Abstract
We consider the problem of sampling from high-dimensional likelihood functions with large amounts of non-identifiabilities via Markov-Chain Monte-Carlo algorithms. Non-identifiabilities are problematic for commonly used proposal densities, leading to a low effective sample size. To address this problem, we introduce a regularization method using an artificial prior, which restricts non-identifiable parts of the likelihood function. This enables us to sample the posterior using common MCMC methods more efficiently. We demonstrate this with three MCMC methods on a likelihood based on a complex, high-dimensional blood coagulation model and a single series of measurements. By using the approximation of the artificial prior for the non-identifiable directions, we obtain a sample quality criterion. Unlike other sample quality criteria, it is valid even for short chain lengths. We use the criterion to compare the following three MCMC variants: The Random Walk Metropolis Hastings, the Adaptive Metropolis Hastings and the Metropolis adjusted Langevin algorithm.
References
[1] G. Bellu, M. P. Saccomani, S. Audoly and L. D’Angiò, Daisy: A new software tool to test global identifiability of biological and physiological systems, Comput. Methods Programs Biomed. 88 (2007), 52–61. 10.1016/j.cmpb.2007.07.002Search in Google Scholar PubMed PubMed Central
[2] S. Brooks, A. Gelman, G. Jones and X. Meng, Handbook of Markov Chain Monte Carlo, Chapman & Hall/CRC, Boca Raton, 2011. 10.1201/b10905Search in Google Scholar
[3] R. Burghaus, K. Coboeken, T. Gaub, C. Niederalt, A. Sensse, H.-U. Siegmund, W. Weiss, W. Mueck, T. Tanigawa and J. Lippert, Computational investigation of potential dosing schedules for a switch of medication from warfarin to rivaroxaban – An oral, direct factor Xa inhibitor, Front. Physiol. 5 (2014), 10.3389/fphys.2014.00417. 10.3389/fphys.2014.00417Search in Google Scholar PubMed PubMed Central
[4] S. D. Cohen and A. C. Hindmarsh, Cvode, a stiff/nonstiff ODE solver in C, Comput. Phys. 10 (1996), 138–143. 10.1063/1.4822377Search in Google Scholar
[5] M. K. Cowles and B. P. Carlin, Markov chain Monte Carlo convergence diagnostics: A comparative review, J. Amer. Statist. Assoc. 91 (1996), 883–904. 10.1080/01621459.1996.10476956Search in Google Scholar
[6] M. Girolami and B. Calderhead, Riemann manifold Langevin and Hamiltonian Monte Carlo methods, J. R. Stat. Soc. Ser. B. Stat. Methodol. 73 (2011), 123–214. 10.1111/j.1467-9868.2010.00765.xSearch in Google Scholar
[7] H. Haario, E. Saksman and J. Tamminen, An adaptive Metropolis algorithm, Bernoulli 7 (2001), 223–242. 10.2307/3318737Search in Google Scholar
[8] W. K. Hastings, Monte Carlo sampling methods using Markov chains and their applications, Biometrika 59 (1970), 97–109. 10.1093/biomet/57.1.97Search in Google Scholar
[9] H. C. Hemker, P. Giesen, R. Al Dieri, V. Regnault, E. de Smedt, R. Wagenvoord, T. Lecompte and S. Béguin, Calibrated automated thrombin generation measurement in clotting plasma, Pathophys. Haemost Thromb. 33 (2003), 4–15. 10.1159/000071636Search in Google Scholar PubMed
[10] M. Krauss, R. Burghaus, J. Lippert, M. Niemi, P. Neuvonen, A. Schuppert, S. Willmann, L. Kuepfer and L. Görlitz, Using Bayesian-PBPK modeling for assessment of inter-individual variability and subgroup stratification, In Sil. Pharmacol. 1 (2013), 10.1186/2193-9616-1-6. 10.1186/2193-9616-1-6Search in Google Scholar PubMed PubMed Central
[11] M. Krauss, K. Tappe, A. Schuppert, L. Kuepfer and L. Goerlitz, Bayesian population physiologically-based pharmacokinetic (PBPK) approach for a physiologically realistic characterization of interindividual variability in clinically relevant populations, PLoS One 10 (2015), Article ID e0139423. 10.1371/journal.pone.0139423Search in Google Scholar PubMed PubMed Central
[12] A. Raue, C. Kreutz, T. Maiwald, J. Bachmann, M. Schilling, U. Klingmüller and J. Timmer, Structural and practical identifiability analysis of partially observed dynamical models by exploiting the profile likelihood, Bioinform. 25 (2009), 1923–1929. 10.1093/bioinformatics/btp358Search in Google Scholar PubMed
[13] G. Roberts and J. Rosenthal, Optimal scaling for various Metropolis-Hastings algorithms, Stat. Sci. 16 (2001), 351–367. 10.1214/ss/1015346320Search in Google Scholar
© 2018 Walter de Gruyter GmbH, Berlin/Boston
