A Methodological Note on Empirical Confidence Intervals for the GCM-Ensemble Mean in Projecting Climate Change Impacts on Health
Tomo, Y.
Show abstract
In climate-health impact projection studies, projected impacts from multiple general circulation models (GCMs) are commonly aggregated by reporting the mean of GCM-specific impacts as the point estimate alongside a 95% empirical confidence interval (eCI) constructed from the 2.5th and 97.5th percentiles of the simulated pooled distribution of GCM-specific impacts. This study shows that the eCI generally does not yield the nominal coverage probability for the GCM-ensemble mean and constructs an interval aligned with the estimand. In a simulation study, the coverage of the eCI for the GCM-ensemble mean deviates from the nominal level in both directions, whereas the aligned interval yields coverage near 95% across all considered settings. The exact coverages derived analytically under a location-shift model agree with the simulation results. In a reanalysis of a heat-related mortality projection in London, the eCI is consistently wider. The eCI should be distinguished from confidence intervals for the GCM-ensemble mean; rather, the interval may be better described as a simulation-based approximate prediction interval for a GCM-specific impact under the uniformly randomly selected GCM from the considered GCM set.
Matching journals
The top 9 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
- Statistical analysis of the impact of environmental temperature on the exponential growth rate of cases infected by COVID-19 91%
- A Stratified Model to Quantify the Effects of Containment Policies on the Spread of COVID-19 90%
- A Bayesian Susceptible-Infectious-Hospitalized-Ventilated-Recovered Model to Predict Demand for COVID-19 Inpatient Care in a Large Healthcare System 90%
Similar papers in this journal
- Modelling COVID-19 contagion: Risk assessment and targeted mitigation policies 91%
- Assessing the impact of widespread respirator use in curtailing COVID-19 transmission in the United States 90%
- Optimal health and economic impact of non-pharmaceutical intervention measures prior and post vaccination in England: a mathematical modelling study 89%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.