Scholarlink

Background <p>HIV incidence estimation in population-based surveys often relies on interval-censored seroconversion times and complex survey designs, requiring computationally efficient Bayesian methods. We compared the computational efficiency and inferential performance of Hamiltonian Monte Carlo (HMC) and Metropolis–Hastings (MH) for Bayesian analysis of interval-censored HIV seroconversion times using a weighted log-logistic accelerated failure-time model.</p> Methods <p>We conducted a simulation study of 5,400 datasets varying sample size, censoring, and weight dispersion under identical likelihoods, priors, diagnostics, and convergence criteria for both samplers, and applied the same model to the Zimbabwe PHIA 2020 survey (ZIMPHIA). Performance was assessed using efficiency (effective sample size per second, ESS/s), accuracy, interval calibration, and standard convergence diagnostics.</p> Results <p>HMC delivered substantially higher sampling efficiency across scenarios while producing comparable point estimates, uncertainty, and coverage. On ZIMPHIA (<InlineEquation ID="IEq1"><EquationSource Format="TEX">\(n = 16{,}554\)</EquationSource></InlineEquation>), HMC delivered <InlineEquation ID="IEq2"><EquationSource Format="TEX">\({\sim }72{\times }\)</EquationSource></InlineEquation> higher effective sample size per second than MH for <InlineEquation ID="IEq3"><EquationSource Format="TEX">\(\beta _{\text {sex}}\)</EquationSource></InlineEquation>, equivalent to 1.43 vs 31.83 minutes of wall time at matched effective sample sizes.</p> Conclusions <p>HMC is a practical default for weighted, interval-censored survival analysis in HIV surveys, with benefits that increase with sample size and weight variability.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Bayesian inference of interval-censored data with an application to HIV population surveys: a simulation study comparing Hamiltonian Monte Carlo and Metropolis–Hastings sampling algorithms

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月9日

查看全文
  • Alexander van Twisk,
  • Innocent Maposa

摘要

Background

HIV incidence estimation in population-based surveys often relies on interval-censored seroconversion times and complex survey designs, requiring computationally efficient Bayesian methods. We compared the computational efficiency and inferential performance of Hamiltonian Monte Carlo (HMC) and Metropolis–Hastings (MH) for Bayesian analysis of interval-censored HIV seroconversion times using a weighted log-logistic accelerated failure-time model.

Methods

We conducted a simulation study of 5,400 datasets varying sample size, censoring, and weight dispersion under identical likelihoods, priors, diagnostics, and convergence criteria for both samplers, and applied the same model to the Zimbabwe PHIA 2020 survey (ZIMPHIA). Performance was assessed using efficiency (effective sample size per second, ESS/s), accuracy, interval calibration, and standard convergence diagnostics.

Results

HMC delivered substantially higher sampling efficiency across scenarios while producing comparable point estimates, uncertainty, and coverage. On ZIMPHIA (\(n = 16{,}554\)), HMC delivered \({\sim }72{\times }\) higher effective sample size per second than MH for \(\beta _{\text {sex}}\), equivalent to 1.43 vs 31.83 minutes of wall time at matched effective sample sizes.

Conclusions

HMC is a practical default for weighted, interval-censored survival analysis in HIV surveys, with benefits that increase with sample size and weight variability.