NavList:
A Community Devoted to the Preservation and Practice of Celestial Navigation and Other Methods of Traditional Wayfinding
Re: Averaging
From: Jim Thompson
Date: 2004 Oct 19, 17:35 -0300
From: Jim Thompson
Date: 2004 Oct 19, 17:35 -0300
> -----Original Message----- > From: Herbert Prinz > the discussion has gone into the very wrong direction that I was > afraid it would. We are proposing methods to average before > having justified > that averaging is appropriate at all. It seems that I have not > made sufficiently > clear why I said from the outset that it is wrong to average the > observations > before reducing them. Let me therefore address this point once more. Herbert is clearly correct to react this way to my post about Excel: on the face of it I appeared to be advocating "willy-nilly statistics" by suggesting that the navigator plot the run of sights on a graph in Excel, then click around the various statistical model options until Excel produces a line that looks cool, and then use that to produce best fit line, without having to think hard or apply first principles. I hasten to mention that I was not advocating such a dangerous approach. As Herbet points out, unless one knows with certainty the model that applies to the body's motion for the specific situation, and unless the correct first steps have been taken to select appropriate sights to plot, and unless the navigator has taken enough sights for the computer to produce a valid line, then the Excel method is too crude. It can, however, be a useful way to quickly double-check situations, if the navigator bears all these concerns in mind: http://jimthompson.net/boating/CelestialNav/MyNoonSun.htm and scroll down to "Method 4b". Ignore the ridiculous degree of precision in the polynomial equation constants generated by Excel. Jim