Combining MCMC with ‘sequential’ PKPD modelling

Lunn, David J.; Best, Nicky; Spiegelhalter, David; Graham, Gordon; Neuenschwander, Beat

doi:10.1007/s10928-008-9109-1

Cited by 89 publications

(94 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a recent paper, Lunn et al (2009a) introduce a method for cutting feedback when fitting complex Bayesian models using MCMC. The approach is similar in spirit to two-stage estimation.…”

Section: Review: Cutting Feedback In Bayesian Computationmentioning

confidence: 99%

“…A related Bayesian computational procedure is proposed by Liu et al (2009). The work of Lunn et al (2009a) is motivated by applications in pharmacokinetics, whereas Liu et al (2009) describe examples in the analysis of computer models. Each case involves combining inferences from multiple data sources using different models.…”

Section: Review: Cutting Feedback In Bayesian Computationmentioning

confidence: 99%

“…Following Lunn et al (2009a) and Liu et al (2009) we cut feedback between the treatment and outcome models by not updating from the full conditional distribution for γ. The correct conditional densities for p(γ|α, β, ξ, λ, data) is given in equation (4).…”

Section: Application To the Thin Datamentioning

confidence: 99%

“…In a recent paper, Lunn et al (2009a) introduce techniques for cutting feedback when fitting complex Bayesian models. They describe an example from pharmacokinetics that involves the joint analysis of multiple datasets where there is uncertainty in the model specification.…”

Section: Introductionmentioning

confidence: 99%

“…See Liu et al (2009) for further discussion of applications to computer models. Lunn et al (2009a) are careful to point out that the resulting inferences does not arise from an underlying probability model. But nor do inferences from other sequential analyses.…”

mentioning

confidence: 99%

See 4 more Smart Citations

Cutting Feedback in Bayesian Regression Adjustment for the Propensity Score

McCandless¹,

Douglas²,

Evans³

et al. 2010

The International Journal of Biostatistics

View full text Add to dashboard Cite

McCandless, Gustafson and Austin (2009) describe a Bayesian approach to regression adjustment for the propensity score to reduce confounding. A unique property of the method is that the treatment and outcome models are combined via Bayes theorem. However, this estimation procedure can be problematic if the outcome model is misspecified. We observe feedback that can bias propensity score estimates. Building on new innovation in Bayesian computation, we propose a technique for cutting feedback in a Bayesian propensity analysis. We use the posterior distribution of the propensity scores as an input in the regression model for the outcome. The method is approximately Bayesian in the sense that it does not use the full likelihood for estimation. Nonetheless, it severs feedback between the treatment and outcome giving propensity score estimates that are free from bias but modeled with uncertainty. We illustrate the method in a matched cohort study investigating the effect of statins on primary stroke prevention.

show abstract

“…In a recent paper, Lunn et al (2009a) introduce a method for cutting feedback when fitting complex Bayesian models using MCMC. The approach is similar in spirit to two-stage estimation.…”

Section: Review: Cutting Feedback In Bayesian Computationmentioning

confidence: 99%

Section: Review: Cutting Feedback In Bayesian Computationmentioning

confidence: 99%

Section: Application To the Thin Datamentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 3 more Smart Citations

Cutting Feedback in Bayesian Regression Adjustment for the Propensity Score

McCandless¹,

Douglas²,

Evans³

et al. 2010

The International Journal of Biostatistics

View full text Add to dashboard Cite

show abstract

Isotope partitioning of soil respiration: A Bayesian solution to accommodate multiple sources of variability

Ogle

Pendall

2015

JGR Biogeosciences

View full text Add to dashboard Cite

Isotopic methods offer great potential for partitioning trace gas fluxes such as soil respiration into their different source contributions. Traditional partitioning methods face challenges due to variability introduced by different measurement methods, fractionation effects, and end-member uncertainty. To address these challenges, we describe a hierarchical Bayesian (HB) approach for isotopic partitioning of soil respiration that directly accommodates such variability. We apply our HB method to data from an experiment conducted in a shortgrass steppe ecosystem, where decomposition was previously shown to be stimulated by elevated CO 2 . Our approach simultaneously fits Keeling plot (KP) models to observations of soil or soil-respired δ 13 C and [CO 2 ] obtained via chambers and gas wells, corrects the KP intercepts for apparent fractionation (Δ) due to isotope-specific diffusion rates and/or method artifacts, estimates method-and treatment-specific values for Δ, propagates end-member uncertainty, and calculates proportional contributions from two distinct respiration sources ("old" and "new" carbon). The chamber KP intercepts were estimated with greater confidence than the well intercepts and compared to the theoretical value of 4.4‰, our results suggest that Δ varies between 2 and 5.2‰ depending on method (chambers versus wells) and CO 2 treatment. Because elevated CO 2 plots were fumigated with 13 C-depleted CO 2 , the source contributions were tightly constrained, and new C accounted for 64% (range = 55-73%) of soil respiration. The contributions were less constrained for the ambient CO 2 treatments, but new C accounted for significantly less (47%, range = 15-82%) of soil respiration. Our new HB partitioning approach contrasts our original analysis (higher contribution of old C under elevated CO 2 ) because it uses additional data sources, accounts for end-member bias, and estimates apparent fractionation effects.

show abstract

Measurement error in two‐stage analyses, with application to air pollution epidemiology

2013

View full text Add to dashboard Cite

Summary Public health researchers often estimate health effects of exposures (e.g., pollution, diet, lifestyle) that cannot be directly measured for study subjects. A common strategy in environmental epidemiology is to use a first-stage (exposure) model to estimate the exposure based on covariates and/or spatio-temporal proximity and to use predictions from the exposure model as the covariate of interest in the second-stage (health) model. This induces a complex form of measurement error. We propose an analytical framework and methodology that is robust to misspecification of the first-stage model and provides valid inference for the second-stage model parameter of interest. We decompose the measurement error into components analogous to classical and Berkson error and characterize properties of the estimator in the second-stage model if the first-stage model predictions are plugged in without correction. Specifically, we derive conditions for compatibility between the first- and second-stage models that guarantee consistency (and have direct and important real-world design implications), and we derive an asymptotic estimate of finite-sample bias when the compatibility conditions are satisfied. We propose a methodology that (1) corrects for finite-sample bias and (2) correctly estimates standard errors. We demonstrate the utility of our methodology in simulations and an example from air pollution epidemiology.

show abstract

Combining MCMC with ‘sequential’ PKPD modelling

Cited by 89 publications

References 27 publications

Cutting Feedback in Bayesian Regression Adjustment for the Propensity Score

Cutting Feedback in Bayesian Regression Adjustment for the Propensity Score

Isotope partitioning of soil respiration: A Bayesian solution to accommodate multiple sources of variability

Measurement error in two‐stage analyses, with application to air pollution epidemiology

Contact Info

Product

Resources

About