plotPRD: Prediction-Realization Diagram for the given data from...

In svcuonghvktqs/FORA: A package for time sereis forecast accuracy evaluation

Description

This function plots Prediction-Realization Diagram for the given data from dataset for different methods.

Usage

plotPRD(df, useLogs = FALSE, xlim = NULL, ylim = NULL)

Arguments

df	A data frame containing columns "actual", "forecast", and "method".
useLogs	logical. If TRUE the resulting prediction-relization digram plotted in logarithmic scales. If FALSE the resulting prediction-relization diagram plotted in scales by default.
xlim	The minimum and maximum values on the axis "Ox". If xlim is NULL, minimum and maximum values are calculated based on given data.
ylim	The minimum and maximum values on the axis "APE"Oy". If ylim is NULL, minimum and maximum values are calculated based on given data.

Value

plotPRD function plots Prediction-Realization Diagram for the given data from dataset.

Author(s)

Sai Van Cuong, Maixm Shcherbakov and Andrey Davydenko

References

Jacob A. Mincer and Victor Zarnowits (1969) Volume title: "Economic Forecasts and Expectations: Analysis of Forecasting Behavior and Performance".Chapter title: The Evaluation of Economic Forecasts. Chapter pages in book: (p.3-46). http://www.nber.org/chapters/c1214.pdf.

See Also

boxplotPEs, boxplotAPEs

Examples

plotPRD(df = FORAYearForecast)
plotPRD(df = FORAYearForecast, useLogs = FALSE, xlim = c(23000, 30000), ylim = c(22000, 31000))
data1 <- subset(FORAYearForecast, actual >= 5000| forecast < 8000)
data2 <- FORAYearForecast[1:300,]
plotPRD(df = data1, useLogs = FALSE, xlim = c(23000, 30000), ylim = c(22000, 31000))
plotPRD(df = data2, useLogs = FALSE, xlim = c(23000, 30000), ylim = c(22000, 31000))

svcuonghvktqs/FORA documentation built on May 20, 2019, 9:57 a.m.