[GRASS-stats] gstat error

[Roger Bivand]

On Fri, 19 Jun 2009, Jarosław Jasiewicz wrote:

> Hi
> Another gstat error:
>
> var.krigged=krige(z~x+y,gr,grid,model=var.fitted)
> [using universal kriging]
>
> "chfactor.c", line 130: singular matrix in function LDLfactor()
> Error in predict.gstat(g, newdata = newdata, block = block, nsim = nsim,  :
> LDLfactor
>

Hi,

Please try ordinary kriging first. I'm pretty sure this has to do with the 
fact that gr$x and gr$y show very little variation. When you do trend 
surface, the underlying methods shift the coordinates to the unit square 
(or similar) to avoid the numerical deterioration that occurs otherwise. 
You could also use elide() in maptools to shift the data manually, but do 
do the same on gr and grid.

Hope this helps,

Roger

>
> regards
> Jarek
>
> here is structure of my gr spatialPointsDataFrame used in analysis:
>
> str(gr)
> Formal class 'SpatialPointsDataFrame' [package "sp"] with 5 slots
> ..@ data       :'data.frame':    2201 obs. of  5 variables:
> .. ..$ cat: num [1:2201] 2 3 4 5 6 7 8 9 10 11 ...
> .. ..$ naz: Factor w/ 874 levels "1000","1001",..: 874 1 2 3 4 5 6 7 8 9 ...
> .. ..$ x  : num [1:2201] 360175 360176 360178 360169 360167 ...
> .. ..$ y  : num [1:2201] 512736 512736 512733 512719 512712 ...
> .. ..$ z  : num [1:2201] 86.5 87.4 87.7 86.9 86 ...
> ..@ coords.nrs : num(0)
> ..@ coords     : num [1:2201, 1:2] 360175 360176 360178 360169 360167 ...
> .. ..- attr(*, "dimnames")=List of 2
> .. .. ..$ : NULL
> .. .. ..$ : chr [1:2] "coords.x1" "coords.x2"
> ..@ bbox       : num [1:2, 1:2] 359907 512481 360492 512778
> .. ..- attr(*, "dimnames")=List of 2
> .. .. ..$ : chr [1:2] "coords.x1" "coords.x2"
> .. .. ..$ : chr [1:2] "min" "max"
> ..@ proj4string:Formal class 'CRS' [package "sp"] with 1 slots
> .. .. ..@ projargs: chr " +proj=tmerc +lat_0=0 +lon_0=19 +k=0.9993 
> +x_0=500000 +y_0=-5300000 +no_defs +a=6378137 +rf=298.257222101 
> +towgs84=0.000,0.000,"| __truncated__
>
> and newdata grid:
> str(grid)
> Formal class 'SpatialGridDataFrame' [package "sp"] with 6 slots
> ..@ data       :'data.frame':    131352 obs. of  1 variable:
> .. ..$ region2: int [1:131352] NA NA NA NA NA NA NA NA NA NA ...
> ..@ grid       :Formal class 'GridTopology' [package "sp"] with 3 slots
> .. .. ..@ cellcentre.offset: Named num [1:2] 359902 512478
> .. .. .. ..- attr(*, "names")= chr [1:2] "x" "y"
> .. .. ..@ cellsize         : num [1:2] 1.001 0.998
> .. .. ..@ cells.dim        : int [1:2] 421 312
> ..@ grid.index : int(0)
> ..@ coords     : num [1:2, 1:2] 359902 360322 512478 512788
> .. ..- attr(*, "dimnames")=List of 2
> .. .. ..$ : NULL
> .. .. ..$ : chr [1:2] "x" "y"
> ..@ bbox       : num [1:2, 1:2] 359901 512477 360323 512789
> .. ..- attr(*, "dimnames")=List of 2
> .. .. ..$ : chr [1:2] "x" "y"
> .. .. ..$ : chr [1:2] "min" "max"
> ..@ proj4string:Formal class 'CRS' [package "sp"] with 1 slots
> .. .. ..@ projargs: chr " +proj=tmerc +lat_0=0 +lon_0=19 +k=0.9993 
> +x_0=500000 +y_0=-5300000 +no_defs +a=6378137 +rf=298.257222101 
> +towgs84=0.000,0.000,"| __truncated__
> _______________________________________________
> grass-stats mailing list
> grass-stats at lists.osgeo.org
> http://lists.osgeo.org/mailman/listinfo/grass-stats
>

-- 
Roger Bivand
Economic Geography Section, Department of Economics, Norwegian School of
Economics and Business Administration, Helleveien 30, N-5045 Bergen,
Norway. voice: +47 55 95 93 55; fax +47 55 95 95 43
e-mail: Roger.Bivand at nhh.no