ensembleBMA (version 2.0)

gridForecastBMA: BMA forecasts for a grid of ensemble predictions.

Description

Computes quantiles for the probability distribution function (PDF) of an ensemble BMA mixture model at a grid of locations.

Usage

gridForecastBMA( object, gridData, quantiles = 0.5, 
                 date = NULL, popData = NULL, ...)

Arguments

object

An ensemble BMA model fit.

gridData

A two- or three dimensional array. If two dimensional, the rows represents spatial locations on a grid the columns represent the ensemble forecasts at each location. If three dimensional, the for two dimension represents spatial locations

quantiles

The vector of desired quantiles for the PDF of the BMA mixture model.

date

For ensembleBMAgamma0 and ensembleBMAnormal objects, there is an additional date argument, giving a character representation of the date for which the grid forecast is desired. date must

popData

For ensembleBMAgamma0 and fitBMAgamma0 objects, there is an additional popData argument for providing predictors in the logistic regression for probability of precipitation. The value of popData

...

Included for generic function compatibility.

Value

• A three dimensional grid in which the first two dimensions represent spatial locations as in the input and the third dimension gives the desired quantile forecasts at each location.

Details

This method is generic, and can be applied to any ensemble BMA forecasting model. Note the model may have been applied to a transformation of the data, but that information is included in the input object, and the output is transformed appropriately. This can be used to compute confidence intervals for the PDF.

References

A. E. Raftery, T. Gneiting, F. Balabdaoui and M. Polakowski, Using Bayesian Model Averaging to Calibrate Forecast Ensembles, Monthly Weather Review 133:1155-1174, 2005.

V. J. Berrocal, A. E. Raftery and T. Gneiting, Combining Spatial and Ensemble Information in Probabilistic Weather Forecasts, Technical Report no. 495, Department of Statistics, University of Washington, February 2006.

See Also

ensembleBMA, fitBMA, quantileForecastBMA

Examples

data(srft)
  data(srftGrid)

  srftData <- ensembleData(dates = srft$date, observations = srft$observation,
  forecasts = srft[c("CMCG","ETA","GASP","GFS","JMA","NGPS","TCWB","UKMO")])

  srftFeb14fit1 <- ensembleBMAnormal( srftData, date = "2004021400",
                                     trainingRule = list(length=25, lag=2))

  gridForecastBMA(srftFeb14fit1, srftGrid[,1:ensembleSize(srftData)], 
                  date = "2004021400")

  trainingFeb14data <- trainingData( srftData, date = "2004021400",
                                 trainingRule = list(length=25, lag=2))

  srftFeb14fit2 <- fitBMAnormal( trainingFeb14data)

  gridForecastBMA(srftFeb14fit2, srftGrid[,1:ensembleSize(srftData)], 
                  date = "2004021400")