performance_weighted_forc {lmForc}

MSE or RMSE weighted forecast

Description

performance_weighted_forc takes two or more forecasts, an evaluation window, and an error function. For each forecast period, the error function is used to calculate forecast accuracy over the past eval_window number of periods. The forecast accuracy of each forecast is used to weight forecasts based on performance. Returns a weighted forecast. Optionally returns the set of weights used to weight forecasts in each period.

Usage

performance_weighted_forc(
  ...,
  eval_window,
  errors = "mse",
  return_weights = FALSE
)

Arguments

...

Two or more forecasts of class Forecast.

eval_window

Integer representing the window over which forecast accuracy is evaluated. Forecasts are weighted based on their accuracy over the past eval_window number of periods.

errors

Character, either "mse" or "rmse". Selects whether forecast accuracy is evaluated using mean squared errors or root mean squared errors.

return_weights

Boolean, selects whether the weights used to weight forecasts in each period are returned. If TRUE, a data frame of weights is returned to the Global Environment.

Details

Forecasts are weighted in each period with the following function. The error function used is MSE or RMSE depending on user selection. This example shows MSE errors.

weight = (1 / MSE(forecast)) / (1 / sum(MSE(forecasts)))

Value

Forecast object that contains the weighted forecast.

See Also

For a detailed example see the help vignette: vignette("lmForc", package = "lmForc")

Examples

y1_forecast <- Forecast(
  origin = as.Date(c("2009-03-31", "2009-06-30", "2009-09-30", "2009-12-31",
                     "2010-03-31", "2010-06-30", "2010-09-30", "2010-12-31", 
                     "2011-03-31", "2011-06-30")),
  future = as.Date(c("2010-03-31", "2010-06-30", "2010-09-30", "2010-12-31",
                     "2011-03-31", "2011-06-30", "2011-09-30", "2011-12-31", 
                     "2012-03-31", "2012-06-30")),
  forecast = c(1.33, 1.36, 1.38, 1.68, 1.60, 1.55, 1.32, 1.22, 1.08, 0.88),
  realized = c(1.09, 1.71, 1.09, 2.46, 1.78, 1.35, 2.89, 2.11, 2.97, 0.99),
  h_ahead = 4L
)

y2_forecast <- Forecast(
  origin = as.Date(c("2009-03-31", "2009-06-30", "2009-09-30", "2009-12-31",
                     "2010-03-31", "2010-06-30", "2010-09-30", "2010-12-31", 
                     "2011-03-31", "2011-06-30")),
  future = as.Date(c("2010-03-31", "2010-06-30", "2010-09-30", "2010-12-31",
                     "2011-03-31", "2011-06-30", "2011-09-30", "2011-12-31", 
                     "2012-03-31", "2012-06-30")),
  forecast = c(0.70, 0.88, 1.03, 1.05, 1.01, 0.82, 0.95, 1.09, 1.07, 1.06),
  realized = c(1.09, 1.71, 1.09, 2.46, 1.78, 1.35, 2.89, 2.11, 2.97, 0.99),
  h_ahead = 4L
)

performance_weighted_forc(
  y1_forecast, y2_forecast,
  eval_window = 2L,
  errors = "mse",
  return_weights = FALSE
)