Monte Carlo profile confidence intervals for dynamic systems - PubMed (original) (raw)
Monte Carlo profile confidence intervals for dynamic systems
E L Ionides et al. J R Soc Interface. 2017 Jul.
Abstract
Monte Carlo methods to evaluate and maximize the likelihood function enable the construction of confidence intervals and hypothesis tests, facilitating scientific investigation using models for which the likelihood function is intractable. When Monte Carlo error can be made small, by sufficiently exhaustive computation, then the standard theory and practice of likelihood-based inference applies. As datasets become larger, and models more complex, situations arise where no reasonable amount of computation can render Monte Carlo error negligible. We develop profile likelihood methodology to provide frequentist inferences that take into account Monte Carlo uncertainty. We investigate the role of this methodology in facilitating inference for computationally challenging dynamic latent variable models. We present examples arising in the study of infectious disease transmission, demonstrating our methodology for inference on nonlinear dynamic models using genetic sequence data and panel time-series data. We also discuss applicability to nonlinear time-series and spatio-temporal data.
Keywords: likelihood-based inference; panel data; phylodynamic inference; sequential Monte Carlo; spatio-temporal data; time series.
© 2017 The Author(s).
Conflict of interest statement
We declare we have no competing interests.
Figures
Figure 1.
The effect of bias on confidence intervals for a quadratic profile log-likelihood function. (a) The blue dotted quadratic represents a log-likelihood profile. The maximum-likelihood estimator of the profiled parameter is _ϕ_3, with corresponding log likelihood . The 95% CI [_ϕ_1, _ϕ_5] is constructed, via the horizontal and vertical blue dotted lines, as the set of parameter values with profile log likelihood higher than ℓ* − 1.92. The red quadratic is the sum of the blue dotted quadratic and linear bias (black dashed line). Horizontal and vertical red lines construct the resulting approximate confidence interval [_ϕ_2, _ϕ_6] and point estimate _ϕ_4. (b) The same construction, but with higher curvature of the profile log likelihood leading to diminishing effect of the bias on the confidence interval. (Online version in colour.)
Figure 2.
Profile likelihood for an infectious disease transmission parameter inferred from genetic data on pathogens. The smoothed profile likelihood and corresponding MCAP 95% CI are shown as solid red lines. The quadratic approximation in a neighbourhood of the maximum is shown as a blue dotted line. (Online version in colour.)
Figure 3.
Profile likelihood for a nonlinear partially observed Markov process model for a panel of time series of historical state-level polio incidence in the USA. The smoothed profile likelihood and corresponding MCAP 95% CI are shown as solid red lines. The quadratic approximation in a neighbourhood of the maximum is shown as a dotted blue line. (Online version in colour.)
Figure 4.
Profile construction for the toy model. The exact profile and its asymptotic 95% CI are constructed with black dashed lines. Points show Monte Carlo profile evaluations. The MCAP is constructed in solid red lines, using the default λ = 0.75 smoothing parameter. The quadratic approximation used to calculate the MCAP profile cut-off is shown as a dotted blue line. (Online version in colour.)
Similar articles
- Profile likelihood-based confidence intervals using Monte Carlo integration for population pharmacokinetic parameters.
Funatogawa T, Funatogawa I, Yafune A. Funatogawa T, et al. J Biopharm Stat. 2006;16(2):193-205. doi: 10.1080/10543400500508861. J Biopharm Stat. 2006. PMID: 16584067 - A practical guide to pseudo-marginal methods for computational inference in systems biology.
Warne DJ, Baker RE, Simpson MJ. Warne DJ, et al. J Theor Biol. 2020 Jul 7;496:110255. doi: 10.1016/j.jtbi.2020.110255. Epub 2020 Mar 26. J Theor Biol. 2020. PMID: 32223995 Review. - Data cloning: easy maximum likelihood estimation for complex ecological models using Bayesian Markov chain Monte Carlo methods.
Lele SR, Dennis B, Lutscher F. Lele SR, et al. Ecol Lett. 2007 Jul;10(7):551-63. doi: 10.1111/j.1461-0248.2007.01047.x. Ecol Lett. 2007. PMID: 17542934 - Sequential Monte Carlo without likelihoods.
Sisson SA, Fan Y, Tanaka MM. Sisson SA, et al. Proc Natl Acad Sci U S A. 2007 Feb 6;104(6):1760-5. doi: 10.1073/pnas.0607208104. Epub 2007 Jan 30. Proc Natl Acad Sci U S A. 2007. PMID: 17264216 Free PMC article. - Applications of Monte Carlo Simulation in Modelling of Biochemical Processes.
Tenekedjiev KI, Nikolova ND, Kolev K. Tenekedjiev KI, et al. In: Mode CJ, editor. Applications of Monte Carlo Methods in Biology, Medicine and Other Fields of Science [Internet]. Rijeka (HR): InTech; 2011 Feb 28. Chapter 4. In: Mode CJ, editor. Applications of Monte Carlo Methods in Biology, Medicine and Other Fields of Science [Internet]. Rijeka (HR): InTech; 2011 Feb 28. Chapter 4. PMID: 28045483 Free Books & Documents. Review.
Cited by
- Malaria treatment for prevention: a modelling study of the impact of routine case management on malaria prevalence and burden.
Camponovo F, Jeandron A, Skrip LA, Golumbeanu M, Champagne C, Symons TL, Connell M, Gething PW, Visser T, Menach AL, Cohen JM, Pothin E. Camponovo F, et al. BMC Infect Dis. 2024 Nov 8;24(1):1267. doi: 10.1186/s12879-024-09912-x. BMC Infect Dis. 2024. PMID: 39516725 Free PMC article. - Inference on spatiotemporal dynamics for coupled biological populations.
Li J, Ionides EL, King AA, Pascual M, Ning N. Li J, et al. J R Soc Interface. 2024 Jul;21(216):20240217. doi: 10.1098/rsif.2024.0217. Epub 2024 Jul 10. J R Soc Interface. 2024. PMID: 38981516 Free PMC article. - EXACT PHYLODYNAMIC LIKELIHOOD VIA STRUCTURED MARKOV GENEALOGY PROCESSES.
King AA, Lin Q, Ionides EL. King AA, et al. ArXiv [Preprint]. 2024 May 27:arXiv:2405.17032v1. ArXiv. 2024. PMID: 38855555 Free PMC article. Preprint. - Informing policy via dynamic models: Cholera in Haiti.
Wheeler J, Rosengart A, Jiang Z, Tan K, Treutle N, Ionides EL. Wheeler J, et al. PLoS Comput Biol. 2024 Apr 29;20(4):e1012032. doi: 10.1371/journal.pcbi.1012032. eCollection 2024 Apr. PLoS Comput Biol. 2024. PMID: 38683863 Free PMC article. - Implementing measurement error models with mechanistic mathematical models in a likelihood-based framework for estimation, identifiability analysis and prediction in the life sciences.
Murphy RJ, Maclaren OJ, Simpson MJ. Murphy RJ, et al. J R Soc Interface. 2024 Jan;21(210):20230402. doi: 10.1098/rsif.2023.0402. Epub 2024 Jan 31. J R Soc Interface. 2024. PMID: 38290560 Free PMC article. Review.
References
- Diggle PJ, Gratton RJ. 1984. Monte Carlo methods of inference for implicit statistical models. J. R. Stat. Soc. B (Stat. Methodol.) 46, 193–227.
- Bretó C, He D, Ionides EL, King AA. 2009. Time series analysis via mechanistic models. Ann. Appl. Stat. 3, 319–348. (10.1214/08-AOAS201) - DOI
- Pawitan Y. 2001. In all likelihood: statistical modelling and inference using likelihood. Oxford, UK: Clarendon Press.
- Barndorff-Nielsen OE, Cox DR. 1994. Inference and asymptotics. London, UK: Chapman and Hall.
- Bérard J, Del Moral P, Doucet A. 2014. A lognormal central limit theorem for particle approximations of normalizing constants. Electron. J. Probab. 19, 1–28. (10.1214/ejp.v19-3428) - DOI
Publication types
MeSH terms
Grants and funding
- R01 AI101155/AI/NIAID NIH HHS/United States
- T32 HG000040/HG/NHGRI NIH HHS/United States
- U01 GM110712/GM/NIGMS NIH HHS/United States
- U54 GM111274/GM/NIGMS NIH HHS/United States
LinkOut - more resources
Full Text Sources
Other Literature Sources
Research Materials