further improved approximation of the correlation matrix., This work was supported by the Spanish Ministry of Science and Innovation and the European Regional Development Fund under grant PID2021- 125380OB-I00 (MCIN/AEI/FEDER); and the National Institutes of Health under Grant GM075091., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Mapping life expectancy loss in Barcelona in 2020

  • Puig Oriol, Xavier
  • Ginebra Molins, Josep
© 2023 The Author(s). Published with license by Taylor & Francis Group, LLC., We use a Bayesian spatio-temporal model, first to smooth small-area initial life expectancy estimates inBarcelona for 2020, and second to predict what small-area life expectancy would have been in 2020 inabsence of covid-19 using mortality data from 2007 to 2019. This allows us to estimate and map the small-area life expectancy loss, which can be used to assess how the impact of covid-19 varies spatially, and toexplore whether that loss relates to underlying factors, such as population density, educational level, orproportion of older individuals living alone. We find that the small-area life expectancy loss for men and forwomen have similar distributions, and are spatially uncorrelated but positively correlated with populationdensity and among themselves. On average, we estimate that the life expectancy loss in Barcelona in 2020 was of 2.01 years for men, falling back to 2011 levels, and of 2.11 years for women, falling back to 2006 levels., This work was supported by the grant PID2021-125380OB-I00 funded by MCIN/AEI/10.13039/501100011033 and by ERDF A way of making Europe., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Biplots for the correlation matrix

  • Graffelman, Jan
The visualization of the correlation matrix by means of biplots is considered. The classical centering operations, either by the overallmean, the column means, or rowand column means are shown to be problematic for the visualization of the correlation matrix, and sub-optimal in terms of goodness-of-fit. More flexible adjustments are possible by using a single scalar adjustment, a set of column scalars or both row–and–column scalars using a weighted alternating least squares algorithm. Recently, correlation biplots with a single scalar adjustment have been advocated and outperform the usual correlation biplots made by principal component analysis. This article presents an iterative algorithm for a column adjustment of the correlation matrix with the goal of improving the goodness-of-fit over the use of a single scalar adjustment and studies its usefulness in practical data analysis. The resulting biplots are harder to read but can be made more interpretable by using correlation tally sticks. Correlation tally sticks are advocated for improving the visualization of correlation structure. The weighted root mean squared error is used to compare lowdimensional approximations to the correlation matrix across methods., This work was supported by the Spanish Ministry of Science and Innovationand the European Regional Development Fund under grant PID2021-125380OB-I00 (MCIN/AEI/FEDER); and the National Institutes of Healthunder Grant GM075091., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Subcompositional coherence and a novel proportionality index of parts

  • Egozcue Rubí, Juan José
  • Pawlowsky Glahn, Vera
Research in compositional data analysis was motivated by spurious (Pearson) correlation. Spurious results are due to semantic incoherence, but the question of ways to relate parts in a statistically consistent way remains open. To solve this problem we frst defne a coherent system of functions with respect to a subcomposition and analyze the space of parts. This leads to understanding why measures like covariance and correlation depend on the subcomposition considered, while measures like the distance between parts are independent of the same. It allows the defnition of a novel index of proportionality between parts., Grants PID2021-125380OB-I00 and PID2021-123833OB-I00 funded by MCIN/AEI/ 10.13039/501100011033 and by ERDF A way of making Europe. The authors also thank the two anonymous reviewers for their detailed and constructive review of the manuscript., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Rainfall and wave storms interdependence in the western Spanish Mediterranean coast

  • Aguilera Vidal, Maria
  • Sanuy Vázquez, Marc
  • Ortego Martínez, María Isabel
  • Jiménez Quintana, José Antonio
We characterise the dominant main terrestrial and marine drivers of compound floodevents in the study region. Due to the prevalence of ephemeral rivers, rainfall represents theterrestrial driver, while waves, more influential than storm surges, represent the marinecomponent. We analyse the frequency, intensity, and interdependence of compound events toidentify spatial patterns across the study area. Conditional exceedance analysis estimates prob-abilities and determines likely driver combinations during multivariate events.New hydrological insights for the region: Significant regional variability exists in compound floodevent drivers. Key hotspots in northern Catalonia and central Valencia are driven by overlappingrainfall and wave patterns. Compound extreme events are around 8–10 % more intense thansingle-driver events. Seasonal patterns revealed that compound extreme events are rare in sum-mer but more frequent in autumn, winter, and spring, with the strongest wave–rainfall correlationoccurring at zero lag time. Areas with stronger statistical dependencies between drivers experi-enced a higher frequency of compound extreme events. We identified the most likely combina-tions of event types associated with various joint return periods. The analysis reveals notableregional variations, with some areas predominantly affected by a single extreme driver, typicallywave storms, and others equally influenced by both wave and rainfall storms. These findingsemphasize the need to incorporate multivariate dependencies and spatial heterogeneity intoregional flood risk assessments., This study was accomplished within the framework of the C3RiskMed research project (PID2020-113638RB-C21, AEI/10.13039/ 501100011033) funded by the Spanish Ministry of Science and Innovation. The first author benefited from a PhD grant from the Spanish Ministry of Science and Innovation (PRE2021-100813). The work of MIO was done in the framework of the projects PID2021-125380OB-I00 (MICIU/AEI/10.13039/501100011033/FEDER, UE), and 2021SGR01197 (Departament de Recerca i Universitats de la Generalitat de Catalunya)., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Estimation of Jacquard’s genetic identity coefficients with bi-allelic variants by constrained least-squares

  • Graffelman, Jan
  • Weir, Bruce S.
  • Goudet, Jérôme
The Jacquard genetic identity coefficients are of fundamental importance in relatedness research. We address the estimation of these coefficients as well as other relationship parameters that derive from them such as kinship and inbreeding coefficients using a concise matrix framework. Estimation of the Jacquard coefficients via likelihood methods and the expectation–maximization algorithm is computationally very demanding for large numbers of polymorphisms. We propose a constrained least squares approach to estimate the Jacquard coefficients. A simulation study shows constrained least squares achieves root-mean-squared errors that are comparable with those of the maximum likelihood approach, in particular when founder allele frequencies are unknown, while obtaining enormous computational savings., This work was supported by the Spanish Ministry of Science and Innovation and the European Regional Development Fund under grant PID2021-125380OB-I00 (MCIN/ AEI/FEDER); by the Swiss National Science Foundation under grants 31003A_179358 and 310030_215709; and by the National Institutes of Health under Grant GM075091. Wethank the Editor and three anonymous reviewers for their comments, which have helped us to improve the manuscript., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

A mixture model application in monitoring error message rates for a distributed industrial fleet

  • Plandolit López, Bernat
  • Puig de Dou, Ignacio
  • Costigan, Gráinne
  • Puig Oriol, Xavier
  • Rodero de Lamo, Lourdes
  • Martínez Martínez, José Miguel
This is an Accepted Manuscript of an article published by Taylor & Francis Group in Quality engineering on 2023, available online at: http://www.tandfonline.com/https://www.tandfonline.com/doi/full/10.1080/08982112.2022.2132866, Remotely monitoring industrial printers for an unexpected increase of warning and error messages reduces equipment downtime and increases customer satisfaction. Directly tracking raw error messages rates during a given observation period poses some issues. Firstly, when a printer has not been used much during the observation period, its actual printing time is low. In this situation, even a small set of error messages can become an unexpectedly large rate of messages per printing hour. Secondly, classifying printers in error messages groups based on their rate (for instance, low, medium and high) and studying group changes over time, is useful in identifying potential problems. To overcome these issues, a nonparametric estimation method which simultaneously obtains empirical Bayes estimations of error messages rates and the number of error messages groups is used. This approach has been used in epidemiology, mainly in disease mapping research, but not in an industrial reliability context. The objective of our work is to show the application of the mixture model to real-time monitoring of printers’ error message rates in a way that addresses the two issues mentioned above., This work was partly supported by the Spanish Ministry of Science and Innovation and the European Regional Development Fund (grant number PID2021-125380OB-I00 (MCINN/AEI/FEDER))., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Insights in hierarchical clustering of variables for compositional data

  • Martín Fernández, Josep Antoni
  • Di Donato, Valentino
  • Pawlowsky Glahn, Vera
  • Egozcue Rubí, Juan José
R-mode hierarchical clustering is a method for forming hierarchical groups of mutually exclusive subsets of variables. This R-mode cluster method identifies interrelationships between variables which are useful for variable selection and dimension reduction. Importantly, the method is based on metric elements defined on the sample space of variables. Consequently, hierarchical clustering of compositional parts should respect the particular geometry of the simplex. In this work, the connections between concepts such as distance, cluster representative, compositional biplot, and log-ratio basis are explored within the framework of the most popular R-mode agglomerative hierarchical clustering methods. The approach is illustrated in a paleoecological study to identify groups of species sharing similar behavior., This research was supported by the Ministerio de Ciencia e Innovación under the projects CODA-GENERA (Ref. PID2021-123833OB-I00) and CONBACO (Ref. PID2021-125380OBI00); and by the Agència de Gestió d’Ajuts Universitaris i de Recerca of the Generalitat de Catalunya under the project COSDA (Ref. 2021SGR01197)., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Assessing the impact on sales of competing nearby supermarkets

  • González Ibáñez, Daniel
  • Puig Oriol, Xavier
The supermarket industry faces fierce competition in many geographic areas, with various brands competing for a market share that represents a significant portion of a country's GDP. For these businesses, understanding the factors that influence their sales and how they do so is crucial: location, pricing, quality, customer loyalty, and more. While much has been written about how these elements can affect revenue, there is a lack of existing models quantifying the monetary impact of having competitor stores within an own establishment area of influence. This article introduces a hierarchical Bayesian model that quantifies this impact for each product category within the brand's catalog. The model requires careful parameterization to adapt to the specific context, and therefore both its application and design represent a methodological novelty in this area. The main result is a matrix of coefficients that indicate the monetary effect of the presence of every competitor for each product category. The findings revealed by the model show that the influence of the proximity of each competitor does indeed vary depending on these categories. This information is valuable for the company when making decisions, such as choosing new store locations or determining the product assortment to offer in each establishment. The use of the results derived from this model provides a competitive advantage over others and helps to better understand the market by identifying which supermarket brands are the perceived leaders in each product category., This work was supported by the grant PID2021-125380OB-I00 funded by ERDF A way of making Europe, MCIN/AEI/ 10.13039/501100011033, and Agencia Estatal de Investigación., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Disease mapping with individual level information; a case study of acute myocardial infarction mortality

  • Puig Oriol, Xavier
  • Ginebra Molins, Josep
© 2025 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY-NC license, When mapping relative mortality risk under specific causes of death in time, one can use small areas and single year mortality data to explore the space time variation in detail. To reduce the variability of the initial mortality risk estimates and help explain their differences, hierarchical Poisson models are typically used. Here we deal with the situation where besides aggregated small-area level data necessary for that, one also has complete individual level data about the presence of certain risk factors in the population, which is now rare but it should become routine in places with universal health coverage using a medical record sharing system. In particular, we consider the convenience of including individual level covariates in the models, and mapping relative mortality risk adjusted for them. That is illustrated by exploring how mortality due to acute myocardial infarction varies in space and in time in Catalonia between 2014 and 2019 using individual data on obesity, diabetes, dyslipidemia and smoking habits., APC - EIO (Josep Ginebra), Peer Reviewed, Postprint (published version)