Stipendiary Lecturer in Probability & Statistics

Daniel Moss

  • I work on the interface between probability and statistics, developing new theoretical results for Bayesian nonparametric statistical procedures
  • I love teaching at Oxford as it gives me the opportunity to share my passion for the subject with bright and enthusiastic students and help them to push the boundaries of their mathematical knowledge and abilities
  • My current research examines so-called ‘cut posterior’ approaches, which modifies the usual Bayesian posterior with the hope of allowing for more robust and theoretically sound inference

Profile

Currently I am a doctoral student in the Department of Statistics associated with the EPSRC CDT in Modern Statistics and Statistical Machine Learning. Prior to this I spent four wonderful and enriching years studying mathematics at Cambridge, where I first encountered statistics in the wonderful lectures of Prof. David Spiegelhalter in my second year. My interest drifted between probability, statistics and pure mathematics throughout my undergraduate studies, before I had the opportunity to unite these interests in the study of statistical theory.

Teaching

At Trinity college, I teach the probability and statistics courses to students in their first and second years. Within the Department of Statistics, I also teach intercollegiate classes for the third year “Foundations of Statistical Inference” course.

Research

My research up to this point has focused on developing theoretically sound Bayesian estimation procedures in hidden Markov models, which are a flexible class of models which have wide ranging applications from finance to genomics. Recently I have become interested in (pseudo-)Bayesian procedures for causal inference.

Please visit my website here for more information.

Subjects
Daniel Moss
daniel.moss@spc.ox.ac.uk

Research in statistical theory allows us to study the fascinating, mathematically rich topics of probability and analysis in the context of a rapidly expanding field with far-reaching applications.