NavList:
A Community Devoted to the Preservation and Practice of Celestial Navigation and Other Methods of Traditional Wayfinding
Re: Rejecting outliers: was: Kurtosis.
From: George Huxtable
Date: 2011 Jan 2, 21:36 -0000
From: George Huxtable
Date: 2011 Jan 2, 21:36 -0000
I had written, earlier today, that- "That's by no means conclusive; no more than suggestive, that the calculated slope of 32 may be somewhat suspect. It would be worth checking it out once again, to be sure. The quoted latitude of 34� corresponds with the (South) lat. of his home port of Sydney, so is unlikely to be wrong, but what about the calculated azimuth of 149�? We haven't been given sufficient information to check that for ourselves; perhaps we can be provided with the missing details." But indeed, we were given the name of the body being sighted, as Canopus, which does provide sufficient information to check out the azimuth and therefore the calculated slope. And this really does turn out to be around 32' per 5-minute period, and not 24'. So imposing such a known rate-of change, as in the second of the methods I listed, is a better way to go than allowing the slope to be freely determined from the data, as in the fourth method. However, neither will do any better than taking the simple mean of amplitudes and times, as every such best-fit line, no matter what its slope, must pass exactly through the mean point marked as P. George. contact George Huxtable, at george{at}hux.me.uk at +44 1865 820222 (from UK, 01865 820222) or at 1 Sandy Lane, Southmoor, Abingdon, Oxon OX13 5HX, UK.