Multilevel and Quasi Monte Carlo Methods for the Calculation of the Expected Value of Partial Perfect Information.
Authors
Wang, Zhenru
Giles, Michael B
Jackson, Chris H
Welton, Nicky J
Publication Date
2022-02Journal Title
Med Decis Making
ISSN
0272-989X
Publisher
SAGE Publications
Volume
42
Issue
2
Pages
168-181
Language
en
Type
Article
This Version
VoR
Metadata
Show full item recordCitation
Fang, W., Wang, Z., Giles, M. B., Jackson, C. H., Welton, N. J., Andrieu, C., & Thom, H. (2022). Multilevel and Quasi Monte Carlo Methods for the Calculation of the Expected Value of Partial Perfect Information.. Med Decis Making, 42 (2), 168-181. https://doi.org/10.1177/0272989X211026305
Abstract
The expected value of partial perfect information (EVPPI) provides an upper bound on the value of collecting further evidence on a set of inputs to a cost-effectiveness decision model. Standard Monte Carlo estimation of EVPPI is computationally expensive as it requires nested simulation. Alternatives based on regression approximations to the model have been developed but are not practicable when the number of uncertain parameters of interest is large and when parameter estimates are highly correlated. The error associated with the regression approximation is difficult to determine, while MC allows the bias and precision to be controlled. In this article, we explore the potential of quasi Monte Carlo (QMC) and multilevel Monte Carlo (MLMC) estimation to reduce the computational cost of estimating EVPPI by reducing the variance compared with MC while preserving accuracy. We also develop methods to apply QMC and MLMC to EVPPI, addressing particular challenges that arise where Markov chain Monte Carlo (MCMC) has been used to estimate input parameter distributions. We illustrate the methods using 2 examples: a simplified decision tree model for treatments for depression and a complex Markov model for treatments to prevent stroke in atrial fibrillation, both of which use MCMC inputs. We compare the performance of QMC and MLMC with MC and the approximation techniques of generalized additive model (GAM) regression, Gaussian process (GP) regression, and integrated nested Laplace approximations (INLA-GP). We found QMC and MLMC to offer substantial computational savings when parameter sets are large and correlated and when the EVPPI is large. We also found that GP and INLA-GP were biased in those situations, whereas GAM cannot estimate EVPPI for large parameter sets.
Keywords
Original Research Articles, expected value of partial perfect information, nested expectations, multilevel Monte Carlo, quasi Monte Carlo
Sponsorship
Engineering and Physical Sciences Research Council (EP/R018561/1)
EPSRC (EP/P020720/2)
Identifiers
10.1177_0272989x211026305
External DOI: https://doi.org/10.1177/0272989X211026305
This record's URL: https://www.repository.cam.ac.uk/handle/1810/333207
Rights
Licence:
https://creativecommons.org/licenses/by/4.0/
Statistics
Total file downloads (since January 2020). For more information on metrics see the
IRUS guide.