I am a econometrics student, and I've to understand what type of process the one in the image below is. I am not able to go back to the main classic stochastic processes (AR, MA, ARMA, ARCH/GARCH). In particular, the fact that epsilon is multiplied and not added generated confusion in me. Epsilon is a Gaussian white noise Thanks!

enter image description here


closed as unclear what you're asking by whuber Nov 25 '18 at 21:01

Please clarify your specific problem or add additional details to highlight exactly what you need. As it's currently written, it’s hard to tell exactly what you're asking. See the How to Ask page for help clarifying this question. If this question can be reworded to fit the rules in the help center, please edit the question.

  • 1
    $\begingroup$ So $\{X_t\}$ is a complex valued? Are you sure $\epsilon_t$ is Gaussian (rather than something else like lognormal)? $\endgroup$ – Matthew Gunn Nov 25 '18 at 20:14
  • $\begingroup$ Yes, epsilon is the disturbance distribuited as a Normal. {Xt} is simply the value of the process at time t. But for example in an Autoregressive process I expect that the disturbance is added not multiplied. $\endgroup$ – White Noise Nov 25 '18 at 20:26
  • $\begingroup$ For $X_t$ to be well-defined, you need to specify which square root you are taking, especially (but not only) for negative or complex values. If this isn't perfectly clear, write a (simple) program to simulate a realization of this process: it will run into trouble the first time $X_{t-1}$ is negative, which will happen quickly. $\endgroup$ – whuber Nov 25 '18 at 21:01
  • $\begingroup$ @whuber thanks for the answer. The exercise must be done without any simulation, it's a written test. I have to tell which type of process is it among the ones studied during the course, and then obtain the autocorrelation function. I think we'are dealing only with real numbers. $\endgroup$ – White Noise Nov 25 '18 at 21:08
  • 1
    $\begingroup$ @whuber really thanks for all the answers. There was a typo in the original source. Thanks a lot $\endgroup$ – White Noise Nov 26 '18 at 22:02