NavList:
A Community Devoted to the Preservation and Practice of Celestial Navigation and Other Methods of Traditional Wayfinding
Re: Averaging
From: George Huxtable
Date: 2004 Oct 19, 21:51 +0100
From: George Huxtable
Date: 2004 Oct 19, 21:51 +0100
Chuck Taylor sent this message- >George Huxtable wrote, concerning the concept of >averaging observed sextant altitudes over time: > >"But I don't see how you would apply that >technique to a quantity that was changing >systematically, in the way that observed altitudes >change rather steadily with time (either >increasing or decreasing), with a bit of random >scatter superimposed." ========================== No. Chuck has that quite wrong; perhaps I didn't make myself clear.. That's what I wrote, in response to a posting by Federico Rossi, but it wasn't "concerning the concept of averaging sextant distances over time." Federico Rossi had written, about averaging an odd number of observations- >The explanation I've found for this recommendation is that this way you >can consider the central value of the odd series (i.e. the so called >median) which is definitely less affected by abnormal values than the >average value. And I replied- "Selecting a median that way seems to be an alternative to averaging. It's a rather extreme case of discarding outliers, in that it discards EVERYTHING but the one median observation. I can see that it might be usable (if not ideal) for dealing with a quantity that fluctuates in a random manner. But I don't see how you would apply that technique to a quantity that was changing systematically, in the way that observed altitudes change rather steadily with time (either increasing or decreasing), with a bit of random scatter superimposed." ================= What I didn't see, was how you could apply the technique of CHOOSING A MEDIAN VALUE (as Federico suggested) to a series of measurements that varied with time, as altitudes do. I see no problem, none at all, in applying an AVERAGING technique to such a series of measurements. George ================================================================ contact George Huxtable by email at george@huxtable.u-net.com, by phone at 01865 820222 (from outside UK, +44 1865 820222), or by mail at 1 Sandy Lane, Southmoor, Abingdon, Oxon OX13 5HX, UK. ================================================================