mase

MASE is computed as \(sum(abs(validation - forecast)) / sum(abs(validation[-1] - validation[-n])) / (n/(n-1))\).

Various algorithms related to linguistic fuzzy logic: mining for linguistic fuzzy association
rules, composition of fuzzy relations, performing perception-based logical deduction (PbLD),
and forecasting time-series using fuzzy rule-based ensemble (FRBE). The package also contains basic
fuzzy-related algebraic functions capable of handling missing values in different styles (Bochvar,
Sobocinski, Kleene etc.), computation of Sugeno integrals and fuzzy transform.

Michal Burda

Linguistic Fuzzy Logic

mase function

<dl><dt>forecast</dt>
<dd>A numeric vector of forecasted values</dd>
<dt>validation</dt>
<dd>A numeric vector of actual (real) values</dd></dl>

Arguments

Author

Compute Mean Absolute Scaled Error (MASE) — mase

<dl>

<dt>forecast</dt>
<dd>A numeric vector of forecasted values</dd>


<dt>validation</dt>
<dd>A numeric vector of actual (real) values</dd>

</dl>

mase: Compute Mean Absolute Scaled Error (MASE)

Description

Usage

Value

Arguments

Author

See Also