Re: Errors of error models. Who is following this and who is confused,


Dr. David Kirkby from Kirkby Microwave Ltd <drkirkby@...>
 

On Sun, 29 Sep 2019 at 14:29, <erik@kaashoek.com> wrote:

I'm assuming (based on my over 40 years ago systems modeling lessons) they
are making a numeric model to translate uncertainties/noise in one domain
into the measurement outcome domain so you can interpret the level of
(un)certainty in you measurements.
I am unable use to the provided documents

I don’t see any document they have provided - plenty of links to other
tools, but I am still at a loss of knowing much about what they are
actually doing.

or tools (for sure have no plans to install a fortran compiler)


I have gcc installed on my Sun, with support for Fortran built in. I
downloaded the Fortran source code and attempted to compile it. The GCC
version I have does not recognise it as Fortran. I am not a Fortran
programmer myself, but the code a bit like Fortran.

There are no significant comments in the Fortran source code, so I didn’t
bother looking any more. There are some data files too, but there’s no
mention of how to use them.


If above statement from me is correct would it be possible to have a
statistical error model of the measured raw data and then use a monte carlo
simulation to estimate the uncertainty in the to be measured data?

I expect a Monte Carlo simulation is a good way to go. All the
uncertainties I have seen for instruments are based on a statistical model,
expressed as a confidence level (typically 95%). Monte Carlo methods are
good for that.

However, I believe that they are taking a purely analytical approach. Files
have been distributed for Maxima which is a symbolic computational program.
Also Mathematics too.


(40 years is a long time so I may be wrong here)
Anyway, I'd like to contribute if possible by providing measurements in
some form but by mathematics are no longer fit for any real contribution.

Hopefully you can make a useful contribution. Personally I am going to give
up unless I can see a written description of the aims and methodology.

Dave.
--
Dr. David Kirkby,
Kirkby Microwave Ltd,
drkirkby@kirkbymicrowave.co.uk
https://www.kirkbymicrowave.co.uk/
Telephone 01621-680100./ +44 1621 680100

Registered in England & Wales, company number 08914892.
Registered office:
Stokes Hall Lodge, Burnham Rd, Althorne, Chelmsford, Essex, CM3 6DT, United
Kingdom

Join nanovna-users@groups.io to automatically receive all group messages.