Selected article for: "effective sample size and sample size"

Author: Michal Ben-Nun; Pete Riley; James Turtle; David P. Bacon; Steven Riley
Title: National and Regional Influenza-Like-Illness Forecasts for the USA
  • Document date: 2018_4_27
  • ID: cheiabv0_27
    Snippet: This total of 32 model-runs were used to make forecasts of incidence at both the 252 national and regional levels. For each region, we simulate three MCMC chains each with 253 10 7 steps and a burn time of 2 × 10 6 steps. The smallest effective sample size that we 254 report for any parameter was greater than 100. After sampling from the individual 255 posterior densities of each region, we calculated our national forecast as the weighted 256 su.....
    Document: This total of 32 model-runs were used to make forecasts of incidence at both the 252 national and regional levels. For each region, we simulate three MCMC chains each with 253 10 7 steps and a burn time of 2 × 10 6 steps. The smallest effective sample size that we 254 report for any parameter was greater than 100. After sampling from the individual 255 posterior densities of each region, we calculated our national forecast as the weighted 256 sum of the regional profiles with the weights given by the relative populations of the 257 regions. The national curve was also fitted directly (without any regional information) 258 using all the models and priors, but these direct results were only used at the end of the 259 season when estimating the performance of each of our procedures.

    Search related documents:
    Co phrase search for related documents
    • direct result and incidence forecast: 1
    • directly fit and national forecast: 1
    • incidence forecast and national curve: 1
    • incidence forecast and sample size: 1
    • MCMC chain and posterior density: 1, 2, 3, 4, 5, 6, 7
    • MCMC chain and prior model: 1, 2, 3, 4, 5
    • MCMC chain and sample size: 1, 2, 3
    • national curve and regional national level: 1
    • national curve and sample size: 1
    • national forecast and regional national level: 1
    • posterior density and prior model: 1
    • posterior density and sample size: 1
    • prior model and relative population: 1
    • prior model and sample size: 1, 2