• embed_me
    link
    fedilink
    arrow-up
    2
    ·
    6 days ago

    Yes, that requires a reference value to be decided upon beforehand.

    • driving_crooner@lemmy.eco.br
      link
      fedilink
      arrow-up
      4
      ·
      6 days ago

      Not really, you do t=n and t=n+1, for n= 1, 2, 3 for a quick view on volatility.

      Then ypu look up for correlations between e[t=n | t= 0, t= 1…] for different Ns. For more I would need to check out my notes

      • embed_me
        link
        fedilink
        arrow-up
        2
        ·
        6 days ago

        Oh I was imagining something entirely different. Like a simple logarithmic scale of a signal, I do not know anything about time series analysis. Should’ve kept my mouth shut