plotCoverage: Coverage Probability Plot

In forvis/forvision: Tools for forecast visualisation and evaluation

Description

Generates a coverage probability plot showing coverage probability estimates, corresponding error bands, and nominal coverage probability.

Usage

plotCoverage(af, pi, methods = NULL, horizons = NULL,
  conf.level = 0.95, coord.flip = FALSE)

Arguments

af	dataframe containing forecast data formatted using the Actual and Forecast Table Schema (AFTS), use showAFTS() to display schema specification details.
pi	nominal coverage probability (confidence level for the prediction interval to be assessed).
methods	array containing method_id values for methods to be shown on the graph, if NULL, all available methods will be shown.
horizons	array containing horizons to be shown on the graph, if NULL, all available horizons will be shown.
conf.level	confidence level for coverage probability estimates, default 0.95.
coord.flip	use FALSE for horizontal bar chart, TRUE for vertical.

Details

Generates a bar chart showing coverage percentages for the given nominal coverage (Sai, Davydenko, and Shcherbakov, 2018). The results are confined to methods contained in methods and horizons contained in horizons. Adds error bars and nominal coverage line to chart.

Value

Returns a ggplot2 object containing the coverage probability plot.

Author(s)

Cuong Sai, Andrey Davydenko, and Maxim Shcherbakov.

References

Sai, C., Davydenko, A., & Shcherbakov, M. (2018, November). Data schemas for forecasting (with examples in R). Seventh International Conference on System Modelling & Advancement on Research Trends, 145-149. Moradabad, India.

Examples

af <- createAFTS(example1_ts, example1_fc)
plotCoverage(af, pi = 90, methods = c("A", "B"))
plotCoverage(af, pi = 90, horizons = 1:2)

forvis/forvision documentation built on April 30, 2020, 3:28 a.m.