Collaborative Research Team Project #19

Improving Robust High-Dimensional Causal Inference and Prediction Modelling

This project explores methods to improve high-dimensional causal inference and prediction modelling in biomedical sciences. 

Research Category: Health & Biology

Why Study Complex Data in Precision Medicine?

Recent advances in “-omics” technologies are allowing scientists to simultaneously collect large amounts of clinical data. This is revolutionizing the way we can measure pathogenic processes or responses to therapies. 

This high-dimensional data has the potential to improve disease prevention and diagnosis. However, it presents significant challenges due to measurement errors, outliers, multivariate responses, and complex correlation structures.

Advancements in this area are essential for building useful models in precision medicine.

Areas of Exploration

Advanced Regularized Regression

Includes reducing variance and decreasing sample errors in biometric data.

Regularized Instrumental Variables

Includes correcting for measurement errors in biometric data.

Matrix-Valued Causal Models

Includes the development of causal models in high-dimensional settings.

Solving Global Challenges

Research Team’s Goal

To develop an advanced analytical framework for managing complex data in biomedical sciences.

People Behind the Project

Project Team

Gabriela Cohen-Freue | University of British Columbia

Celia Greenwood | Lady Davis Institute for Medical Research, McGill University


Sahir Bhatnagar | McGill University

Tom Blydt-Hansen | University of British Columbia

Dehan Kong | University of Toronto

Karim Oualkacha | Université du Québec à Montréal

Brent Richards | McGill University

David Soave | Laurier University

Linbo Wang | University of Toronto

Zhaolei Zhang | University of Toronto


Improving Robust High-Dimensional Causal Inference and Prediction Modelling is a Collaborative Research Team project. This program tackles complex problems through a three-year research and training agenda.

CANSSI offers approximately $200,000 for this type of project, which requires a team of faculty, postdocs, and students.