ensembleBMA: An R Package for Probabilistic Forecasting using Ensembles and Bayesian Model Averaging

Abstract

ensembleBMA is a contributed R package for probabilistic forecasting using ensemble postprocessing via Bayesian Model Averaging. It provides functions for parameter estimation via the EM algorithm for normal mixture models "appropriate for temperature or pressure" and mixtures of gamma distributions with a point mass at 0 "appropriate for precipitation" from training data. Also included are functions giving quantile forecasts based on these models, as well as for verification.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Aug 15, 2007
Accession Number
ADA478634

Entities

People

  • Adrian Raftery
  • Chris Fraley
  • J. M. Sloughter
  • Tilmann Gneiting

Organizations

  • University of Washington

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Abstracts
  • Bayesian Networks
  • Data Sets
  • Delphi Method
  • Distribution Functions
  • Freezing
  • Grids
  • Latitude
  • Longitude
  • Models
  • Observation
  • Plotting
  • Precipitation
  • Probability
  • Surface Temperature
  • Training
  • Verification

Readers

  • Atmospheric Science/Meteorology
  • Computer Science.
  • Statistical inference.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Machine Learning Algorithms