[R-sig-Geo] [OT?] time-series community?

[Tom Gottfried]

Tom,

their is a Task View "TimeSeries" on CRAN. And textbooks exist on that 
topic using R. E.g.

Cryer, Jonathan D., und Kung-Sik Chan. Time Series Analysis: With 
Applications in R. 2nd Aufl. Springer, 2009.

Metcalfe, Andrew V., und Paul S.P. Cowpertwait. Introductory Time Series 
with R. Use R! New York, NY: Springer New York, 2009. 
http://www.springerlink.com/content/978-0-387-88697-8/#section=58375&page=1.

HTH,
Tom

Am 15.09.2012 00:33, schrieb Tom Roche:
>
> Dunno if this is the place to ask, but I'd appreciate pointers toward
> learning about, and channels for asking questions about, analysis of
> time series for evaluating model/obs fits. What I mean:
>
> I'm a student working on process-modeling atmospheric N2O concentrations
> over the contiguous US (CONUS), comparing hourly predictions to
> daily observations at 4 towers. Sad, but there's just not much data.
> And it gets worse! the N2O emissions inventories (EIs) driving the model
> are currently annual, monthly, or daily. (Fortunately, both EIs and
> datasets are improving; increased modeling may incent increased effort.)
>
> Hence I'll want (once I get the model running, which seems imminent) to
> test the time series of predictions against the time series of obs at
> the tower locations. I'd like to test imposed temporalities, e.g.,
>
> * model vs obs with imposed diurnality (so as to test hourly vs hourly)
>
> * feeding EIs with imposed seasonality and diurnality to the model,
>    comparing those predictions vs obs
>
> Unfortunately my background is computer science, not physical science:
> I know a bit about techniques like calculating standard deviation of
> biases, still less about applying autocorrelation functions (e.g. acf,
> pacf), and have only read wikipedia about AIC/AICc. I'm very much
> interested in learning more, and would appreciate pointers toward
>
> * resources (esp cookbooks and tutorials :-)
>
> * places to ask when one encounters problems
>
> that would assist me in practical application of tools (esp R-based
> ones) in this domain.
>
> Feel free to reply on- or off-list, Tom Roche<Tom_Roche at pobox.com>
>
> _______________________________________________
> R-sig-Geo mailing list
> R-sig-Geo at r-project.org
> https://stat.ethz.ch/mailman/listinfo/r-sig-geo

-- 
Indo-German Centre for Sustainability
Indian Institute of Technology Madras
600 036 Chennai, India
www.igcs-chennai.org