Let's assume we have a CNC machine cutting an aluminium block and we are monitoring its RMS power consumption at a constant sample rate e.g. 1Hz (see figure below for example). Can this considered to be a time-series signal? This link states that time-series should show some internal structure, others could argue that any signal observed over time can be described as time-series.


If the example above is not a time-series, what else could you call that signal?

  • $\begingroup$ The definition in your reference makes no mention of "internal structure." $\endgroup$
    – whuber
    Sep 22 '17 at 17:09
  • $\begingroup$ You are right. The link I posted however, (which is from the same source) states that "Time series analysis accounts for the fact that data points taken over time may have an internal structure (such as autocorrelation, trend or seasonal variation) that should be accounted for." I guess that's where my confusion comes in. $\endgroup$
    – DimP
    Sep 24 '17 at 18:06
  • $\begingroup$ @whuber Btw, thanks for the linked question. I am not quite sure if it is exactly the same as mine, but helps understanding the definition of time-series. I would conclude the above signal is a time-series indeed, to my best understanding. $\endgroup$
    – DimP
    Sep 24 '17 at 18:13
  • 1
    $\begingroup$ A key to interpreting your quotation is the word "may," which does not imply "must have." $\endgroup$
    – whuber
    Sep 25 '17 at 13:18