Estimating the Under-Five Mortality Rate Using a Bayesian Hierarchical Time Series Model
2011

Estimating Under-Five Mortality Rate Using a Bayesian Model

Sample size: 165 publication 10 minutes Evidence: moderate

Author Information

Author(s): Leontine Alkema, Ann Wei Ling

Primary Institution: National University of Singapore

Hypothesis

Can a Bayesian hierarchical time series model provide more accurate estimates of under-five mortality rates compared to traditional methods?

Conclusion

The proposed Bayesian model offers smoother estimates of under-five mortality rates and better uncertainty assessments than traditional methods.

Supporting Evidence

  • The Bayesian model provides credible bounds for under-five mortality rates that are well calibrated during the observation period.
  • Cross-validation showed that the model's predictions were generally accurate.
  • The model allows for the exchange of information between countries to improve estimates.

Takeaway

This study created a new way to estimate how many young children die in different countries, making the numbers more accurate and easier to understand.

Methodology

A Bayesian hierarchical time series model was used to estimate under-five mortality rates for 165 countries, allowing for smooth changes over time.

Potential Biases

Potential biases from incomplete vital registration systems were addressed by down-weighting or excluding biased observations.

Limitations

The model may underestimate rates of decline in countries with recent accelerations in mortality reduction.

Participant Demographics

Data from 165 countries were analyzed.

Statistical Information

Confidence Interval

95%

Digital Object Identifier (DOI)

10.1371/journal.pone.0023954

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication