Project: Aggregating Statistical Models and Human Judgment Config

    Summary: Four models, 12 forecasts, 45 predictions
    Owner: allicodi
    Model Owners: allicodi, mcandrew
    Visibility Public
    Description: This project aims to provide public health officials forecasts of the COVID-19 outbreak using human judgment.

    A consensus forecast is an equally weighted combination of probabilistic predictions made by individuals. We included consensus forecasts from individual forecasters on Metaculus (https://www.metaculus.com/questions/) and from Good Judgment Open (https://www.gjopen.com/). A chimeric forecast is also included: an equally weighted combination of human judgment consensus forecasts and of computational models from the COVID-19 Forecasthub ensemble.

    Each month, individuals contribute forecasts for incident cases, deaths, hospitalizations, cumulative number of vaccines, and variant prevalence at the US national level. Individuals can produce forecasts at the beginning of each month until the middle of the month. All forecasting ends at 2PM EST.
    Home: https://github.com/computationalUncertaintyLab/aggStatModelsAndHumanJudgment_PUBL
    Core data: https://dataverse.harvard.edu/dataverse/aggregating_statistical_models_and_human_judgment
    Truth Data: (No truth data)
    Visualization: Visualization (Edit options ) (interactive visualization of all forecasts in the project - beta feature)
    Summary: Summary (interactive visualization/tabular summary of all - or a subset of - forecasts in the project)
    Explorer: Explorer (summarizes the subset of the most recent forecasts from each team)
    Download: Download (interface to start a query for any forecast data in the project)

    Models (4)

    Abbreviation Team # Forecasts Oldest Newest Upload time
    HJ_Consensus Computational Uncertainty Laboratory 6 2021-01-16 2021-06-16 2022-04-30 23:58:40 UTC
    Chimeric Computational Uncertainty Laboratory 6 2021-01-16 2021-06-16 2022-04-25 20:38:56 UTC
    GJOCon Computational Uncertainty Laboratory 0
    MetaculusCon Computational Uncertainty Laboratory 0

    Units (6)

    Abbreviation Name
    case incident cases
    death incident deaths
    hosp incident hospitalizations
    vaccine1 cumulative first-dose vaccinations
    vaccine2 cumulative full vaccinations
    variant variant prevalence

    Targets (33)

    Target Group # Targets Type Outcome Variable Step ahead? Example Target
    2021-01-24 case 1 continuous number of cases “2021-01-24 case”
    2021-01-24 death 1 continuous number of deaths “2021-01-24 death”
    2021-01-24 hosp 1 continuous number of hosps “2021-01-24 hosp”
    2021-02-01 variant 1 continuous variant prevalence “2021-02-01 variant”
    2021-02-21 case 1 continuous number of cases “2021-02-21 case”
    2021-02-21 death 1 continuous number of deaths “2021-02-21 death”
    2021-02-21 hosp 1 continuous number of hosps “2021-02-21 hosp”
    2021-02-28 vaccine1 1 continuous number of 1st dose vaccinations “2021-02-28 vaccine1”
    2021-03-21 case 1 continuous number of cases “2021-03-21 case”
    2021-03-21 death 1 continuous number of deaths “2021-03-21 death”
    2021-03-21 hosp 1 continuous number of hosps “2021-03-21 hosp”
    2021-03-21 variant 1 continuous variant prevalence “2021-03-21 variant”
    2021-03-29 variant 1 continuous variant prevalence “2021-03-29 variant”
    2021-03-31 vaccine1 1 continuous number of 1st dose vaccinations “2021-03-31 vaccine1”
    2021-03-31 vaccine2 1 continuous number of full vaccinations “2021-03-31 vaccine2”
    2021-04-24 variant 1 continuous variant prevalence “2021-04-24 variant”
    2021-04-25 case 1 continuous number of cases “2021-04-25 case”
    2021-04-25 death 1 continuous number of deaths “2021-04-25 death”
    2021-04-25 hosp 1 continuous number of hosps “2021-04-25 hosp”
    2021-04-30 vaccine1 1 continuous number of 1st dose vaccinations “2021-04-30 vaccine1”
    2021-04-30 vaccine2 1 continuous number of full vaccinations “2021-04-30 vaccine2”
    2021-05-23 variant 1 continuous variant prevalence “2021-05-23 variant”
    2021-05-30 case 1 continuous number of cases “2021-05-30 case”
    2021-05-30 death 1 continuous number of deaths “2021-05-30 death”
    2021-05-30 hosp 1 continuous number of hosps “2021-05-30 hosp”
    2021-05-31 vaccine1 1 continuous number of 1st dose vaccinations “2021-05-31 vaccine1”
    2021-05-31 vaccine2 1 continuous number of full vaccinations “2021-05-31 vaccine2”
    2021-06-27 case 1 continuous number of cases “2021-06-27 case”
    2021-06-27 death 1 continuous number of deaths “2021-06-27 death”
    2021-06-27 hosp 1 continuous number of hosps “2021-06-27 hosp”
    2021-06-27 variant 1 continuous variant prevalence “2021-06-27 variant”
    2021-06-30 vaccine1 1 continuous number of 1st dose vaccinations “2021-06-30 vaccine1”
    2021-06-30 vaccine2 1 continuous number of full vaccinations “2021-06-30 vaccine2”

    Time zeros (6)

    Time Zero Data Version Date # Forecasts Starts Season
    2021-01-16 (No data version date) 2
    2021-02-15 (No data version date) 2
    2021-03-15 (No data version date) 2
    2021-04-20 (No data version date) 2
    2021-05-18 (No data version date) 2
    2021-06-16 (No data version date) 2