Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > sci.stat.math > #10812

Re: statistics in Roberts. Was: RAW vs. raw image format

Cross-posted to 2 groups.

Show all headers | View raw

David Jones:

> The paper is extremely difficult to understand and I have
> tried very hard..

Thank you!  That makes four people who have found it
unclear.

> There seems a possibility that you are over-interpreting
> what the author means by "chi-squared". I have heard some
> non-statistical experts in other fields just using "chi-
> squared" to mean a sum of squared errors. So not a formal
> test-statistic for comparing two models?

That is the least problematic part. Before fitting anythng
to anything, one must create a good model -- the
parametrised function to fit, and make sure that function
correctly describes physcial process.

> The various data-manipulations, both in the original paper
> and this one are difficult to follow.

Well, I can help you with those in the original:

   Miller D.C.
   The Ether-Drift Experiment and the Determination of
   the Absolute Motion of the Earth
   Reviews of modern physics, Vol.5, July 1933
   http://ether-wind.narod.ru/Miller_1933/Miller1933_ocr.pdf

I am sure I understand at least them, and that they are
really simple. Ask away or just ask me to recap it for you.

> My guess is that some of the stuff in this paper is
> throwing-out some information about variability in
> whatever "errors" are here.

I beg pardon -- do you mean the paper by Roberts or the one
by Miller (the original)?  I fear that Roberts does it, yes.
Miller, considering the level of statistical science in
1933, did a top-notch job. Both his graphs and results of
mechanical harmonic analysis[1] show a dominance of the
second harmonic in the signal, albeit at a much lower
magnitude that initially expected.

> If this were a simple time series, one mainstream approach
> from "time-series analysis" would be to present a spectral
> analysis of a detrended and prefiltered version of the
> complete timeseries, to try to highlight any remaining
> periodicities. There would seem to be a possibility of
> extending this to remove other systematic effects.

Actually, the sequences of consequtive interferometer "runs"
may be considered as uninterrupted time series, with the
reservation that the data has no time readings, because the
experimenters did not intend it for such analysis. They
averaged the signal between runs for each of the sixteen
orientations. The problem of separating the systematic error
from the signal is quite hard and, in my opinion, requires
an accurately consturcted model, which Roberts seems to
lack.

> I think the key point here is to try to separate-out any
> isolated frequencies that may be of interest, rather than
> to average across a range of neighbouring frequencies, as
> may be going on in this paper.

The second harmonic is of special interest, and I will say
for Roberts that he does try to meausre it in secions II-
III. This question of mine, however, is specifically about
Roberts's statistical model in secion IV.

> To go any further in understanding this one would need to
> have a mathematical description of whatever model is being
> used

If you think Roberts does not provide even this, you confim
my low opinion of his analysis.  I thought that maybe
Roberts was simply too clever for me to understand. If
statisticians fail to understand his article and/or find it
incomplete, then something may be really wrong with it.

> for the full data-set

I think we have to separate the model and the data to which
it is fitted and applied.  Since Roberts's data is
incomplete -- he selected 67 datasheets from different
experiments accoding to undisclosed criteria! -- and as yet
unpublished, I propose to focus on the model per se, that is
the mathematics and method behind it, if any.  I will peruse
futher feedback form statisticians and then share my
criticisms in more detail.

> together with a proper description of what the various
> parameters and error-terms are supposed to mean.

Indeed. I too found them rather muddy, if not internally
contradictory.  Robert's model is:

   singnal(orientation) + system_error(time)

but he seems to be confused about what he means by time. At
one point he says it is the number of the interferometer
revolution, at another he seems to imply that the sequence
of sixteen readings /during/ a revolution is also time.  But
then, this kind of time includes orientation, because,
naturally, the device rotates in time. I therefore fail to
comprehend how this model gurrantees that the singal is not
misinterpreted as part of systematic error.  Also -- where
is random error in the model? All in all, I am utterly
confused by Roberts's model from the start.

> One wonders if an attempt has been made to contact the
> author of the Roberts paper, for better information. A
> straightforward search in a few steps finds:

Yes.  I had a long, yet emotional and unproductive,
discussion with him several years ago on in relativity
newsgroup, where he is still available.  Now, I should like
to discuss his paper in a calmer manner, and with
statisciticians.  Roberts being a physicist, I fear his
statistics are a bit rusty, which is only too bad because
the entire article, being a re-analysis of pre-existing
data, is built primarily upon statisics.

Futhermore, any decent scientific article should be
understandable without additional help form the author, and
contrary to J.J. Lodder -- who absurdly forbids me to
discuss this paper "behind the author's back" -- everyone is
entitiled and encourated to discuss published scientific
articles without the biasing presence of their authors. I
intended to contact Roberts again, after I had acuqired a
better understanding of his model, to be better armed. If we
invite Roberts now, I fear there is going to be much flame
and little argument. I am going to be labeled a "relativity
crank" &c. My honest intent now is to forget about
relativity and discuss statistics.

Thank you for the feedback, David.  I begin to wonder if I
am going to meet a statistician that understands Roberts's
re-analysis, let alone validates his model as self-
consistent and sound. One cannot criticise what one does not
understand.
____________________
1. E.g. Michelson's harmonic analyser:
   https://archive.org/details/pdfy-z5_uTnE-Kga9HKk6

-- 
()  ascii ribbon campaign -- against html e-mail
/\  www.asciiribbon.org   -- against proprietary attachments

Back to sci.stat.math | Previous | Next — Previous in thread | Next in thread | Find similar

Thread

statistics in Roberts. Was: RAW vs. raw image format Rich Ulrich <rich.ulrich@comcast.net> - 2023-02-27 16:00 -0500
  Re: statistics in Roberts. Was: RAW vs. raw image format davidd02@tpg.com.au (David Duffy) - 2023-02-28 07:47 +0000
    Re: statistics in Roberts. Was: RAW vs. raw image format davidd02@tpg.com.au (David Duffy) - 2023-02-28 09:12 +0000
      Re: statistics in Roberts. Was: RAW vs. raw image format davidd02@tpg.com.au (David Duffy) - 2023-03-13 01:23 +0000
        Re: statistics in Roberts. Was: RAW vs. raw image format Anton Shepelev <anton.txt@g{oogle}mail.com> - 2023-03-13 10:32 +0300
        Re: statistics in Roberts. Was: RAW vs. raw image format Anton Shepelev <anton.txt@g{oogle}mail.com> - 2023-03-13 10:58 +0300
          Re: statistics in Roberts. Was: RAW vs. raw image format davidd02@tpg.com.au (David Duffy) - 2023-03-14 04:13 +0000
  Re: statistics in Roberts. Was: RAW vs. raw image format "David Jones" <dajhawkxx@nowherel.com> - 2023-02-28 12:42 +0000
    Re: statistics in Roberts. Was: RAW vs. raw image format nospam@de-ster.demon.nl (J. J. Lodder) - 2023-02-28 14:22 +0100
      Re: statistics in Roberts. Was: RAW vs. raw image format "David Jones" <dajhawkxx@nowherel.com> - 2023-02-28 14:01 +0000
        Re: statistics in Roberts. Was: RAW vs. raw image format nospam@de-ster.demon.nl (J. J. Lodder) - 2023-02-28 15:12 +0100
          Re: statistics in Roberts. Was: RAW vs. raw image format "David Jones" <dajhawkxx@nowherel.com> - 2023-02-28 14:57 +0000
            Re: statistics in Roberts. Was: RAW vs. raw image format nospam@de-ster.demon.nl (J. J. Lodder) - 2023-02-28 21:36 +0100
    Re: statistics in Roberts. Was: RAW vs. raw image format Anton Shepelev <anton.txt@gmail.moc> - 2023-03-04 00:46 +0300
      Re: statistics in Roberts. Was: RAW vs. raw image format nospam@de-ster.demon.nl (J. J. Lodder) - 2023-03-03 23:40 +0100
    Re: statistics in Roberts. Was: RAW vs. raw image format "David Jones" <dajhawkxx@nowherel.com> - 2023-03-09 17:07 +0000
    Re: statistics in Roberts. Was: RAW vs. raw image format Anton Shepelev <anton.txt@gmail.moc> - 2023-03-19 00:41 +0300
      Re: statistics in Roberts. Was: RAW vs. raw image format "David Jones" <dajhawkxx@nowherel.com> - 2023-03-19 00:08 +0000
        Re: statistics in Roberts. Was: RAW vs. raw image format Anton Shepelev <anton.txt@gmail.moc> - 2023-03-20 01:08 +0300
          Re: statistics in Roberts. Was: RAW vs. raw image format "David Jones" <dajhawkxx@nowherel.com> - 2023-03-19 23:14 +0000
            Re: statistics in Roberts. Was: RAW vs. raw image format "David Jones" <dajhawkxx@nowherel.com> - 2023-03-19 23:48 +0000
            Re: statistics in Roberts. Was: RAW vs. raw image format Anton Shepelev <anton.txt@g{oogle}mail.com> - 2023-03-20 11:58 +0300
              Re: statistics in Roberts. Was: RAW vs. raw image format "David Jones" <dajhawkxx@nowherel.com> - 2023-03-20 17:23 +0000
                Re: statistics in Roberts. Was: RAW vs. raw image format Anton Shepelev <anton.txt@gmail.moc> - 2023-03-24 00:11 +0300
                Re: statistics in Roberts. Was: RAW vs. raw image format "David Jones" <dajhawk18xx@@nowhere.com> - 2023-03-23 23:59 +0000
      Re: statistics in Roberts. Was: RAW vs. raw image format Tom Roberts <tjoberts137@sbcglobal.net> - 2023-03-19 14:22 -0500
        Re: statistics in Roberts. Was: RAW vs. raw image format Anton Shepelev <anton.txt@g{oogle}mail.com> - 2023-03-20 14:07 +0300
          Re: statistics in Roberts. Was: RAW vs. raw image format nospam@de-ster.demon.nl (J. J. Lodder) - 2023-03-20 14:35 +0100
            Re: statistics in Roberts. Was: RAW vs. raw image format Anton Shepelev <anton.txt@g{oogle}mail.com> - 2023-03-20 17:01 +0300
          Re: statistics in Roberts. Was: RAW vs. raw image format Tom Roberts <tjoberts137@sbcglobal.net> - 2023-03-20 16:20 -0500
        Re: statistics in Roberts. Was: RAW vs. raw image format nospam@de-ster.demon.nl (J. J. Lodder) - 2023-03-20 14:35 +0100
          Re: statistics in Roberts. Was: RAW vs. raw image format Anton Shepelev <anton.txt@g{oogle}mail.com> - 2023-03-20 17:33 +0300
  Re: statistics in Roberts. Was: RAW vs. raw image format Anton Shepelev <anton.txt@gmail.moc> - 2023-03-03 23:33 +0300
  Re: statistics in Roberts' paper on Miller Tom Roberts <tjoberts137@sbcglobal.net> - 2023-03-05 12:48 -0600
    Re: statistics in Roberts' paper on Miller nospam@de-ster.demon.nl (J. J. Lodder) - 2023-03-05 21:47 +0100
      Re: statistics in Roberts' paper on Miller Tom Roberts <tjoberts137@sbcglobal.net> - 2023-03-08 21:26 -0600
    Re: statistics in Roberts' paper on Miller Rich Ulrich <rich.ulrich@comcast.net> - 2023-03-06 23:08 -0500
      Re: statistics in Roberts' paper on Miller Tom Roberts <tjoberts137@sbcglobal.net> - 2023-03-08 21:40 -0600
    Re: statistics in Roberts' paper on Miller Anton Shepelev <anton.txt@gmail.moc> - 2023-03-08 15:33 +0300
      Re: statistics in Roberts' paper on Miller Tom Roberts <tjoberts137@sbcglobal.net> - 2023-03-08 23:11 -0600
        Re: statistics in Roberts' paper on Miller Anton Shepelev <anton.txt@gmail.moc> - 2023-03-10 01:04 +0300
          Re: statistics in Roberts' paper on Miller Tom Roberts <tjoberts137@sbcglobal.net> - 2023-03-11 12:54 -0600
            Re: statistics in Roberts' paper on Miller Anton Shepelev <anton.txt@gmail.moc> - 2023-03-12 14:25 +0300
              Re: statistics in Roberts' paper on Miller Tom Roberts <tjoberts137@sbcglobal.net> - 2023-03-17 13:27 -0500
                Re: statistics in Roberts' paper on Miller Anton Shepelev <anton.txt@gmail.moc> - 2023-03-19 00:32 +0300
                Re: statistics in Roberts' paper on Miller Tom Roberts <tjoberts137@sbcglobal.net> - 2023-03-19 14:45 -0500
            Re: statistics in Roberts' paper on Miller Tom Roberts <tjoberts137@sbcglobal.net> - 2023-03-20 16:06 -0500
              Re: statistics in Roberts' paper on Miller Anton Shepelev <anton.txt@g{oogle}mail.com> - 2023-03-21 13:00 +0300
    Re: statistics in Roberts' paper on Miller Anton Shepelev <anton.txt@gmail.moc> - 2023-03-08 19:11 +0300
      Re: statistics in Roberts' paper on Miller Anton Shepelev <anton.txt@g{oogle}mail.com> - 2023-03-09 11:48 +0300
        Re: statistics in Roberts' paper on Miller Anton Shepelev <anton.txt@g{oogle}mail.com> - 2023-03-09 11:57 +0300
    Re: statistics in Roberts' paper on Miller Tom Roberts <tjoberts137@sbcglobal.net> - 2023-03-08 21:09 -0600
    Re: statistics in Roberts' paper on Miller "David Jones" <dajhawkxx@nowherel.com> - 2023-03-09 17:13 +0000
      Re: statistics in Roberts' paper on Miller Anton Shepelev <anton.txt@gmail.moc> - 2023-03-09 23:26 +0300
        Re: statistics in Roberts' paper on Miller "David Jones" <dajhawkxx@nowherel.com> - 2023-03-10 01:37 +0000
          Re: statistics in Roberts' paper on Miller nospam@de-ster.demon.nl (J. J. Lodder) - 2023-03-10 11:25 +0100
          Re: statistics in Roberts' paper on Miller Anton Shepelev <anton.txt@gmail.moc> - 2023-03-11 00:13 +0300
          Re: statistics in Roberts' paper on Miller Tom Roberts <tjoberts137@sbcglobal.net> - 2023-03-10 15:42 -0600
            Re: statistics in Roberts' paper on Miller Anton Shepelev <anton.txt@gmail.moc> - 2023-03-11 01:32 +0300
              Re: statistics in Roberts' paper on Miller - Data Tom Roberts <tjoberts137@sbcglobal.net> - 2023-03-11 12:18 -0600
                Re: statistics in Roberts' paper on Miller - Data Anton Shepelev <anton.txt@gmail.moc> - 2023-03-12 00:13 +0300
                Re: statistics in Roberts' paper on Miller - Data Anton Shepelev <anton.txt@gmail.moc> - 2023-03-20 00:38 +0300
        Re: statistics in Roberts' paper on Miller Tom Roberts <tjoberts137@sbcglobal.net> - 2023-03-10 15:25 -0600
          Re: statistics in Roberts' paper on Miller Anton Shepelev <anton.txt@gmail.moc> - 2023-03-12 00:01 +0300
      Re: statistics in Roberts' paper on Miller Tom Roberts <tjoberts137@sbcglobal.net> - 2023-03-10 15:10 -0600
    Re: statistics in Roberts' paper on Miller Anton Shepelev <anton.txt@gmail.moc> - 2023-03-11 01:14 +0300
      Re: statistics in Roberts' paper on Miller Tom Roberts <tjoberts137@sbcglobal.net> - 2023-03-11 13:08 -0600
        Re: statistics in Roberts' paper on Miller Anton Shepelev <anton.txt@gmail.moc> - 2023-03-12 01:51 +0300
    Re: statistics in Roberts' paper on Miller "David Jones" <dajhawkxx@nowherel.com> - 2023-03-15 17:10 +0000
      Re: statistics in Roberts' paper on Miller nospam@de-ster.demon.nl (J. J. Lodder) - 2023-03-15 22:36 +0100
        Re: statistics in Roberts' paper on Miller "David Jones" <dajhawk18xx@@nowhere.com> - 2023-03-15 22:18 +0000
          Re: statistics in Roberts' paper on Miller nospam@de-ster.demon.nl (J. J. Lodder) - 2023-03-15 23:28 +0100
      Re: statistics in Roberts' paper on Miller Tom Roberts <tjoberts137@sbcglobal.net> - 2023-03-19 13:46 -0500
        Re: statistics in Roberts' paper on Miller "David Jones" <dajhawkxx@nowherel.com> - 2023-03-19 22:57 +0000
          Re: statistics in Roberts' paper on Miller Anton Shepelev <anton.txt@g{oogle}mail.com> - 2023-03-20 12:05 +0300

csiph-web