fit_best: Estimates the Best Equation...

In gu-stat/gears: GEARS Method for Univariate and Multivariate Time Series Forecasting

Description

Given the number of the equation that minimizes the selected error measure, fit_best estimates the equation for each rolling sample and forecast lead.

Usage

fit_best(
  forecast.lead,
  eq.number,
  sample.number,
  glm.family,
  Y.name,
  all.equations.rhs,
  DF.Fit.Predict,
  ...
)

Arguments

forecast.lead	Number of the forecast lead.
eq.number	Number (position)of the equation in the vector of all possible equations.
sample.number	Number of the specific random sample that will be evaluated.
glm.family	A description of the error distribution to be used in the model. Inherits from gears.
Y.name	Name of the y variable (variable to be forecasted) created by gears.
all.equations.rhs	Vector with all possible combinations of right-hand side variables.
DF.Fit.Predict	a data frame with training data and test data for the estimation estage.
...	Additional parameters passed to glm.

Value

Returns an object of class inheriting from "glm" (see glm).

gu-stat/gears documentation built on Oct. 20, 2021, 2:53 a.m.