NavList:
A Community Devoted to the Preservation and Practice of Celestial Navigation and Other Methods of Traditional Wayfinding
Re: Linear Regression In Reverse
From: George Huxtable
Date: 2005 Jun 5, 15:50 +0100
From: George Huxtable
Date: 2005 Jun 5, 15:50 +0100
I'm still in a bit of difficulty over Peter Fogg's proposal for determining altitude of a body at the exact moment it's on the observer's prime vertical (his East-West line). >George has written, on the process of LINEAR REGRESSION IN REVERSE: > >> I just don't understand what Peter is proposing here. My fault, rather >> than >> his, no doubt. >> >> Could he provide a bit more detail, please, perhaps with an example? >> Couldn't the moment, at which the Sun was theoretically on the East-West >> line, be precalculated ... > >Yes, precalculation is what I am proposing, to give the moment of east or >west azimuth (prime vertical). How is that precalculation done, I ask? What's the expression that's used to provide the moment when the body is exactly East or West? I can see that it could be determined by plugging an azimuth of 90 degrees into a standard navigational triangle, but what's the resulting trig expression? Presumably the precalculation is based on an assumed position. How sensitive is the result to errors in that assumed position, and does that matter? Does the method provide for reiteration if the observation shows up significant errors in that assumed position? How important is it, anyway, to know the exact moment when the Sun is on the prime vertical? As I see it, it's a very undemanding requirement. > >Then a series of observations of the body (it can be any celestial object >for which almanac data is available, just as observation of meridian passage >can, in theory, be made with any body). > >From then on it is the application of what seems a favourite hobby-horse of >mine, comparing the slope with the sights. Is this a precalculated slope? If so, how is it calculated? What's the expression used to give the slope? What's the slope used for? If the calculated slope doesn't correspond with the observed slope of the sights, around the precalculated moment, what happens next? Is something then adjusted to fit? Its something I have written >about here time and again; once with the title 'Good Data from Bad'. Now >there's an approach you can appreciate. > >The practical advantage here is that it is not necessary to manage to make a >timed observation at exactly the precalculated moment. So long as a series >of sights encompasses that moment the time can be selected later from the >graphed time axis and related, via the slope, to its accompanying altitude >on the other axis. To clarify matters to me, let me ask: If you DID manage to make that altitude observation at exactly that precalculated moment, would any of this "slope" business be required? >Rather than churn out more words I would encourage you to provide your own >example, just as I have with Fred. Give it a whirl. I hesitate to say much >more; for fear of becoming a bore just banging on about his id?e fixe, but I >will say that the moment I understood this slope method was an Eureka moment >for me and it has become part of the process of timed sights, just like >recording the compass bearing of the body at the time of observation. Good >or bad, the only reason I do these things is because they work a treat. ================= Peter, please don't hesitate to say more, in response to these requests, to explain just what you do and how you do it. In those circumstances, nobody will accuse you of "just banging on about his idee fixe". I don't see how you can expect me to "provide my own example", when your methods remain unclear to me (perhaps because of my own naivety). Only you can do that, to illustrate those very methods. > >How do you like the new name: LINEAR REGRESSION IN REVERSE. Nifty, huh? It's not what it's called, it's what it DOES, that's more important. George. =============== In a later message, Peter added- >George asked, on the subject of Reverse Linear Regression (is this a better >version of my identifying title?): > >> Could he provide a bit more detail, please, perhaps with an example? > >Hidden away in a back alley of the Starpath site is an informative article >on this, complete with an example showing how this technique is superior for >its purpose; compared to its relative with whom it is often confused: linear >regression. > >The other one-stop shop that has everything needed: example, slope >calculator, the form incorporating graph paper specifically designed for the >purpose (and much more) is George Bennett's book "The Complete On-Board >Celestial Navigator". It is available from Celestaire, who deserve our >patronage and support, being uniquely dedicated to supplying the tools >navigators need. ============= Well, I wasn't asking about the general topic of linear regression (reversed or otherwise) but about the specific details of how Peter himself carries out his observation and analysis, questions that I have spelled out in detail above. Bennett's book provides no answers to those questions. Somehow, I doubt whether "a back alley of the Starpath site", to quote Peter's woolly reference, would do so either. A direct response from Peter is requested, please. 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. ================================================================