Welcome!

Marta Bofill Roig

Marta Bofill Roig

Serra Húnter Fellow

Universitat Politècnica de Catalunya

I am a Serra Húnter Fellow (tenure-track lecturer) at the Department of Statistics and Operations Research of the Universitat Politècnica de Catalunya - BarcelonaTech (UPC), and a member of the research group GRBIO. My research focuses on methods and software for clinical trials with multiple endpoints and adaptive platform trials.

Interests
  • Clinical trials
  • Adaptive designs
  • Survival analysis
  • Platform trials
Education

  • PhD in Statistics and Operations Research, 2020

    Universitat Politècnica de Catalunya

  • MSc in Statistics and Operations Research, 2016

    Universitat Politècnica de Catalunya and Universitat de Barcelona

  • BSc in Mathematics, 2014

    Universitat de Barcelona

Recent Publications

Discover all methodological publications by filtering publications. For a full list of publications, see CV.
Treatment-control comparisons in platform trials including non-concurrent controls
Marta Bofill Roig, Pavla Krotka, Katharina Hees, Franz Koenig, Dominic Magirr, Peter Jacko, Tom Parke, Martin Posch
Preprint PDF Code
Design of Trials with Composite Endpoints with the R Package CompAREdesign
Jordi Cortes-Martinez, Marta Bofill Roig, Guadalupe Gómez Melis
Preprint Code
The Online Closure Principle
Lasse Fischer, Marta Bofill Roig, Werner Brannath
Preprint PDF Code
Statistical modeling to adjust for time trends in adaptive platform trials utilizing non-concurrent controls
Pavla Krotka, Martin Posch, Mohamed Gewily, Günter Höglinger, Marta Bofill Roig
Preprint Code
An exhaustive ADDIS principle for online FWER control
Lasse Fischer, Marta Bofill Roig, Werner Brannath
Preprint PDF Code
See all publications

Software

R packages & Shiny apps

Discover the R code of the papers in Publications list. More repositories on GitHub.

R packages:

  • CompARE: Sample size and effect size calculation for composite endpoints. [GitHub] [CRAN] [website] [Shiny-app]

  • NCC: Design and analysis of platform trials with non-concurrent controls. (Maintainer: Pavla Krotka). [GitHub] [CRAN] [website] [Slides]

  • survmixer: Design of clinical trials with survival endpoints based on binary response. [GitHub] [CRAN] [website]

  • eselect: R package for adaptive trial designs with endpoint selection and sample size reassessment. [GitHub] [CRAN]

  • Survbin: Two-sample statistics for binary and time-to-event outcomes. [GitHub] [website]

Fun stuff:

Talks

And other materials

Talks:

Slides on Maximizing efficiency in platform trials with shared controls: Optimal allocation strategies and non-concurrent controls (Vigo, 2023).

Slides on Adaptive selection of composite endpoints and sample size reassessment based on blinded data (Basel, 2023).

Slides on Model-based time trend adjustments in platform trials with non-concurrent controls (Online, 2021).

Teaching:

Slides and R labs from the short course on Statistical Inference. [GitHub]

Thesis:

My thesis dissertation is available on Zenodo.

Projects

Research projects & working groups

ADMTP

ADMTP

Adaptive Designs and Multiple Testing Procedures Working Group

CompARE

CompARE

Working group on the design of clinical trials with composite endpoints

EU-PEARL

EU-PEARL

EU-PEARL aims to create a tested and trusted framework for patient-centric integrated research platform trials

eWHORM

eWHORM

eWHORM Project to Eliminate Worm Infections in Sub-Saharan Africa. eWHORM aims to develope and test more efficacious and safe treatment options that act across different helminth species

GRBIO

GRBIO

Research group with an expertise in Biostatistics and Bioinformatics

NCC

NCC

Working group on software for platform trials using non-concurrent control data

Outreach

Dissemination:

Tweetorial on the Shiny-app CompARE by Jordi Cortés

Tweetorial on Model-based time trend adjustments in platform trials with non-concurrent controls by Kert Viele

EU-PEARL Interview

Outreach:

Video on survival analysis. See Youtube channel Llampecs de Ciència.

Poster on multi-state models for Science Week 2020. [Zenodo]

Contact