Learn R Programming

scoringfunctions (version 1.2)

bmedian_rs: Realised \(\beta\)-median score

Description

The function bmedian_rs computes the realised \(\beta\)-median score with parameter \(b\), when \(\textbf{\textit{y}}\) materialises and \(\textbf{\textit{x}}\) is the prediction.

Realised \(\beta\)-median score is a realised score corresponding to the \(\beta\)-median scoring function bmedian_sf.

Usage

bmedian_rs(x, y, b)

Value

Value of the realised \(\beta\)-median score.

Arguments

x

Prediction. It can be a vector of length \(n\) (must have the same length as \(\textbf{\textit{y}}\)).

y

Realisation (true value) of process. It can be a vector of length \(n\) (must have the same length as \(\textbf{\textit{x}}\)).

b

It can be a scalar.

Details

The realised \(\beta\)-median score is defined by:

$$S(\textbf{\textit{x}}, \textbf{\textit{y}}, b) := (1/n) \sum_{i = 1}^{n} L(x_i, y_i, b)$$

where

$$\textbf{\textit{x}} = (x_1, ..., x_n)^\mathsf{T}$$

$$\textbf{\textit{y}} = (y_1, ..., y_n)^\mathsf{T}$$

and

$$L(x, y, b) := |1 - (y/x)^b|$$

Domain of function:

$$\textbf{\textit{x}} > \textbf{0}$$

$$\textbf{\textit{y}} > \textbf{0}$$

$$b \neq 0$$

where

$$\textbf{0} = (0, ..., 0)^\mathsf{T}$$

is the zero vector of length \(n\) and the symbol \(>\) indicates pairwise inequality.

Range of function:

$$S(\textbf{\textit{x}}, \textbf{\textit{y}}, b) \geq 0, \forall \textbf{\textit{x}}, \textbf{\textit{y}} > \textbf{0}, b \neq 0$$

References

Fissler T, Ziegel JF (2019) Order-sensitivity and equivariance of scoring functions. Electronic Journal of Statistics 13(1):1166--1211. tools:::Rd_expr_doi("10.1214/19-EJS1552").

Gneiting T (2011) Making and evaluating point forecasts. Journal of the American Statistical Association 106(494):746--762. tools:::Rd_expr_doi("10.1198/jasa.2011.r10138").

See Also

bmedian_sf

Examples

Run this code
# Compute the realised beta-median score.

set.seed(12345)

b <- 2

x <- 0.5

y <- rlnorm(n = 100, meanlog = 0, sdlog = 1)

print(bmedian_rs(x = x, y = y, b = b))

print(bmedian_rs(x = rep(x = x, times = 100), y = y, b = b))

Run the code above in your browser using DataLab