Hi John and thanks for the response - I posted the question for the sake of
other users, but also because I had written to the developer, Mark Handcock,
in the past with no response.
Since the example of ruf.fit in the ruf package of R uses data from one
individual jay (d412), and since as you say 250m would be correct in the jay
cases, why does the R example start with 0.2?? I once asked you this
question and you speculated that perhaps it was in kilometer units, so it
would seem that few save Mark Handcock are in a position to really verify
this. There is no reference to the units of theta in the help vignette,
only a reference to your 2004 paper, which speaks of meters for the spatial
range parameter.
Tyler
On Mon, Jul 26, 2010 at 1:55 PM, John Marzluff <cor...@u.washington.edu>wrote:
> Hi Tyler It is a starting point and the program iterates from that start.
> It is in meters and we often use the smoothing parameter from the kernel
> estimator at the starting estimate. 250 would be correct in the jay cases.
> John
>
> ----- Original Message -----
> *From:* Tyler Dean Rudolph <tylerdeanrudo...@gmail.com>
> *To:* r-sig-geo@stat.math.ethz.ch
> *Cc:* Mark S. Handcock <handc...@stat.washington.edu> ; John M.
> Marzluff<cor...@u.washington.edu>
> *Sent:* Monday, July 26, 2010 10:04 AM
> *Subject:* spatial range parameter in ruf.fit (package ruf)
>
> Two parameters are required in order to fit a Resource Utilization Function
> to spatial attribute data using ruf.fit, 1) *spatial range* and 2)
> smoothness (theta). With regard to the spatial range parameter, rho,
> Marzluff et al. (2004) state this to be the range of spatial dependence in
> *metres*. Concordingly, Hepinstall, Marzluff et al. (in Resource
> Selection Methods & Applications, S. Huzurbazar, ed.) provide an example of
> an RUF fit with a spatial range of *250m*. This being said, in the
> example of ruf.fit provided in the ruf package (d412.fit), the estimate (
> hval[1]) provided is *0.2*, a seemingly different order of magnitude.
>
> Could someone please explain this discrepancy for the sake of clarity?
> This would be much appreciated!
>
> Tyler
>
>
[[alternative HTML version deleted]]
_______________________________________________
R-sig-Geo mailing list
R-sig-Geo@stat.math.ethz.ch
https://stat.ethz.ch/mailman/listinfo/r-sig-geo
