A Bayesian Framework for Parameter Estimation in Dynamical Models
2011

Bayesian Framework for Parameter Estimation in Dynamic Models

Sample size: 7 publication Evidence: moderate

Author Information

Author(s): Flávio Codeço Coelho, Cláudia Torres Codeço, M. Gabriela Gomes

Primary Institution: Instituto Gulbenkian de Ciência, Oeiras, Portugal

Hypothesis

Can a Bayesian framework effectively estimate parameters in dynamic biological models using time-series data?

Conclusion

The proposed Bayesian framework successfully estimates parameters for an influenza transmission model using incidence data from three European countries.

Supporting Evidence

  • The model was fitted to incidence data from Belgium, the Netherlands, and Portugal.
  • The framework allows for the estimation of posterior probability distributions for model parameters.
  • The study highlights the importance of handling uncertainties in dynamic biological models.

Takeaway

This study shows a way to use math to understand how diseases spread by looking at past data. It helps scientists make better predictions about future outbreaks.

Methodology

The study used a Bayesian framework to fit a deterministic influenza transmission model to seven years of incidence data from Belgium, the Netherlands, and Portugal.

Limitations

The applicability of the method is currently limited by the robustness of MCMC samplers in handling complex high-dimensional parametric spaces.

Participant Demographics

Data from three European countries: Belgium, the Netherlands, and Portugal.

Statistical Information

Confidence Interval

95% credible intervals for parameter estimates.

Digital Object Identifier (DOI)

10.1371/journal.pone.0019616

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication