NavList:

   

Reply

I think it would be interesting to see the results of various
methods.  But I must confess, I use "Mark I eyeball" to estimate best
fit.

Thomas A. Sult, MD
3rd Opinion
1415 First First St. South #5
Willmar, MN 56201
320 235 2101 Office
www.3rdOpinion.us
tsult@mac.com






On Dec 9, 2010, at 3:51 PM, George Huxtable wrote:

> Peter Fogg wrote-
>
> "3. Use of the slope technique, using the calculated slope, is the
> best
> method presently known to reduce random observational error."
>
> That is no more than an assertion, one that Peter Fogg has been making
> repeatedly for some years. He has claimed that he can get closer to
> the
> truth than can a statistical least-squares fit, or simply averaging
> the
> observations for time and altitude.
>
> Recently-joined Navlist members will not be aware that a year or two
> back,
> I posted several sets of artificially-generated observations, with
> slope
> and intercept known (but not disclosed). These data points had then
> been
> perturbed by having computer-generated random offsets added to them,
> to
> simulate real data, as closely as was possible..
>
> Peter Fogg was then challenged to apply whatever methods he chose,
> to show
> us whether he could discover those original undisclosed values, more
> precisely than could be done by a standard statistical analysis. He
> declined to take part.
>
> That test could always be repeated, whenever Peter Fogg chooses.
>
> George.
>
> contact George Huxtable, at  george@hux.me.uk
> or at +44 1865 820222 (from UK, 01865 820222)
> or at 1 Sandy Lane, Southmoor, Abingdon, Oxon OX13 5HX, UK.
>
>
>
>

   

Reply