Suppose that follows a simple AR(1) model, that is, it can be expressed as , where is a white noise with mean equal to and variance . There are many examples in practice where these assumptions hold very well. Consider . We shall show that the autocorrelation function of characterizes the distribution of W-t.
“The final publication is available at Springer via http://dx.doi.org/10.1007/s00184-014-0497-5"
Moriña, D., Puig, P., Valero, J. A characterization of the innovations of first order autoregressive models. "MetrikA", 01 Febrer 2015, vol. 78, núm. 2, p. 219-225.