I have checked out the answer to this question on stats.stackexchange: What are good resources providing a history of statistics? Indeed, the Stigler book "Statistics on the Table" looks excellent and I'm looking forward to reading it. But I'm more interested in the development of modern ARIMA models.
I think I remember hearing that much progress was stimulated in trying to predict random inaccuracies with artillery guns around WWII. Also, of course, to some extent astronomers throughout the second half of the millennium were using some sort of time series for understanding the motion of heavenly bodies. However, I can't remember where I heard about the artillery application of time series and I have a background in physics, and I don't really know what statistical methods the astronomers were working with.
So, I would love to hear what you think are the most pertinent historical influences on the development of time series methods, e.g., were they stimulated mainly by finance, defense, geology/geophysics, or some combination of all these and more? Are there informative books or websites on the history of ARIMA?