NavList:
A Community Devoted to the Preservation and Practice of Celestial Navigation and Other Methods of Traditional Wayfinding
Re: On checking accuracy
From: Bill Morris
Date: 2008 Aug 10, 13:08 -0700
From: Bill Morris
Date: 2008 Aug 10, 13:08 -0700
Peter Fogg wrote "All sights are not created equally. Some are better than others. The good ones tend to be closest to that slope." Would it not be truer to say that the good ones tend to have aclosest to that slope? And he wrote "Such irony. The closed mind that has decided in advance just what is permissible, in this case the reduction of random error, and anything else must be wrong. We might as well be back in the Dark Ages. " I have been following the arguments closely. I perfectly understand the point Peter is making but have doubts that it is a valid one. I haven't reached a conclusion and await further enlightenment, perhaps from a professor of applied statistics, i.e. in my ignorance I make an appeal to authority. It is curious how in such intense discussions phrases such as "closed mind" crop up. I think an open mind is good, but try to take care that mine is not so open that my brains drop out. And Bill B. wrote "He should be severally chastised for saying "line" instead of "line > segment." Ouch! Do the end points lie on the horizon? On Aug 10, 11:05�pm, Bill wrote: > Bill the engineer wrote: > > There is an infinity of > > possible lines of that slope > > Peter responded: > > > Yes. �But only one of them is correct. �Its that correct one we are working > > towards. �Having the right slope to begin with tends to be quite useful, > > instead of deriving an incorrect one. > > > and the line that best uses the > > data(since we have no information about which are "best") > > My initial impression was that Bill the engineer was suggesting different > slopes and different placements. �Reading carefully, he stated "There is an > infinity of possible lines OF THAT SLOPE." �He does not, I think, argue with > the concept of fitting to the actual slope, but rather questions, as I did, > how to make the agonizing decision of where (horizontally and vertically) I > should place the slope in relationship to the plotted points. > > He should be severally chastised for saying "line" instead of "line > segment." > > But let's hear from him before we raise our back hair. > > Bill B. � --~--~---------~--~----~------------~-------~--~----~ Navigation List archive: www.fer3.com/arc To post, email NavList@fer3.com To , email NavList-@fer3.com -~----------~----~----~----~------~----~------~--~---