qpred: Quantile function of IDR or raw forecasts

In isodistrreg: Isotonic Distributional Regression (IDR)

Description

Evaluate the the quantile function of IDR predictions or of unprocessed forecasts in a data.frame.

Usage

qpred(predictions, quantiles)

## S3 method for class 'idr'
qpred(predictions, quantiles)

## S3 method for class 'data.frame'
qpred(predictions, quantiles)

Arguments

predictions	either an object of class idr (output of predict.idrfit), or a data.frame of numeric variables. In the latter case, quantiles are computed using the empirical distribution of the variables in predictions.
quantiles	numeric vector of desired quantiles.

Details

The quantiles are defined as lower quantiles, that is,

q(u) = inf(x: cdf(x) >= u).

Value

A matrix of forecasts for the desired quantiles, one column per quantile.

See Also

predict.idrfit, cdf, qscore

Examples

data("rain")

## Postprocess HRES forecast using data of 3 years

X <- rain[1:(3 * 365), "HRES", drop = FALSE]
y <- rain[1:(3 * 365), "obs"]

fit <- idr(y = y, X = X)

## Compute 95%-quantile forecast given that the HRES forecast is
## 2.5 mm, 5 mm or 10 mm

predictions <- predict(fit, data = data.frame(HRES = c(2.5, 5, 10)))
qpred(predictions, quantiles = 0.95)

isodistrreg documentation built on March 22, 2021, 5:06 p.m.