I have a non-stationary AR(1)-process. After taking the first difference, how can I derive the MA representation of the resulting „difference process“ Delta_xt?

As an example, consider

xt = 1.5xt-1 + et

<=> (xt-xt-1=) Delta_xt = 0.5xt-1 + et.

How can I convert this process Delta_xt into an MA process?

  • $\begingroup$ You don't do differencing. You do back substitution, So substitute 1.5 X(t-2) + e(t-1) for X(t-1) making X(t) = (1.5)$^2$ X(t-2) + 1.5 e(t-1) + e(t) and continue t substitute for X(t-2) and so forth in the same way to get the infinite moving average representation. The infinite series of the e(t) is divergent which shows that the process is non stationary $\endgroup$ – Michael Chernick Jan 20 '18 at 2:25
  • $\begingroup$ But I am looking for the MA representation of the „difference-process“ Delta_xt. I don’t want the MA of the original process. $\endgroup$ – Abc123 Jan 20 '18 at 2:42
  • $\begingroup$ That isn't what your title said and it wasn't explained in the question. $\endgroup$ – Michael Chernick Jan 20 '18 at 2:58
  • $\begingroup$ I changed the text and hope that my question is clearer now. I would still appreciate any help $\endgroup$ – Abc123 Jan 20 '18 at 3:07

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.