1

I am trying to estimate a MIDAS regression on a subsample of my data using the window function. However, when I use this, the midas_r() function throws me back the error:

Error in prepmidas_r(y, X, mt, Zenv, cl, args, start, Ofunction, weight_gradients, : Starting values for weight parameters must be supplied

Here is my code:

install.packages("midasr")
library(midasr)
yrs <- 10
x <- ts(rnorm(12*yrs),start=c(1900,1),frequency = 12)
y <- ts(rnorm(yrs),start=c(1900,1))

midas_r(y~fmls(x,3,12,nealmon),start=list(x=rep(0,3)))

x_est <- window(x,end=c(1910,0))
y_est <- window(y,end=(1910))

midas_r(y_est~fmls(x_est,3,12,nealmon)+1,start=list(x=rep(0,3)))

Does anyone know what's the issue? Thanks in advance!

Werner Hertzog
  • 2,002
  • 3
  • 24
  • 36
dinochka314
  • 11
  • 2

1 Answers1

0

The issue is in list(x=rep(0, 3)). This list has indeed to be named, but this name needs to coincide with the variable name. Hence,

midas_r(y_est ~ fmls(x_est, 3, 12, nealmon), start = list(x_est = rep(0, 3)))

works.

Julius Vainora
  • 47,421
  • 9
  • 90
  • 102