I am a research fellow specialised in causal inference from complex observational data. I received my M.Sc. in Statistics from Université de Montréal in 2020 and my Ph.D. in Biostatistics from McGill University in 2024. 

My research involves developing causal inference methods in settings of dependence, including social network data, where we can expect treatments assigned to individuals to disseminate along the edges of the graph. Causal inference from observational social network data is rife with challenges, as these data are prone to unmeasured network confounding, interference, and contagion. More recently, I have been interested in the problem of disentangling effects due to influence and selection in the presence of homophily confounding, and performing causal inferences on dynamic networks. 

A closely related area of research is learning from data obtained from respondent-driven sampling (RDS), a chain-referral method for sampling members of hard-to-reach populations. With collaborators from the Engage study, I have also been studying ways to perform valid inference from RDS cohort studies leveraging weighting techniques from the survey sampling and causal inference literatures. As a statistician, I have also contributed to projects in cardiometabolic health in pediatric populations and plant science.

• Causal inference
• Network interference
• Social network analysis
• Semi-parametric estimation
• Robustness
• Unmeasured confounding
• Latent space models
• Spatio-temporal modelling
• Hierarchical modelling
• Bayesian inference

Research groups

• Statistics & data analytics
• Bayesian modelling & inference
• Computational statistics
• Nonparametric & semi-parametric statistics
• Biostatistics, epidemiology, & health applications

List by: Type | Date

• Sasibala Senthil Raja, Meyvizhi
  Developing novel ways to represent spatial patterns in disease risk