Dr Robert Goudie
(he/him/his)About Dr Robert Goudie
I am a Group Leader at the MRC Biostatistics Unit, working on data integration and analysis of hospital record data.
Research Interests
- Analysis of hospital electronic health record data, particularly from eHospital (Epic) at Cambridge University Hospitals
- Simplifying Bayesian model building for complex systems using Markov melding
- Methods for modularisation of Bayesian models with cut distributions
- Compositional and modular methods for probabilistic programming languages, as part of the Turing’s Fundamental AI programme
- Methods for making prior specification more practical
- Bayesian methods for weighted data
- Bayesian longitudinal correlated factor analysis with dependent Gaussian processes
- Parallelisation of the general purpose Bayesian software MultiBUGS
Some of my software is on Github.
Current Group Members
Research Associates:
- Rebecca Brock
- Yixuan Liu
PhD students:
- Matilda Pitt
- Shizhe Li
- Craig Dunipace
Teaching
- MPhil Population Health Sciences – Bayesian statistics
Committees
- University Research Ethics Committee
- MRC Biostatistics Unit Graduate Education Committee
Publications
Showing 1 to 10 of 40 publications
EnRICH: an integrated geriatrician-led Interface model associated with reduced emergency admissions among care home residents.
Authors: C Love, MJ Butler, S D'Souza, A Rose, J Di Gesso, J Ford, L Van Der Poel, R Simpson, J Hampton, RWS Biram, SA Hopkins, RJB Goudie, RH Harwood
Published:
Journal: Age Ageing
DOI: 10.1093/ageing/afag195
Chained Markov melding using divide and conquer sequential Monte Carlo
Authors: Y Liu, RJB Goudie
Published:
DOI: 10.48550/arxiv.2605.22301
Translating Predictive Distributions into Informative Priors
Authors: AA Manderson, RJB Goudie
Published:
Journal: Journal of the American Statistical Association
DOI: 10.1080/01621459.2026.2614034
A Bayesian Prevalence Incidence Cure model for estimating survival using Electronic Health Records with incomplete baseline diagnoses
Authors: M Pitt, RJB Goudie
Published:
DOI: 10.48550/arxiv.2602.00291
A general framework for cutting feedback within modularized Bayesian inference
Authors: Y Liu, RJB Goudie
Published:
Journal: Journal of the Royal Statistical Society Series B Statistical Methodology
DOI: 10.1093/jrsssb/qkaf012
Validation of PREdiction of DELIRium in ICu patients (PRE-DELIRIC) model for ICU delirium in general ICU and patients with liver disease: a retrospective cohort study.
Authors: A Papadopoulou, SL Cowan, J Preller, RJB Goudie
Published:
Journal: J Intensive Care
DOI: 10.1186/s40560-025-00800-3
Translating predictive distributions into informative priors
Authors: AA Manderson, RJB Goudie
Published:
DOI: 10.48550/arxiv.2303.08528
A General Framework for Cutting Feedback within Modularised Bayesian Inference
Authors: Y Liu, RJB Goudie
Published:
DOI: 10.48550/arxiv.2211.03274
Prevalence of venous thromboembolism in patients undergoing diagnostic venous ultrasound during the first SARS-CoV-2 pandemic.
Authors: G La Torre, R Nagra, H Wijesinghe, G Rajeswaran, J Riya, S Abdulkhaliq, T Barker, A Ganeshan, R Goudie, N Hosaam, A Tiwari, MT Juszczak
Journal: Vasa
DOI: 10.1024/0301-1526/a001052
Generalized Geographically Weighted Regression Model within a Modularized Bayesian Framework.
Authors: Y Liu, RJB Goudie
Published:
Journal: Bayesian Anal
DOI: 10.1214/22-BA1357