[R] Time Series Decomposition On Zoo Objects: Errors

Roy Mendelssohn roy.mendelssohn at noaa.gov
Fri Apr 4 00:04:15 CEST 2014


The state-space approach has the advantage in the appropriate situations that  you can model the trends and seasonals and cycles in a way that doesn't assume stationarity and provides a lot of flexibility.  To me a lot of it depends on if the nature of the irregularity is an inherent property of the data themselves or of the observation process - for example if it makes sense to say the physical observable is there every month but we just have not been able to observe.  I have fit state-space models to reasonably sparse data with what appear to be good results.  

If you want I can send you some examples off-line.

-Roy


On Apr 3, 2014, at 2:54 PM, Rich Shepard <rshepard at appl-ecosys.com> wrote:

> On Thu, 3 Apr 2014, Roy Mendelssohn wrote:
> 
>> How irregular is irregular. kalman filter based methods, such as those in
>> KFAS and DLM, can handle missing data, and often "irregular" data can be
>> thought of as regular data with missing values, A lot depends on how
>> irregular and how big the gaps, to the point where the analysis can be
>> calculated but is not very meaningful.
> 
> Roy,
> 
>  The degree of irregularity varies with the data set. It varies greatly.
> Sometimes, monthly samples are missed because the streambed is dry, or
> because there are several meters of snow on top of the channel. Sometimes
> regulators have permit holders stop analyzing for a chemical constituent,
> then there's an agency staff change and that constituent is back on the list
> of chemicals to be monitored. Some times fish are present, other times
> they're not.
> 
>> Don't know if this helps.
> 
>  Yes, it does. I'll read up on Kalman filters, on state-space models with
> missing data modifications in Shumway & Stoffer (3rd Ed.), and on gamm.
> 
> Thanks,
> 
> Rich
> 
> ______________________________________________
> R-help at r-project.org mailing list
> 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.

**********************
"The contents of this message do not reflect any position of the U.S. Government or NOAA."
**********************
Roy Mendelssohn
Supervisory Operations Research Analyst
NOAA/NMFS
Environmental Research Division
Southwest Fisheries Science Center
1352 Lighthouse Avenue
Pacific Grove, CA 93950-2097

e-mail: Roy.Mendelssohn at noaa.gov (Note new e-mail address)
voice: (831)-648-9029
fax: (831)-648-8440
www: http://www.pfeg.noaa.gov/

"Old age and treachery will overcome youth and skill."
"From those who have been given much, much will be expected" 
"the arc of the moral universe is long, but it bends toward justice" -MLK Jr.




More information about the R-help mailing list