Supervision

Instructions to Apply:

Graduate students in statistics, biostatistics, epidemiology, economics or computer science with somewhat strong methodological expertise in statistics (as well as statistical computing) are encouraged to contact me directly; particularly those with some of the following skills: 
  • making data requests, 
  • extracting analytic data from administrative (e.g., health admin) and survey databases (e.g., DHS, NHANES, BRFSS or CCHS), 
  • running statistical analyses using standard software (e.g., SAS, R or python), 
  • coding statistical estimators (via SAS macro/IML, R or stata mata), 
  • conducting simulation studies (e.g., in servers / parallel computing), 
  • excellent scientific writing (e.g., demonstrated via peer-reviewed publications), 
  • ability to work on a multidisciplinary team (e.g., work within biostatistics groups). 
Interested candidates should email me (at my UBC email address) the following: 
  1. cover letter, mentioning whether you are interested in an MSc or a PhD program, why you want to work with me,
  2. a complete CV (including publication & award list, if any), 
  3. copy of the unofficial transcripts (post-secondary), and 
  4. list of research / work experiences in healthcare related settings (if any)
  5. Names of 2 referees (with official email addresses).
  6. If you are coming from an institution where English is not used as the first language, please also include your TOEFL (iBT), IELTS or equivalent scores in your CV. Please check out these websites for MSc and PhD requirements for SPPH, UBC (see under 'Requirements' section). Note that the requirements vary by department (e.g., check for Statistics).
Please check out my G+PS profile for my research interests, as well as my previous publications
Only shortlisted candidates will be contacted

Available to supervise on the following projects:
I am currently looking for multiple graduate students (current and prospective) for the following projects (with methodologic focuses within epidemiologic contexts):
  • Improving Causal Inference Methods in Statistics for Analyzing High-dimensional / Big Data. See publication from a related project here:
Related project

  • Developing and Evaluating Causal Inference Methods for Pragmatic Trials to address nonadherence. See a brief introduction to some of the basic ideas in the following video:

Causal inference in pragmatic trials

MS

  • Applying Machine Learning Methods in Mediation Analysis for Extracting Causal Explanations from Large Healthcare Databases. See one of our previous applications of such mediation methods. 
Mediation Analysis