Fitting Production Curves

classic Classic list List threaded Threaded
2 messages Options
Reply | Threaded
Open this post in threaded view
|

Fitting Production Curves

R help mailing list-2
Hi All,

By a production curve I mean for example the output of a mine, peak oil production or the yield of a farm over time within the same season. It is this last example that we should take as the prototypical case.

What I would like to do is to fit a curve that inherits qualities of the discrete production data (such as area of the curve equaling the total production for the season). Fitting a curve with least squares (such as a Gaussean or Hubbert) presents some issues (with regards to accuracy of inherited features). My next logical attempt would be to fit a sum of curves, such as a Fourier or Wavelet sum. Perhaps there is something simpler or more flexible in the way I am thinking?

My question is:

1. What would be an effective approach be to fit generalised production curves?
2. If a Wavelet sum is one of the best approaches, what would be a good way of implementing such curve fitting (including calculated coefficients) in R?
3. Is there anything else or another way that I should rather be thinking about this instead?

Best regards
Phillip-Jan van Zyl
MSc Mathematics, Stellenbosch

______________________________________________
[hidden email] mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Reply | Threaded
Open this post in threaded view
|

Re: Fitting Production Curves

Bert Gunter-2
This list doesn't do statistics -- it does R programming, though statistics
does occur incidentally sometimes in that context. Not in your post
though. You should post on a statistics site like stats.stackexchange.com
for statistics questions.

Cheers,
Bert

Bert Gunter

"The trouble with having an open mind is that people keep coming along and
sticking things into it."
-- Opus (aka Berkeley Breathed in his "Bloom County" comic strip )


On Thu, Sep 20, 2018 at 10:38 PM mikorym via R-help <[hidden email]>
wrote:

> Hi All,
>
> By a production curve I mean for example the output of a mine, peak oil
> production or the yield of a farm over time within the same season. It is
> this last example that we should take as the prototypical case.
>
> What I would like to do is to fit a curve that inherits qualities of the
> discrete production data (such as area of the curve equaling the total
> production for the season). Fitting a curve with least squares (such as a
> Gaussean or Hubbert) presents some issues (with regards to accuracy of
> inherited features). My next logical attempt would be to fit a sum of
> curves, such as a Fourier or Wavelet sum. Perhaps there is something
> simpler or more flexible in the way I am thinking?
>
> My question is:
>
> 1. What would be an effective approach be to fit generalised production
> curves?
> 2. If a Wavelet sum is one of the best approaches, what would be a good
> way of implementing such curve fitting (including calculated coefficients)
> in R?
> 3. Is there anything else or another way that I should rather be thinking
> about this instead?
>
> Best regards
> Phillip-Jan van Zyl
> MSc Mathematics, Stellenbosch
>
> ______________________________________________
> [hidden email] mailing list -- To UNSUBSCRIBE and more, see
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
> http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>

        [[alternative HTML version deleted]]

______________________________________________
[hidden email] mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.