![]() |
News from da outaworlds |
mail files register groups login |
Message-ID: |
Subject | Author |
![]() | David Duffy |
![]() ![]() | Anton Shepelev |
![]() ![]() | Anton Shepelev |
1 |
In sci.stat.math David Duffy <davidd02@tpg.com.au> wrote:
> In sci.stat.math David Duffy <davidd02@tpg.com.au> wrote:
>>
>> This is a quick and dirty analysis in the R stats package.
>
> I was too quick quick in writing this - I needed to unpack those
> degrees of freedom into a linear decline over the rotation, due
> to the overall drift, which explains most of that signal,
> and the actual bump at 180 degrees. If I instead fit a polynomial term,
I have put the resulting plots up at
http://users.tpg.com.au/davidd02/
I smoothed the trends in the data using localized regression separately
for each time the inferometer was readjusted, and have plotted the
resulting residuals. They appear roughly the same as Miller's plot. For
one formal test, I have fitted a random intercept model for the (20)
rotations, along with a fixed effects linear decline within the rotation,
and then added higher degree polynomials to show a weakly significant
non-linear term.
Cheers, David Duffy.
David Duffy:
> I have put the resulting plots up at
> http://users.tpg.com.au/davidd02/
Thank you very much, David. Your great, clean, and pure-
HTML blog is an eye-cake.
> I smoothed the trends in the data using localized
> regression separately for each time the inferometer was
> readjusted,
Mr. Roberts "sewed" the entire run (20 turns) into a single
sequence of observations by joining the ends of adjustment
turns. Would it not be a better thing to do, yielding a
single analysable sequence?
> For one formal test, I have fitted a random intercept
> model for the (20) rotations, along with a fixed effects
> linear decline within the rotation, and then added higher
> degree polynomials to show a weakly significant non-linear
> term.
How did you determine the phase and amplitude of the signal
that you write "Miller was hoping for"? Altough it requries
additional work, the time and amplitude of the expected
signal may be estimated knowing the time and latitude.
Observe also that Mr. Roberts has uploaded the enire dataset
he used for his article:
https://www.dropbox.com/sh/8z5svuenaabegoq/AAAPrjK9AOqP-yyPRr5wNBwra?dl=0
--
() ascii ribbon campaign -- against html e-mail
/\ www.asciiribbon.org -- against proprietary attachments
David Duffy:
> [http://users.tpg.com.au/davidd02/]
> For one formal test, I have fitted a random intercept
> model for the (20) rotations, along with a fixed effects
> linear decline within the rotation, and then added higher
> degree polynomials to show a weakly significant non-linear
> term.
I have a question about your plot of detrended data: why do
some rotations start at marker 1 and some at marker 0? This
may have to do with adjustment rotations, and marker 0 is
the same orientation as marker 16, but still I think the
sine should be fitted to a sequences of sixteen observations
at sixteen markers, not seventeen. The extra marker should
be used to take adjustments into account.
--
() ascii ribbon campaign -- against html e-mail
/\ www.asciiribbon.org -- against proprietary attachments
1 |