variogramST does not like STIDF

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

variogramST does not like STIDF

sytbru
Dear all,



I intend to compute a space-time variogram from irregularly spaced data. I created a STIDF object for that (package stacetime), but gstat's function "variogram" only seems to only accept STSDF or STFDF objects as data. The following message was generated: Error: is(data, "STFDF") || is(data, "STSDF") is not TRUE. A solution would be to first coerce the STIDF to STSDF --which is wat I am doing-- but is there a reason why variogram does not accept STIDF?



Thanks,

Sytze

_______________________________________________
R-sig-Geo mailing list
[hidden email]
https://stat.ethz.ch/mailman/listinfo/r-sig-geo
Reply | Threaded
Open this post in threaded view
|

Re: variogramST does not like STIDF

edzer


On 10/04/2012 04:54 PM, Bruin, Sytze de wrote:
> Dear all,
>
>
>
> I intend to compute a space-time variogram from irregularly spaced data. I created a STIDF object for that (package stacetime), but gstat's function "variogram" only seems to only accept STSDF or STFDF objects as data. The following message was generated: Error: is(data, "STFDF") || is(data, "STSDF") is not TRUE. A solution would be to first coerce the STIDF to STSDF --which is wat I am doing-- but is there a reason why variogram does not accept STIDF?
>
Sytze,

The reason is that nobody has implemented it, so far, and this is the
first time someone asks.

When you're done coercing, please let me know whether you still think
there is a need for computing variograms from STIDF data.
--
Edzer Pebesma
Institute for Geoinformatics (ifgi), University of Münster
Weseler Straße 253, 48151 Münster, Germany. Phone: +49 251
8333081, Fax: +49 251 8339763  http://ifgi.uni-muenster.de
http://www.52north.org/geostatistics      [hidden email]

_______________________________________________
R-sig-Geo mailing list
[hidden email]
https://stat.ethz.ch/mailman/listinfo/r-sig-geo
Reply | Threaded
Open this post in threaded view
|

Re: variogramST does not like STIDF

sytbru
In reply to this post by sytbru
Hi Edzer,

Thanks for your answer!
After the lengthy computation of the variogram (> 65000 observations) on the data that were coerced from STIDF to STSDF, a warning was issued that fixed distances were assumed, which may indicate that I did something wrong. If so, a separate method for STIDF data would be welcome!
In the meantime, I implemented a primitive R script computing an ST variogram for data irregularly spaced in space and time, allowing different lag boundaries for space and time (which is still running).

Best,
Sytze de Bruin
_______________________________________________
R-sig-Geo mailing list
[hidden email]
https://stat.ethz.ch/mailman/listinfo/r-sig-geo
Reply | Threaded
Open this post in threaded view
|

Re: variogramST does not like STIDF

edzer


On 10/05/2012 03:13 PM, Bruin, Sytze de wrote:
> Hi Edzer,
>
> Thanks for your answer!
> After the lengthy computation of the variogram (> 65000 observations) on the data that were coerced from STIDF to STSDF, a warning was issued that fixed distances were assumed, which may indicate that I did something wrong. If so, a separate method for STIDF data would be welcome!

It indicates that your time points are irregular, but are taken as
(coerced to) regular. If your time points are nearly regular, this is no
problem.

> In the meantime, I implemented a primitive R script computing an ST variogram for data irregularly spaced in space and time, allowing different lag boundaries for space and time (which is still running).

Great; if it works, please consider contributing it!
>
> Best,
> Sytze de Bruin
> _______________________________________________
> R-sig-Geo mailing list
> [hidden email]
> https://stat.ethz.ch/mailman/listinfo/r-sig-geo
>

--
Edzer Pebesma
Institute for Geoinformatics (ifgi), University of Münster
Weseler Straße 253, 48151 Münster, Germany. Phone: +49 251
8333081, Fax: +49 251 8339763  http://ifgi.uni-muenster.de
http://www.52north.org/geostatistics      [hidden email]

_______________________________________________
R-sig-Geo mailing list
[hidden email]
https://stat.ethz.ch/mailman/listinfo/r-sig-geo