Resolution XXIII Student contest of Applied Statistics
Of the finalist projects presented at the XXIII Student contest of Applied Statistics:
- add2compareGroups. Ampliació del paquet de R compareGroups
- Análisis comparativo de las características determinantes de los precios de venta y alquiler y su impacto en la rentabilidad inmobiliaria en Barcelona
- Arquitectures socials del temps: Anàlisi de l’associació entre factors socioeconòmics i l’ús del temps
- DISTANCE-BASED DIMENSIONALITY REDUCTION FOR BIG DATA
- Extension and implementation of bootstrap-based approaches for inference on the total deviation index
- Gender-based violence across seven countries: A Machine Learning approach
- Log-Concavitat. Aplicacions en Real-Time Computing
- Optimizing dynamic predictions from joint models for multivariate longitudinal and time-to-event data via super learning approach
- The Impact of Formations on Football Matches Using Double Machine Learning
Jury members of the XXIII Student contest of Applied Statistics, have decided to award the Idescat prize at the best master paper to:
Anna Felip Badia
Student of the Màster Universitari en Estadística i Investigació Operativa.
Universitat Politècnica de Catalunya
For the paper entitled:
Extension and implementation of bootstrap-based approaches for inference on the total deviation index
The total deviation index (TDI) is an unscaled statistical measure used to evaluate the deviation between paired quantitative measurements when assessing agreement between different raters. It describes a boundary such that a large specified proportion of the differences in paired-measurements are within the boundary. The inference of the TDI involves the estimation of a 100(1 − α)% upper bound, where α is the significance level. Already existing methodologies for TDI estimation and inference include both parametric (Choudhary, Escaramís et al.) and non-parametric approaches (Choudhary, Perez-Jaume and Carrasco). In this work, the goals are to propose and evaluate new bootstrap-based approaches for inference on the TDI in the method of Perez-Jaume and Carrasco and to implement the existing and new methodologies in an R package. We apply all methodologies to a real-world dataset and we also conduct a simulation study to assess their performance. We conclude that, under skewed data, agreement should be assessed via the non-parametric methods.
Àlex Costa presenting the certificate to Anna Feliu, winner of the IDESCAT prize for the master’s thesis
Jury members of the XXIII Student contest of Applied Statistics, have decided to award the Almirall prize to the best biostatistic paper to:
Arnau Garcia Fernández
Student of the Màster Universitari en Estadística i Investigació Operativa.
Universitat Politècnica de Catalunya
For the paper entitled:
Optimizing dynamic predictions from joint models for multivariate longitudinal and time-to-event data via super learning approach
In health research, longitudinal biomarkers and time-to-event outcomes are often of interest. Joint models (JMs) have become a valuable tool for simultaneously analyzing such data and producing dynamic, individualized predictions. However, extending them to multiple longitudinal outcomes is computationally demanding due to the high number of random effects and parameters.
This work explores super learning, an ensemble method that combines several prediction algorithms to obtain an optimal forecast. Using both simulation studies and a real-world case study, we show that combining univariate JMs through super learning produces dynamic predictions comparable to those of a multivariate JM, while substantially reducing computational demands.
This work provides a replicable and methodologically rigorous framework for deriving dynamic predictions in complex settings. All simulation studies and case analyses are fully reproducible, with openly accessible code and publicly available data in R.
Daniel Peña presenting the certificate to Guadalupe Gómez, on behalf of Arnau Garcia, winner of Almirall prize for the biostatistics best paper
Jury members of the XXIII Student contest of Applied Statistics, have decided to award the SEA – Anna Espinal prize to the best degree paper to:
Andreu Arcas Martínez
Student of the Grau d’Estadística Aplicada.
Universitat Autònoma de Barcelona
For the paper entitled:
Arquitectures socials del temps
Anàlisi de l’associació entre factors socioeconòmics i l’ús del temps
L’organització del temps al llarg del dia està profundament condicionada per múltiples factors estructurals. Tot i que nombroses recerques han examinat les desigualtats en l’ús del temps per raó de gènere, són escassos els estudis que integren altres eixos d’estratificació social o que aborden l’anàlisi de l’ús del temps des d’una perspectiva seqüencial. En aquest projecte, utilitzo dades de l’American Time Use Survey (ATUS) i la Current Population Survey (CPS) de l’any 2023 per a complir un doble objectiu: d’una banda, classificar els patrons d’ús del temps en clústers mitjançant Anàlisi de Seqüències (SA) i Mixtures de Models de Màrkov Ocults (MHMM); de l’altra, emprant models multinomials, analitzar l’associació d’aquests clústers amb variables indicadores de l’estratificació social. Aquest estudi revela associacions significatives entre variables socioeconòmiques i patrons d’ús del temps i mostra així com, més enllà de l’evident rellevància del gènere, altres eixos d’estratificació social també configuren de manera significativa l’ús del temps. A més, demostra l’aplicabilitat de diverses eines estadístiques avançades per a l’anàlisi sociològica de l’ús del temps.
Anabel Blasco presenting the certificate to Toni Arcas, on the behalf of Andreu Arcas winner of the SEA – Anna Espinal prize at the best degree paper
The Servei de Consultoria Matemàtica and the Institut d’Estadística de Catalunya, wants to express his most effussive congratulations to the winners and thank the others participants for the interest and effort showed.
The awards ceremony took place on October 20, 2025, on the occasion of the XXV Dia de l’Estadística a Catalunya convened by the Societat Catalana d’Estadística and organized by the Servei de Consultoria Matemàtica de la UAB (MCS-UAB).
Awards Cerimony of the Student 2025 contest