Professor Mark Strong BSc MB ChB MPH MSc PhD MRCPCH MFPH FHEA CStat
Deputy Dean of ScHARR
Professor of Public Health
Section of Public Health
School of Health and Related Research
The University of Sheffield
30 Regent Street
Sheffield S1 4DA
PA: Karen Johnson firstname.lastname@example.org
I am an academic public health doctor and a statistician, and currently Deputy Dean of ScHARR.
Check out our web-app - SAVI - Sheffield Accelerated Value of Information
This web-app lets you calculate Expected Value of (Partial) Perfect Information for any cost-effectiveness model. Just upload the probabilistic sensitivity analysis sample and the app does the rest.
SAVI is now available as an R package from GitHub. This allows users to run the SAVI app on their own machine, and removes the need to transfer any data over the net. Installation instructions are here.
For more resources that relate to Value of Information, see our Collaborative Network for Value of Information (CONVOI) website.
My Research interests
I have three related research interests that fall under the general banner of Uncertainty Quantification: (1) how do we properly account for all relevant uncertainties when we build a computer model of a physical, biological or social system? (2) how do we (efficiently) compute value of information? (3) how do we work out the value of a computer model? How much should we pay to make a simple model more complex? When do we stop increasing the complexity of a model?
Jeremy Oakley, Jim Chilcott and I have proposed an "internal" discrepancy-based method for managing model uncertainty. See this paper in JRSS Series C, and this paper in SIAM/ASA Journal of Uncertainty Quantification that develops the idea of the 'Expected Value of Model Improvement'. The method is discussed in more detail in my PhD thesis.
We have proposed an efficient method for computing partial EVPI. This method works for any number of parameters of interest and requires only the PSA sample. See this open access paper in Medical Decision Making. R functions to implement the method can be downloaded here. This paper uses Gaussian process-based methods that are nicely described in the Managing Uncertainty in Complex Models (MUCM) toolkit.
The partial EVPI method extends nicely to the computation of EVSI. See here for our open access paper on the efficient computation of EVSI.
I welcome PhD applications at any time. You are welcome to email me to discuss an idea before making an application through the ScHARR online system. I supervise students who are interested in the topics of Value of Information and Uncertainty Quantification in health economic decision making.
I teach on the Master in Public Health and undergraduate medical MB ChB degrees, and offer MFPH exam support to the Yorkshire and Humber public health training scheme.
I am an honorary clinical consultant in public health at Public Health England.
I am an Associate Editor at Medical Decision Making.
Current and recent projects
- Calibrated Agent Simulations for Combined Analysis of Drinking Etiologies (CASCADE): A US National Institutes of Health funded project on alcohol consumption (2016-2021). PI - Robin Purshouse.
- Systems Science in Public Health and Health Economic Research (SIPHER): A major UK Prevention Research Partnership funded project that will generate evidence for healthy public policy through a systems-science approach (2019-2024). PI - Petra Meier.
- Strong M, Oakley JE, Brennan A, Breeze P. Estimating the Expected Value of Sample Information using the Probabilistic Sensitivity Analysis Sample. A Fast Non-Parametric Regression Based Method. Medical Decision Making. 2015;35(5):570-583 Open Access. doi: http://dx.doi.org/10.1177/0272989X15575286
- Strong M, Oakley JE. When is a model good enough? Deriving the expected value of model improvement via specifying internal model discrepancies. SIAM/ASA Journal on Uncertainty Quantification. 2014;2(1):106-125. Open Access. doi: http://dx.doi.org/10.1137/120889563
- Strong M, Oakley JE, Brennan A. Estimating multi-parameter partial Expected Value of Perfect Information from a probabilistic sensitivity analysis sample: a non-parametric regression approach. Medical Decision Making. 2014;34(3):311-26. Open Access. doi: http://dx.doi.org/10.1177/0272989X13505910 R code here.
- Strong M, Oakley JE, Chilcott, J. Managing structural uncertainty in health economic decision models: a discrepancy approach. Journal of the Royal Statistical Society, Series C. 2012;61(1):25-45. doi: http://dx.doi.org/10.1111/j.1467-9876.2011.01014.x Preprint here.
- Strong M, Oakley JE. Bayesian inference for comorbid disease risks using marginal disease risks and correlation information from a separate source. Medical Decision Making 2011;31(4):571-581. Preprint here.