About Me

About Me

My postdoctoral research focuses on areas of causal inference related to respondent-driven sampling (RDS). RDS is a survey sampling technique employed to study hard-to-reach population. The sample is formed by starting from identified members of the target population, and using their personal networks to recruit further members of the target population in a way that is probabalistically motivated. There exists comparatively little methodology for analyzing data from RDS, though this form of data collection is becoming increasingly common. My postdoctoral research looks to expand on this existing work, moving beyond the estimation of means and proportions, allowing for associational and causal modelling that is expected when employing other methods of sampling. Moreover, my work seeks to expand these techniques to longitudinal RDS data, a question which has to date received no research attention.

Alongside these questions, I will continue to pursue methodologies related to dynamic treatment regimes, the core topic studied during my graduate schooling. During my graduate studies, my research focused on measurement error and causal inference. Briefly, measurement error occurs whenever we are interested in measuring something and we do a bad job of it. This happens in almost every study that is run, and unfortunately means that the conclusions that we draw may not be accurate: statistical work on measurement error tries to correct this. Causal inference asks questions of the form “Does X cause Y?” [For instance “Does smoking cause lung cancer?” (yes, it does).] I have a keen interest in providing a theoretical basis for (comparatively) straightforward methods, which are easy to use for non-statisticians, while exhibiting provably good theoretical properties.

Outside of causal inference and measurement error, I am interested in machine learning, and in particular in trying to establish a statistical basis for novel machine learning techniques (including questions related to inference, interpretability, and model selection).

I previously did an undergraduate degree in Finance and Mathematics at Queen’s University (I transferred there after completing my first year at Waterloo/Laurier in the ‘Double Degree’ program), and a Master’s of Statistics at Waterloo.

Outside of my research, I pay very close attention to sports, mostly hockey, (and how statistics is, or should be, applied there), play music (without any connection to statistics), and enjoy board/video games (with varying degrees of statistical relevance). I have a cat (Charles) who is wonderful.

My Teaching

  • In the Winter of 2022 I taught STAT 437 at the University of Waterloo. The course was offered online, and the material is available on my website.
  • In the Winter of 2021 I was one of the instructors for STAT 231 at the University of Waterloo. As a part of my role for this I produced a set of weekly tutorial videos. These are available to view in a YouTube playlist.
  • I have served as a teaching assistant for 18 courses between my time at the University of Waterloo and Queen’s University. A full list is available in my CV.

Contacting Me

  • Email: See my departmental website.
  • Twitter: @DylanSpicker. (As of November 2021, I am incredibly inactive).
  • LinkedIn: In case anyone is still using this.