arXiv subjects

Anna Heath

Publications and source records attributed to Anna Heath.

At least 19 recordsLinked to original sources

arXiv2026

Calculating the Expected Value of Sample Information accounting for missing data

The Expected Value of Sample Information (EVSI) is a powerful instrument to determine the value of additional evidence to inform an economic model. However, EVSI has been applied only to idealized data collection mechanisms, thereby reducing its potential applications in realistic studies. In this paper, we define a methodology to calculate EVSI when the additional evidence we aim to collect exhibits missing data; a very common challenge in real-world studies. First, we define how to simulate individual-level data and how to induce missingness inside the simulated data. We will reproduce Missing Completely At Random (MCAR), Missing At Random (MAR), and Missing Not At Random (MNAR) missing data mechanisms. Then, we will apply the multiple imputation method to adjust for the bias related to the missing data. Finally, we use the imputed data to compute the EVSI using nonparametric regression methods. We apply the novel methodology to two different health economic models and compare the EVSI computed on data without missingness with the EVSI with different types of missing data. We show that the EVSI decreases when the additional evidence suffers from missingness, and therefore, we define a method to efficiently compute the sample size we need to collect to recover the idealized EVSI (without missingness). We find out that the number of additional samples needed to correct for missing data exceeds that coming from standard approaches. With this methodology, we compute EVSI when the additional data are affected by non-trivial forms of missingness, modeling both the MAR and MNAR mechanisms, and extending EVSI calculation to more realistic scenarios. The fact that the necessary sample size to recover the idealized EVSI exceeds that of standard methods suggests that this methodology potentially represents a novel technique for sample size calculation in realistic studies.

stat.ME↗

arXiv2026

Remote, bivariate expert elicitation to determine the prior probability distribution for sample size calculation in a Bayesian non-inferiority multicenter randomized controlled trial (Croup Dosing Trial)

Prior distributions must be specified for the parameters of interest in a Bayesian clinical trial. When existing evidence on the effects of the trial interventions is limited, prior distributions can be constructed with expert elicitation. However, conventional elicitation requires face-to-face interactions and intensive pre-elicitation training, which can be infeasible. Our remote elicitation was based on established expert elicitation methods. We used bivariate prior distributions for dependencies between elicited quantities. We elicited a prior distribution for the Croup Dosing Trial, which will assess the number of return visits to the emergency department within 7 days in children with croup. This trial evaluates the non-inferiority of 0.15 mg/kg of dexamethasone, compared to the standard dose of 0.60 mg/kg to treat croup. We conducted three remote workshops to elicit expert beliefs on the efficacy of the two doses of dexamethasone. Each workshop consisted of two survey rounds, separated by a group discussion. Prior to the workshop, experts reviewed provided literature on the effects of the two doses of dexamethasone. Beliefs were aggregated with expert-specific bivariate distributions. The aggregated distribution and surveyed non-inferiority margin determined the sample size. Twelve emergency medicine physicians participated in our remote elicitation exercise. The elicitation generated a prior distribution centered at 6% for the 0.60 mg/kg dose and 8% for the 0.15 mg/kg dose. The aggregated prior distribution produced a sample size of 1850, based on a non-inferiority margin of 4%. We elicited a prior distribution that incorporated past evidence and expert opinion. The elicited prior is consistent with literature on the efficacy of the dexamethasone doses in treating croup. Our approach demonstrates the feasibility of remotely eliciting bivariate distributions for clinical trials.

stat.AP↗

arXiv2025

Marginal and conditional summary measures: transportability and compatibility across studies

Marginal and conditional summary measures do not generally coincide, have different interpretations and correspond to different decision questions. While these aspects have primarily been recognized for non-collapsible summary measures, they are equally problematic for some collapsible measures in the presence of effect modification. We clarify the interpretation and properties of several marginal and conditional summary measures, considering different types of outcomes and hypothetical outcome-generating mechanisms. We describe implications of the choice of summary measure for transportability, highlighting that covariates not conventionally described as effect modifiers can modify population-level treatment effects. Finally, we illustrate existing summary measure incompatibility issues in the context of evidence synthesis, using the case of covariate adjustment methods for indirect treatment comparisons. Because marginal and conditional summary measures do not generally coincide, their na\"ive pooling in evidence synthesis can produce bias. Almost invariably, care is needed to ensure that evidence synthesis methods are combining compatible summary measures, and this may be easier to accomplish with full access to individual patient data.

stat.ME↗

arXiv2025

A systematic review of sample size determination in Bayesian randomized clinical trials: full Bayesian methods are rarely used

Utilizing Bayesian methods in clinical trials has become increasingly popular, as they can incorporate historical data and expert opinions into the design and allow for smaller sample sizes to reduce costs while providing reliable and robust statistical results. Sample size determination (SSD) is a key aspect of clinical trial design and various methods for Bayesian sample size determination are available. However, it is unclear how these methods are being used in practice. A systematic literature review was conducted to understand how sample sizes for Bayesian randomized clinical trials (RCTs) are determined and inform the design of future Bayesian trials. We searched five databases in May 2023, and updated in January 2025, including efficacy RCTs in humans which utilized a Bayesian framework for the primary data analysis, published in English, and enrolled participants between 2009 and 2024. The literature search produced 19,182 records, of which 105 studies were selected for data extraction. Results show that the most common method for SSD in Bayesian RCTs was a hybrid approach in which elements of Bayesian and frequentist theory are combined. Many RCTs did not provide a justification for SSD, while fully Bayesian methods were rarely used in practice, despite significant theoretical development. Our review also revealed a lack of standardized reporting, making it challenging to review the SSD. The CONSORT statement for reporting RCTs states that sample size calculations must be reported, which was poorly adhered to. Among RCTs that reported SSD, relevant information was frequently omitted from the reports and discussed in poorly structured supplementary materials. Thus, there is a critical need for greater transparency, standardization and translation of relevant methodology in Bayesian RCTs.

stat.AP↗

arXiv2024

Effect modification and non-collapsibility leads to conflicting treatment decisions: a review of marginal and conditional estimands and recommendations for decision-making

Effect modification occurs when a covariate alters the relative effectiveness of treatment compared to control. It is widely understood that, when effect modification is present, treatment recommendations may vary by population and by subgroups within the population. Population-adjustment methods are increasingly used to adjust for differences in effect modifiers between study populations and to produce population-adjusted estimates in a relevant target population for decision-making. It is also widely understood that marginal and conditional estimands for non-collapsible effect measures, such as odds ratios or hazard ratios, do not in general coincide even without effect modification. However, the consequences of both non-collapsibility and effect modification together are little-discussed in the literature. In this paper, we set out the definitions of conditional and marginal estimands, illustrate their properties when effect modification is present, and discuss the implications for decision-making. In particular, we show that effect modification can result in conflicting treatment rankings between conditional and marginal estimates. This is because conditional and marginal estimands correspond to different decision questions that are no longer aligned when effect modification is present. For time-to-event outcomes, the presence of covariates implies that marginal hazard ratios are time-varying, and effect modification can cause marginal hazard curves to cross. We conclude with practical recommendations for decision-making in the presence of effect modification, based on pragmatic comparisons of both conditional and marginal estimates in the decision target population. Currently, multilevel network meta-regression is the only population-adjustment method capable of producing both conditional and marginal estimates, in any decision target population.

stat.ME↗

arXiv2024

Bayesian Joint Modeling for Longitudinal Magnitude Data with Informative Dropout: an Application to Critical Care Data

In various biomedical studies, analysis often focuses on data magnitudes, particularly when algebraic signs are irrelevant or lost. For repeated measures studies involving magnitude outcomes, incorporating random effects is essential as they account for individual heterogeneity, thereby enhancing parameter estimation precision. However, established regression methods specifically designed for magnitude outcomes that incorporate random effects are currently lacking. This article bridges this gap by introducing Bayesian regression modeling approaches for analyzing magnitude data, with a key focus on incorporating random effects. The proposed method is further extended to address multiple causes of informative dropout, a common challenge in repeated measures studies. To tackle this missing data challenge, a joint modeling strategy is developed, building upon the introduced regression techniques. Two numerical simulation studies assess the validity of our method. The chosen simulation scenarios are designed to resemble the conditions of our motivating study. Results demonstrate that the proposed method for magnitude data performs well in terms of estimation accuracy, and the joint models effectively mitigate bias due to missing data. Finally, we apply these models to analyze magnitude data from the motivating study, investigating whether sex impacts the magnitude change in diaphragm thickness over time for ICU patients.

stat.ME↗

arXiv2024

A Nonparametric Approach for Estimating the Effective Sample Size in Gaussian Approximation of Expected Value of Sample Information

The effective sample size (ESS) measures the informational value of a probability distribution in terms of an equivalent number of study participants. The ESS plays a crucial role in estimating the Expected Value of Sample Information (EVSI) through the Gaussian approximation approach. Despite the significance of ESS, existing ESS estimation methods within the Gaussian approximation framework are either computationally expensive or potentially inaccurate. To address these limitations, we propose a novel approach that estimates the ESS using the summary statistics of generated datasets and nonparametric regression methods. The simulation results suggest that the proposed method provides accurate ESS estimates at a low computational cost, making it an efficient and practical way to quantify the information contained in the probability distribution of a parameter. Overall, determining the ESS can help analysts understand the uncertainty levels in complex prior distributions in the probability analyses of decision models and perform efficient EVSI calculations.

stat.ME↗

arXiv2024

Estimating the EVSI with Gaussian Approximations and Spline-Based Series Methods

Background. The Expected Value of Sample Information (EVSI) measures the expected benefits that could be obtained by collecting additional data. Estimating EVSI using the traditional nested Monte Carlo method is computationally expensive but the recently developed Gaussian approximation (GA) approach can efficiently estimate EVSI across different sample sizes. However, the conventional GA may result in biased EVSI estimates if the decision models are highly nonlinear. This bias may lead to suboptimal study designs when GA is used to optimize the value of different studies. Therefore, we extend the conventional GA approach to improve its performance for nonlinear decision models. Methods. Our method provides accurate EVSI estimates by approximating the conditional benefit based on two steps. First, a Taylor series approximation is applied to estimate the conditional benefit as a function of the conditional moments of the parameters of interest using a spline, which is fitted to the samples of the parameters and the corresponding benefits. Next, the conditional moments of parameters are approximated by the conventional GA and Fisher information. The proposed approach is applied to several data collection exercises involving non-Gaussian parameters and nonlinear decision models. Its performance is compared with the nested Monte Carlo method, the conventional GA approach, and the nonparametric regression-based method for EVSI calculation. Results. The proposed approach provides accurate EVSI estimates across different sample sizes when the parameters of interest are non-Gaussian and the decision models are nonlinear. The computational cost of the proposed method is similar to other novel methods. Conclusions. The proposed approach can estimate EVSI across sample sizes accurately and efficiently, which may support researchers in determining an economically optimal study design using EVSI.

stat.ME↗

arXiv2023

Methodological considerations for novel approaches to covariate-adjusted indirect treatment comparisons

We examine four important considerations in the development of covariate adjustment methodologies for indirect treatment comparisons. Firstly, we consider potential advantages of weighting versus outcome modeling, placing focus on bias-robustness. Secondly, we outline why model-based extrapolation may be required and useful, in the specific context of indirect treatment comparisons with limited overlap. Thirdly, we describe challenges for covariate adjustment based on data-adaptive outcome modeling. Finally, we offer further perspectives on the promise of doubly-robust covariate adjustment frameworks.

stat.ME↗

arXiv2023

Model-based standardization using multiple imputation

When studying the association between treatment and a clinical outcome, a parametric multivariable model of the conditional outcome expectation is often used to adjust for covariates. The treatment coefficient of the outcome model targets a conditional treatment effect. Model-based standardization is typically applied to average the model predictions over the target covariate distribution, and generate a covariate-adjusted estimate of the marginal treatment effect. The standard approach to model-based standardization involves maximum-likelihood estimation and use of the non-parametric bootstrap. We introduce a novel, general-purpose, model-based standardization method based on multiple imputation that is easily applicable when the outcome model is a generalized linear model. We term our proposed approach multiple imputation marginalization (MIM). MIM consists of two main stages: the generation of synthetic datasets and their analysis. MIM accommodates a Bayesian statistical framework, which naturally allows for the principled propagation of uncertainty, integrates the analysis into a probabilistic framework, and allows for the incorporation of prior evidence. We conduct a simulation study to benchmark the finite-sample performance of MIM in conjunction with a parametric outcome model. The simulations provide proof-of-principle in scenarios with binary outcomes, continuous-valued covariates, a logistic outcome model and the marginal log odds ratio as the target effect measure. When parametric modeling assumptions hold, MIM yields unbiased estimation in the target covariate distribution, valid coverage rates, and similar precision and efficiency than the standard approach to model-based standardization.

stat.ME↗

arXiv2023

Designing a Bayesian adaptive clinical trial to evaluate novel mechanical ventilation strategies in acute respiratory failure using Integrated Nested Laplace Approximations

Background: We aimed to design a Bayesian adaption trial through extensive simulations to determine values for key design parameters, demonstrate error rates, and establish the expected sample size. The complexity of the proposed outcome and analysis meant that Markov Chain Monte Carlo methods were required, resulting in an infeasible computational burden. Thus, we leveraged the Integrated Nested Laplace Approximations (INLA) algorithm, a fast approximation method, to ensure the feasibility of these simulations. Methods: We simulated Bayesian adaptive two-arm superiority trials that stratified participants into two disease severity states. The outcome was analyzed with proportional odds logistic regression. Trials were stopped for superiority or futility, separately for each state. We calculated the type I error and power across 64 scenarios that varied the stopping thresholds and the minimum sample size before commencing adaptive analyses. We incorporated dynamic borrowing and used INLA to compute the posterior distributions at each adaptive analysis. Designs that maintained a type I error below 5%, a power above 80%, and a feasible mean sample size were then evaluated across 22 scenarios that varied the odds ratios for the two severity states. Results: Power generally increased as the initial sample size and the threshold for declaring futility increased. Two designs were selected for further analysis. In the comprehensive simulations, the one design had a higher chance of reaching a trial conclusion before the maximum sample size and higher probability of declaring superiority when appropriate without a substantial increase in sample size for the more realistic scenarios and was selected as the trial design. Conclusions: We designed a Bayesian adaptive trial to evaluate novel strategies for ventilation using the INLA algorithm to and optimize the trial design through simulation.

stat.AP↗

arXiv2022

BCEA: An R Package for Cost-Effectiveness Analysis

We describe in detail how to perform health economic cost-effectiveness analyses (CEA) using the R package $\textbf{BCEA}$ (Bayesian Cost-Effectiveness Analysis). CEA consist of analytic approaches for combining costs and health consequences of intervention(s). These help to understand how much an intervention may cost (per unit of health gained) compared to an alternative intervention, such as a control or status quo. For resource allocation, a decision maker may wish to know if an intervention is cost saving, and if not then how much more would it cost to implement it compared to a less effective intervention. Current guidance for cost-effectiveness analyses advocates the quantification of uncertainties which can be represented by random samples obtained from a probability sensitivity analysis or, more efficiently, a Bayesian model. $\textbf{BCEA}$ can be used to post-process the sampled costs and health impacts to perform advanced analyses producing standardised and highly customisable outputs. We present the features of the package, including its many functions and their practical application. $\textbf{BCEA}$ is valuable for statisticians and practitioners working in the field of health economic modelling wanting to simplify and standardise their workflow, for example in the preparation of dossiers in support of marketing authorisation, or academic and scientific publications.

stat.CO↗

arXiv2021

Parametric G-computation for Compatible Indirect Treatment Comparisons with Limited Individual Patient Data

Population adjustment methods such as matching-adjusted indirect comparison (MAIC) are increasingly used to compare marginal treatment effects when there are cross-trial differences in effect modifiers and limited patient-level data. MAIC is based on propensity score weighting, which is sensitive to poor covariate overlap and cannot extrapolate beyond the observed covariate space. Current outcome regression-based alternatives can extrapolate but target a conditional treatment effect that is incompatible in the indirect comparison. When adjusting for covariates, one must integrate or average the conditional estimate over the relevant population to recover a compatible marginal treatment effect. We propose a marginalization method based on parametric G-computation that can be easily applied where the outcome regression is a generalized linear model or a Cox model. The approach views the covariate adjustment regression as a nuisance model and separates its estimation from the evaluation of the marginal treatment effect of interest. The method can accommodate a Bayesian statistical framework, which naturally integrates the analysis into a probabilistic framework. A simulation study provides proof-of-principle and benchmarks the method's performance against MAIC and the conventional outcome regression. Parametric G-computation achieves more precise and more accurate estimates than MAIC, particularly when covariate overlap is poor, and yields unbiased marginal treatment effect estimates under no failures of assumptions. Furthermore, the marginalized regression-adjusted estimates provide greater precision and accuracy than the conditional estimates produced by the conventional outcome regression, which are systematically biased because the measure of effect is non-collapsible.

stat.ME↗

arXiv2021

Methods for Population Adjustment with Limited Access to Individual Patient Data: A Review and Simulation Study

Population-adjusted indirect comparisons estimate treatment effects when access to individual patient data is limited and there are cross-trial differences in effect modifiers. Popular methods include matching-adjusted indirect comparison (MAIC) and simulated treatment comparison (STC). There is limited formal evaluation of these methods and whether they can be used to accurately compare treatments. Thus, we undertake a comprehensive simulation study to compare standard unadjusted indirect comparisons, MAIC and STC across 162 scenarios. This simulation study assumes that the trials are investigating survival outcomes and measure continuous covariates, with the log hazard ratio as the measure of effect. MAIC yields unbiased treatment effect estimates under no failures of assumptions. The typical usage of STC produces bias because it targets a conditional treatment effect where the target estimand should be a marginal treatment effect. The incompatibility of estimates in the indirect comparison leads to bias as the measure of effect is non-collapsible. Standard indirect comparisons are systematically biased, particularly under stronger covariate imbalance and interaction effects. Standard errors and coverage rates are often valid in MAIC but the robust sandwich variance estimator underestimates variability where effective sample sizes are small. Interval estimates for the standard indirect comparison are too narrow and STC suffers from bias-induced undercoverage. MAIC provides the most accurate estimates and, with lower degrees of covariate overlap, its bias reduction outweighs the loss in effective sample size and precision under no failures of assumptions. An important future objective is the development of an alternative formulation to STC that targets a marginal treatment effect.

stat.AP↗

arXiv2021

Calculating Expected Value of Sample Information Adjusting for Imperfect Implementation

Background: The Expected Value of Sample Information (EVSI) calculates the value of collecting additional information through a study with a given design. Standard EVSI analyses assume that the treatment recommendations based on the new information will be implemented immediately and completely once the study has finished. However, treatment implementation is often slow and incomplete, giving a biased estimation of the study value. Previous methods have adjusted for this bias, but they typically make the unrealistic assumption that the study outcomes do not impact the implementation. One method does assume that the implementation is related to the strength of evidence in favour of the treatment but this method uses analytical results, which require alternative restrictive assumptions. Methods: We develop two implementation-adjusted EVSI calculation methods that relax these assumptions. The first method uses computationally demanding nested simulations, using the definition of the implementation-adjusted EVSI. The second method aims to facilitate the computation by adapting a recently developed efficient EVSI computation method to adjust for imperfect implementation. The implementation-adjusted EVSI is then calculated with the two methods across three examples. Results: The maximum difference between the two methods is at most 6% in all examples. The efficient computation method is between 6 and 60 times faster than the nested simulation method in this case study and could be used in practice. Conclusions: The methods developed in this paper calculate implementation-adjusted EVSI using realistic assumptions. The efficient estimation method is accurate and can estimate the implementation-adjusted EVSI in practice. By adapting standard EVSI estimation methods, we allow accurate adjustments for imperfect implementation with the same computational cost as a standard analysis.

stat.ME↗

arXiv2020

Effect modification in anchored indirect treatment comparisons: Comments on "Matching-adjusted indirect comparisons: Application to time-to-event data"

This commentary regards a recent simulation study conducted by Aouni, Gaudel-Dedieu and Sebastien, evaluating the performance of different versions of matching-adjusted indirect comparison (MAIC) in an anchored scenario with a common comparator. The simulation study uses survival outcomes and the Cox proportional hazards regression as the outcome model. It concludes that using the LASSO for variable selection is preferable to balancing a maximal set of covariates. However, there are no treatment effect modifiers in imbalance in the study. The LASSO is more efficient because it selects a subset of the maximal set of covariates but there are no cross-study imbalances in effect modifiers inducing bias. We highlight the following points: (1) in the anchored setting, MAIC is necessary where there are cross-trial imbalances in effect modifiers; (2) the standard indirect comparison provides greater precision and accuracy than MAIC if there are no effect modifiers in imbalance; (3) while the target estimand of the simulation study is a conditional treatment effect, MAIC targets a marginal or population-average treatment effect; (4) in MAIC, variable selection is a problem of low dimensionality and sparsity-inducing methods like the LASSO may be problematic. Finally, data-driven approaches do not obviate the necessity for subject matter knowledge when selecting effect modifiers. R code is provided in the Appendix to replicate the analyses and illustrate our points.

stat.ME↗

arXiv2020

Conflating marginal and conditional treatment effects: Comments on 'Assessing the performance of population adjustment methods for anchored indirect comparisons: A simulation study'

In this commentary, we highlight the importance of: (1) carefully considering and clarifying whether a marginal or conditional treatment effect is of interest in a population-adjusted indirect treatment comparison; and (2) developing distinct methodologies for estimating the different measures of effect. The appropriateness of each methodology depends on the preferred target of inference.

stat.ME↗

arXiv2020

A Bayesian response-adaptive dose finding and comparative effectiveness trial

Aims: Combinations of treatments can offer additional benefit over the treatments individually. However, trials of these combinations are lower priority than the development of novel therapies, which can restrict funding, timelines and patient availability. This paper develops a novel trial design to facilitate the evaluation of novel combination therapies that combines elements of phase II and phase III trials. Methods: This trial uses response adaptive randomisation to increase the information collected about successful novel drug combinations and Bayesian dose-response modelling to undertake a comparative-effectiveness analysis for the most successful dose combination against a relevant comparator. We used simulation methods to evaluate the probability of selecting the correct optimal dose combination, the operating characteristics and predictive power of this design for a trial in pain management and sedation in paediatric emergency departments. Results: With 410 participants, 5 interim updates of the randomisation ratio and a probability of effectiveness of 0.93, 0.88 and 0.83 for the three dose combinations, we have an 83% chance of randomising the largest number of patients to the drug with the highest probability of effectiveness. Based on this adaptive randomisation procedure, the comparative effectiveness analysis has a type I error of less than 5% and a 93% chance of correctly concluding non-inferiority when the probability of effectiveness for the optimal combination therapy is 0.9. In this case, the trial has a 77% chance of meeting its dual aims of dose finding and comparative effectiveness. Finally, the Bayesian predictive power of the trial is over 90%. Conclusion: The proposed trial has high potential to meet the dual study objectives within a feasible level of recruitment, minimising the administrative burden and recruitment time for a trial.

stat.AP↗