Title: | The Use of Marginal Distributions in Conditional Forecasting |
---|---|
Description: | A new way to predict time series using the marginal distribution table in the absence of the significance of traditional models. |
Authors: | Mohamad-Taher Anan [aut], Mohamad Alawad [aut], Bushra Alsaeed [aut, cre] |
Maintainer: | Bushra Alsaeed <[email protected]> |
License: | GPL-3 |
Version: | 0.1.1 |
Built: | 2024-12-16 06:37:12 UTC |
Source: | CRAN |
A new way to predict time series using the marginal distribution table in the absence of the significance of traditional models.
ff(dt,m,w,n,q1)
ff(dt,m,w,n,q1)
dt |
data frame |
m |
the number of time series |
w |
the number of predicted values |
n |
number of values |
q1 |
matrix independent time series values #In the case of m=2, enter the independent string values as follows(matrix(c())),In the case of m=3, enter the independent string values as follows(matrix(c(),w,m-1,byrow=T)) |
the output from ff()
x=rnorm(17,10,1) y=rnorm(17,10,1) data=data.frame(x,y) print("Enter independent time series values") q1=list(q=matrix(c(scan(,,quiet=TRUE)),1,2-1)) 10.5 ff(data,2,1,17,q1)
x=rnorm(17,10,1) y=rnorm(17,10,1) data=data.frame(x,y) print("Enter independent time series values") q1=list(q=matrix(c(scan(,,quiet=TRUE)),1,2-1)) 10.5 ff(data,2,1,17,q1)