cochrane.orcutt.jva: Cochrane-Orcutt Estimation
In JVAdams/jvamisc: A Collection of Utility Functions

Description Usage Arguments Details Value References See Also Examples

Interactive method using to solve first order autocorrelation problems. This procedure estimates both autocorrelation and beta coefficients recursively until we reach the convergence (8th decimal). The residuals are computed after estimating Beta using EGLS approach and Rho is estimated using the previous residuals.

1	cochrane.orcutt.jva(reg, convergence = 8, max.iter = 100)

`reg`	a linear model built with lm function
`convergence`	decimal value to reach for convergence, 8 as default
`max.iter`	the maximum number of iterations to try before giving up on convergence, 100 as default

This is a duplicate of the cochrane.orcutt() function from package orcutt version 2.2, with the addition of an upper limit on the number of iterations to avoid an infinite while() loop.

An object of class "orcutt". See cochrane.orcutt

Verbeek M. (2004) A guide to modern econometrics, John Wiley & Sons Ltd, ISBN:978-88-08-17054-5

cochrane.orcutt

# example from orcutt package that converges
  data(icecream, package="orcutt")
  lm <- lm(cons ~ price + income + temp, data=icecream)
  cochrane.orcutt.jva(lm)
# another example that doesn't converge
  mydat <- data.frame(year=2013:2017, meas=c(14.8, 10.7, 6.2, 4, 3.9))
  lmfit <- lm(meas ~ year, data=mydat)
  cochrane.orcutt.jva(lmfit)